modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-29 00:46:34
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 502
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-29 00:44:25
| card
stringlengths 11
1.01M
|
---|---|---|---|---|---|---|---|---|---|
gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2 | gyr66 | 2024-01-09T14:55:47Z | 74 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"token-classification",
"generated_from_trainer",
"custom_code",
"zh",
"dataset:gyr66/privacy_detection",
"base_model:gyr66/RoBERTa-ext-large-chinese-finetuned-ner",
"base_model:finetune:gyr66/RoBERTa-ext-large-chinese-finetuned-ner",
"autotrain_compatible",
"region:us"
] | token-classification | 2024-01-09T13:44:15Z | ---
base_model: gyr66/RoBERTa-ext-large-chinese-finetuned-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Ernie-3.0-large-crf-chinese-finetuned-ner
results: []
datasets:
- gyr66/privacy_detection
language:
- zh
library_name: transformers
pipeline_tag: token-classification
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RoBERTa-ext-large-crf-chinese-finetuned-ner
This model is a fine-tuned version of [gyr66/RoBERTa-ext-large-chinese-finetuned-ner](https://huggingface.co/gyr66/RoBERTa-ext-large-chinese-finetuned-ner) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5907
- Precision: 0.7278
- Recall: 0.75
- F1: 0.7387
- Accuracy: 0.9629
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0061 | 1.0 | 503 | 0.6739 | 0.6747 | 0.7457 | 0.7084 | 0.9608 |
| 0.0078 | 2.0 | 1006 | 0.6343 | 0.7083 | 0.7518 | 0.7294 | 0.9622 |
| 0.0072 | 3.0 | 1509 | 0.6237 | 0.6867 | 0.7621 | 0.7224 | 0.9607 |
| 0.0052 | 4.0 | 2012 | 0.5929 | 0.7136 | 0.7616 | 0.7368 | 0.9635 |
| 0.0031 | 5.0 | 2515 | 0.5907 | 0.7278 | 0.75 | 0.7387 | 0.9629 |
| 0.0014 | 6.0 | 3018 | 0.6080 | 0.7172 | 0.7558 | 0.7360 | 0.9636 |
| 0.001 | 7.0 | 3521 | 0.6179 | 0.7198 | 0.7586 | 0.7387 | 0.9637 |
| 0.0005 | 8.0 | 4024 | 0.6208 | 0.7211 | 0.7518 | 0.7361 | 0.9632 |
| 0.0004 | 9.0 | 4527 | 0.6169 | 0.7271 | 0.7487 | 0.7378 | 0.9636 |
| 0.0002 | 10.0 | 5030 | 0.6202 | 0.7266 | 0.7495 | 0.7379 | 0.9636 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0 |
mmnga/baku-10b-chat-v2-gguf | mmnga | 2024-01-09T14:55:39Z | 184 | 0 | null | [
"gguf",
"llama",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-01-09T12:47:24Z | ---
license: apache-2.0
tags:
- llama
---
# baku-10b-chat-v2-gguf
[sudy-superさんが公開しているbaku-10b-chat-v2](https://huggingface.co/sudy-super/baku-10b-chat-v2)のggufフォーマット変換版です。
他のモデルはこちら
[mmnga/baku-10b-gguf](https://huggingface.co/mmnga/baku-10b-gguf)
[mmnga/baku-13b-v2-gguf](https://huggingface.co/mmnga/baku-13b-v2-gguf)
[mmnga/baku-10b-chat-v2-gguf](https://huggingface.co/mmnga/baku-10b-chat-v2-gguf)
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'baku-10b-chat-v2-q4_0.gguf' -p 'USER:仕事の熱意を取り戻すためのアイデアを5つ挙げてください。 ASSISTANT:' -n 100 --temp 0.8
``` |
jysssacc/roberta-base_lora_lr5e-05_bs4_epoch5_wd0.01 | jysssacc | 2024-01-09T14:55:39Z | 1 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:adapter:FacebookAI/roberta-base",
"license:mit",
"region:us"
] | null | 2024-01-09T14:49:54Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: roberta-base
model-index:
- name: roberta-base_lora_lr5e-05_bs4_epoch5_wd0.01
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base_lora_lr5e-05_bs4_epoch5_wd0.01
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9767
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 19.1905 | 1.0 | 157 | 13.0895 |
| 5.1439 | 2.0 | 314 | 4.1232 |
| 3.8429 | 3.0 | 471 | 2.7016 |
| 2.6318 | 4.0 | 628 | 2.1310 |
| 2.3486 | 5.0 | 785 | 1.9767 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0 |
aiflows/AbstractBossFlowModule | aiflows | 2024-01-09T14:27:53Z | 0 | 0 | null | [
"region:us"
] | null | 2024-01-09T14:27:44Z | # Table of Contents
* [AbstractBossFlow](#AbstractBossFlow)
* [AbstractBossFlow](#AbstractBossFlow.AbstractBossFlow)
* [instantiate\_from\_config](#AbstractBossFlow.AbstractBossFlow.instantiate_from_config)
* [run](#AbstractBossFlow.AbstractBossFlow.run)
* [CtrlExMemFlow](#CtrlExMemFlow)
* [CtrlExMemFlow](#CtrlExMemFlow.CtrlExMemFlow)
* [detect\_finish\_or\_continue](#CtrlExMemFlow.CtrlExMemFlow.detect_finish_or_continue)
* [\_\_init\_\_](#__init__)
<a id="AbstractBossFlow"></a>
# AbstractBossFlow
<a id="AbstractBossFlow.AbstractBossFlow"></a>
## AbstractBossFlow Objects
```python
class AbstractBossFlow(SequentialFlow, ABC)
```
This class is an abstraction of memory-planner-controller-executor flow. At a higher level, it is
an abstract agent empowered by multiple language models and subsequent tools like code interpreters, etc.
It is designed to cooperate with memory management mechanisms, lm-powered planner and controller, and
arbitrary executors.
*Configuration Parameters*
- `name` (str): Name of the flow.
- `description` (str): Description of the flow.
- `memory_files` (dict): A dictionary of memory files. The keys are the names of the memory files and the values
are the path to the memory files. Typical memory files include plan, logs, code library.
- `subflows_config`:
- MemoryReading: reads the content of the memory files into the flow states for later use.
- Planner: make a step-by-step plan based on the current goal.
- CtrlExMem: controller-executor agent with memory reading and memory writing, it will execute the plan generated by the planner.
- `early_exit_key` (str): The key in the flow state that indicates the early exit condition.
- `topology` (list) : The topology of the flow.
*Input Interface (expected input)*
- `goal` (str): The goal from the caller (source flow)
*Output Interface (expected output)*
- `result` (str): The result of the flow, the result will be returned to the caller.
- `summary` (str): The summary of the flow, the summary will be logged into the logs of the caller flow.
**Arguments**:
- `memory_files` (`dict`): A dictionary of memory files. The keys are the names of the memory files and the values are the path to the memory files.
<a id="AbstractBossFlow.AbstractBossFlow.instantiate_from_config"></a>
#### instantiate\_from\_config
```python
@classmethod
def instantiate_from_config(cls, config)
```
This method instantiates the flow from a configuration dictionary.
**Arguments**:
- `config` (`dict`): The configuration dictionary.
<a id="AbstractBossFlow.AbstractBossFlow.run"></a>
#### run
```python
def run(input_data: Dict[str, Any]) -> Dict[str, Any]
```
This method runs the flow.
**Arguments**:
- `input_data` (`dict`): The input data, the input_data is supposed to contain 'goal'
<a id="CtrlExMemFlow"></a>
# CtrlExMemFlow
<a id="CtrlExMemFlow.CtrlExMemFlow"></a>
## CtrlExMemFlow Objects
```python
class CtrlExMemFlow(CircularFlow, ABC)
```
This class is the controller-executor agent with memory reading and memory writing, it will execute the plan
generated by the planner. This flow is, at a higher level, a circular flow, it runs until either max_round is
reached, or the controller decides to early exit (see: detect_finish_or_continue)
The brain of the flow is the controller, the controller decides what action (which branch of the branching flow)
to take next. The controller can also decide to early exit the flow, in which case the flow will stop. After the
controller decides what action to take, the controller will pass the action to the executor, the executor will
execute the action, yielding `result` and `summary`, which respectively will be passed to the controller and the
memory writer (into logs of the upper layer of flow). Depending on the `result`, the controller will decide what
action to take next.
*Configuration Parameters*:
- `name` (str): Name of the flow.
- `description` (str): Description of the flow.
- `max_round` (int): The maximum number of rounds the flow will run. Default: 30.
- `subflows_config` (dict): The configuration of the subflows.
- `Controller` (dict): The configuration of the controller. It is important that the target of the controller (instance customizable by the user) and the api information should be specified.
- `Executor` (dict): The executor of the flow, it is supposed to be a branching flow. To instantiate the executor, the user needs to specify the subflows of the executor (i.e. the actual tools that can be used by the agent, e.g. a flow for interpreting code)
- `MemoryWriting` (dict): The configuration of the memory writer. There is an existing memory writing flow implemented.
- 'MemoryReading' (dict): The configuration of the memory reader. There is an existing memory reading flow implemented.
- `topology` (List): The topology of the subflows, notice that the output interface of the Controller must be implemented and specified.
*Input Interface*:
- `plan` (str): The plan generated by the planner, the CtrlExMem flow should follow the plan.
- `memory_files` (dict): mem_name - memfile_path pairs, the memory files that the memory reader will read from.
- `goal` (str): The goal of the flow
- `logs` (str): Execution history of the flow, contains all actions taken by each subflow of the flow.
*Output Interface*:
- `result` (str): The result of the flow, will be returned to the controller of the caller flow.
- `summary` (str): The summary of the flow, will be written to the logs of the caller flow.
<a id="CtrlExMemFlow.CtrlExMemFlow.detect_finish_or_continue"></a>
#### detect\_finish\_or\_continue
```python
@abstractmethod
@CircularFlow.output_msg_payload_processor
def detect_finish_or_continue(output_payload: Dict[str, Any],
src_flow) -> Dict[str, Any]
```
This function is called after the Controller, it is used to:
1. Check if the Controller decides to early-exit, if so, implement necessary logics for exiting e.g. drafting result and summary, etc.
2. For other commands called by the controller, implement necessary logics for the flow to continue e.g. providing necessary information to the branching flow.
**Arguments**:
- `output_payload` (`Dict[str, Any]`): The output payload of the Controller.
- `src_flow` (`Flow`): The source flow of the Controller.
**Returns**:
The input payload of the Executor.
<a id="__init__"></a>
# \_\_init\_\_
|
NLPProject2023Z/xlnet-regression | NLPProject2023Z | 2024-01-09T14:26:59Z | 118 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2024-01-09T14:26:36Z | ---
tags:
- generated_from_trainer
model-index:
- name: xlnet-regression
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlnet-regression
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3743
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 50
- eval_batch_size: 50
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 80 | 0.3743 |
| No log | 2.0 | 160 | 0.3747 |
| No log | 3.0 | 240 | 0.3743 |
| No log | 4.0 | 320 | 0.3743 |
| No log | 5.0 | 400 | 0.3743 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
svenbl80/roberta-base-finetuned-chatdoc-test | svenbl80 | 2024-01-09T14:22:42Z | 48 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"roberta",
"text-classification",
"generated_from_keras_callback",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T14:18:51Z | ---
license: mit
base_model: roberta-base
tags:
- generated_from_keras_callback
model-index:
- name: svenbl80/roberta-base-finetuned-chatdoc-test
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# svenbl80/roberta-base-finetuned-chatdoc-test
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.0815
- Validation Loss: 1.0109
- Train Accuracy: 0.4343
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 750, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 1.0815 | 1.0109 | 0.4343 | 0 |
### Framework versions
- Transformers 4.36.2
- TensorFlow 2.13.1
- Datasets 2.16.1
- Tokenizers 0.15.0
|
mip016/rl-faketaxi | mip016 | 2024-01-09T14:09:38Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T14:09:30Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: rl-faketaxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="mip016/rl-faketaxi", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
ybelkada/test-model-already-tagged | ybelkada | 2024-01-09T14:06:44Z | 176 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"tag-test",
"tag-test-2",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T14:05:35Z | ---
library_name: transformers
tags:
- tag-test
- tag-test-2
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ybelkada/test-tag-already-tagged | ybelkada | 2024-01-09T14:03:13Z | 97 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"tag-test-3",
"generated_from_trainer",
"base_model:HuggingFaceM4/tiny-random-LlamaForCausalLM",
"base_model:finetune:HuggingFaceM4/tiny-random-LlamaForCausalLM",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T13:59:17Z | ---
base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
tags:
- trl
- sft
- tag-test-3
- generated_from_trainer
model-index:
- name: test-tag-already-tagged
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# test-tag-already-tagged
This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.0
- Tokenizers 0.15.0
|
NLPProject2023Z/roberta-regression | NLPProject2023Z | 2024-01-09T14:03:13Z | 174 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2024-01-09T14:02:45Z | ---
tags:
- generated_from_trainer
model-index:
- name: roberta-regression
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-regression
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5758
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 84 | 0.5758 |
| No log | 2.0 | 168 | 0.5758 |
| No log | 3.0 | 252 | 0.5758 |
| No log | 4.0 | 336 | 0.5758 |
| No log | 5.0 | 420 | 0.5758 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
mattia-colbertaldo/whisper-small-custom | mattia-colbertaldo | 2024-01-09T13:58:59Z | 61 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"en",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-01-09T12:10:47Z | ---
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small Custom - Mattia Colbertaldo
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Custom - Mattia Colbertaldo
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Mattia's Dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8726
- Wer: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 2.1417 | 10.0 | 10 | 3.0808 | 0.0 |
| 0.6544 | 20.0 | 20 | 1.2364 | 57.1429 |
| 0.4179 | 30.0 | 30 | 1.0541 | 57.1429 |
| 0.3622 | 40.0 | 40 | 0.9383 | 1000.0 |
| 0.3339 | 50.0 | 50 | 0.8726 | 0.0 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
badokorach/bert-base-cased-squad2-agic2-060124 | badokorach | 2024-01-09T13:58:48Z | 1 | 0 | transformers | [
"transformers",
"tf",
"bert",
"question-answering",
"generated_from_keras_callback",
"base_model:badokorach/bert-base-cased-squad2-agic2-051223",
"base_model:finetune:badokorach/bert-base-cased-squad2-agic2-051223",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2024-01-06T03:04:38Z | ---
license: cc-by-4.0
base_model: badokorach/bert-base-cased-squad2-agic2-051223
tags:
- generated_from_keras_callback
model-index:
- name: badokorach/bert-base-cased-squad2-agic2-060124
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# badokorach/bert-base-cased-squad2-agic2-060124
This model is a fine-tuned version of [badokorach/bert-base-cased-squad2-agic2-051223](https://huggingface.co/badokorach/bert-base-cased-squad2-agic2-051223) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1138
- Validation Loss: 0.0
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': None, 'class_name': 'CustomLearningRateScheduler', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1044, 'warmup_steps': 116, 'end_learning_rate': 1e-05}, 'registered_name': 'CustomLearningRateScheduler'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: mixed_float16
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.7839 | 0.0 | 0 |
| 0.6859 | 0.0 | 1 |
| 0.4749 | 0.0 | 2 |
| 0.3586 | 0.0 | 3 |
| 0.3039 | 0.0 | 4 |
| 0.2084 | 0.0 | 5 |
| 0.1471 | 0.0 | 6 |
| 0.1420 | 0.0 | 7 |
| 0.1221 | 0.0 | 8 |
| 0.1138 | 0.0 | 9 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
MatrixC7/Mixtral_34Bx2_MoE_60B-4.65bpw-h6-exl2 | MatrixC7 | 2024-01-09T13:58:30Z | 6 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T08:03:09Z | ---
license: cc-by-nc-4.0
---
- The measurement file is attached in the branch `measurement`.
---
# Mixtral MOE 2x34B
This is my first English & Chinese MoE Model based on
* [jondurbin/bagel-dpo-34b-v0.2]
* [SUSTech/SUS-Chat-34B]
gpu code example
```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Mixtral_34Bx2_MoE_60B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
```
CPU example
```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "cloudyu/Mixtral_34Bx2_MoE_60B"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.bfloat16, device_map='cpu'
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
```
Output Examples:
```
please input prompt:write a story about yosemite
write a story about yosemite national park
Yosemite National Park is located in the Sierra Nevada Mountains of California, USA. It was established on October 1st, 1890 and covers an area of approximately 747,956 acres (302,687 hectares). The park boasts some of America's most iconic natural wonders such as Yosemite Valley, Half Dome, El Capitan, Bridalveil Fall, Tuolumne Meadows, Glacier Point, Mariposa Grove, and many more breathtaking landscapes that attract millions of visitors each year.
The history of Yosemite dates back to over seven million years ago when glaciers carved out its stunning granite cliffs and valleys. Native American tribes like Miwok and Paiute have lived here for thousands of years before European explorers arrived during the mid-nineteenth century. In fact, it was John Muir - one of America’s greatest conservationists who helped establish this region as a protected wilderness area by advocating for its preservation through his writings and activism.
Today, Yosemite offers various recreational activities including hiking, rock climbing, camping, fishing, horseback riding, wildlife watching, photography, and winter sports like skiing and snowshoeing. Visitors can also enjoy ranger programs, guided tours, educational exhibits at visitor centers, or simply take time to appreciate nature while strolling along scenic trails surrounded by towering sequoia trees, cascading waterfalls, and crystal clear lakes.
In addition to preserving these awe-inspiring vistas, Yosemite plays a crucial role in protecting numerous plant and animal species found within its boundaries. Some notable inhabitants include black bears, mountain lions, mule deer, coyotes, bobcats, golden eagles, peregrine falcons, bighorn sheep, and several types of fish native to the Merced River which runs through the heart of the valley.
As we continue our journey into the future, let us remember the importance of safeguarding places like Yosemite so they may remain pristine sanctuaries where both humans and animals alike can thrive together amidst unspoiled beauty.</s>
please input prompt:李开复是谁?
李开复是谁?
他是一个在人工智能领域有着卓越贡献的科学家,也是一位成功的企业家。他的名字与谷歌、微软等科技巨头紧密相连,他是创新工场的创始人之一,更是无数创业者心中的偶像和导师。然而,除了这些耀眼的光环之外,李开复还有着怎样的故事呢?让我们一起来揭秘这位传奇人物的人生历程吧!</s>
``` |
w11wo/xlm-roberta-base-twitter-indonesia-sarcastic | w11wo | 2024-01-09T13:56:59Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T13:47:50Z | ---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: xlm-roberta-base-twitter-indonesia-sarcastic
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-twitter-indonesia-sarcastic
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4359
- Accuracy: 0.8513
- F1: 0.7386
- Precision: 0.6570
- Recall: 0.8433
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 100.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.5641 | 1.0 | 59 | 0.5260 | 0.75 | 0.0 | 0.0 | 0.0 |
| 0.5317 | 2.0 | 118 | 0.5030 | 0.75 | 0.0 | 0.0 | 0.0 |
| 0.4995 | 3.0 | 177 | 0.4656 | 0.75 | 0.0 | 0.0 | 0.0 |
| 0.4599 | 4.0 | 236 | 0.4503 | 0.7687 | 0.6026 | 0.5281 | 0.7015 |
| 0.4082 | 5.0 | 295 | 0.3785 | 0.8470 | 0.6435 | 0.7708 | 0.5522 |
| 0.3274 | 6.0 | 354 | 0.3605 | 0.8619 | 0.6992 | 0.7679 | 0.6418 |
| 0.2621 | 7.0 | 413 | 0.3765 | 0.8619 | 0.6838 | 0.8 | 0.5970 |
| 0.2332 | 8.0 | 472 | 0.3408 | 0.8769 | 0.7591 | 0.7429 | 0.7761 |
| 0.1579 | 9.0 | 531 | 0.4382 | 0.8731 | 0.7213 | 0.8 | 0.6567 |
| 0.1467 | 10.0 | 590 | 0.3855 | 0.8806 | 0.7895 | 0.7059 | 0.8955 |
| 0.098 | 11.0 | 649 | 0.4693 | 0.8806 | 0.7500 | 0.7869 | 0.7164 |
| 0.0929 | 12.0 | 708 | 0.6206 | 0.8806 | 0.7333 | 0.8302 | 0.6567 |
| 0.0555 | 13.0 | 767 | 0.7134 | 0.8843 | 0.7634 | 0.7812 | 0.7463 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
Ghunghru/Misinformation-Covid-Articles | Ghunghru | 2024-01-09T13:51:16Z | 91 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-german-cased",
"base_model:finetune:google-bert/bert-base-german-cased",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T10:01:02Z | ---
license: mit
base_model: bert-base-german-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Misinformation-Covid-Articles
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Misinformation-Covid-Articles
This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1395
- Accuracy: 0.9840
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.1266 | 1.0 | 3609 | 0.1224 | 0.9703 |
| 0.0639 | 2.0 | 7218 | 0.1170 | 0.9735 |
| 0.0437 | 3.0 | 10827 | 0.1230 | 0.9808 |
| 0.0148 | 4.0 | 14436 | 0.1209 | 0.9832 |
| 0.0044 | 5.0 | 18045 | 0.1395 | 0.9840 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3
|
eth-easl/pythia_2.8b_deduped-task380_boolq_yes_no_question | eth-easl | 2024-01-09T13:50:32Z | 0 | 0 | null | [
"arxiv:2312.05215",
"region:us"
] | null | 2023-09-01T13:40:02Z | ### More details
[Paper](https://arxiv.org/abs/2312.05215) |
JDB03/Qlearning-Taxi | JDB03 | 2024-01-09T13:49:23Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T13:48:55Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Qlearning-Taxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="JDB03/Qlearning-Taxi", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
JDB03/Qlearning-FrozenLake | JDB03 | 2024-01-09T13:46:15Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T13:44:41Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Qlearning-FrozenLake
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="JDB03/Qlearning-FrozenLake", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
hlrh/sd-class-butterflies-32 | hlrh | 2024-01-09T13:40:51Z | 44 | 0 | diffusers | [
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | 2024-01-09T13:40:29Z | ---
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
license: mit
---
# 这个模型用于生成蝴蝶图像的无条件图像生成扩散模型
'''python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('hlrh/sd-class-butterflies-32')
image = pipeline().images[0]
image
|
kk08/mistral-gsm8k-finetune | kk08 | 2024-01-09T13:40:32Z | 2 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-01-09T13:39:57Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistral-gsm8k-finetune
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral-gsm8k-finetune
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8062
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5604 | 0.01 | 10 | 1.4867 |
| 1.3198 | 0.02 | 20 | 1.2589 |
| 1.11 | 0.03 | 30 | 1.0018 |
| 0.8584 | 0.04 | 40 | 0.8349 |
| 0.77 | 0.05 | 50 | 0.8062 |
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0 |
JacobLinCool/whisper-small-tw2 | JacobLinCool | 2024-01-09T13:32:41Z | 61 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"zh",
"dataset:mozilla-foundation/common_voice_16_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-01-09T07:01:38Z | ---
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
model-index:
- name: Whisper Small zh-TW - Chinese
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small zh-TW - Chinese
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2102
- Cer: 125.9209
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0977 | 1.33 | 1000 | 0.1988 | 92.1973 |
| 0.04 | 2.65 | 2000 | 0.1952 | 127.6179 |
| 0.0102 | 3.98 | 3000 | 0.2032 | 152.5090 |
| 0.0017 | 5.31 | 4000 | 0.2102 | 125.9209 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0.post301
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Felladrin/onnx-tinyllama-15M | Felladrin | 2024-01-09T13:32:38Z | 3 | 0 | transformers.js | [
"transformers.js",
"onnx",
"llama",
"text-generation",
"base_model:nickypro/tinyllama-15M",
"base_model:quantized:nickypro/tinyllama-15M",
"license:mit",
"region:us"
] | text-generation | 2024-01-09T13:23:58Z | ---
license: mit
library_name: "transformers.js"
base_model: nickypro/tinyllama-15M
---
INT8 ONNX version of [nickypro/tinyllama-15M](https://huggingface.co/nickypro/tinyllama-15M) to use with [Transformers.js](https://huggingface.co/docs/transformers.js).
|
SimplCup/DanTDM | SimplCup | 2024-01-09T13:18:18Z | 0 | 0 | null | [
"license:cc-by-nc-nd-4.0",
"region:us"
] | null | 2024-01-09T13:17:58Z | ---
license: cc-by-nc-nd-4.0
---
|
scoup123/Berturk-AffixChecker | scoup123 | 2024-01-09T13:14:34Z | 92 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"feature-extraction",
"text-classification",
"tr",
"dataset:scoup123/affixfinder",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T12:44:45Z | ---
datasets:
- scoup123/affixfinder
language:
- tr
metrics:
- accuracy
pipeline_tag: text-classification
---
# Model Card for Model ID
### Model Description
Given 2 words in Turkish, the model predicts whether they share an affix or not. Fine-tuned on dbmdz/bert-base-turkish-cased,
fine-tuned on a task similar to NLI, but on word level and with 2 labels. It was created as a final project for one of my classes.
- **Developed by:** Scoup123
- **Model type:** BERT
- **Language(s) (NLP):** Turkish
- **Finetuned from model [optional]:** dbmdz/bert-base-turkish-cased
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** in-works
-
## Uses
It can be used in morphological analyzing tasks.
### Direct Use
It can probably be used without additional finetuning on Turkish.
## Training Details
### Training Data
scoup123/affixfinder
The dataset used was generated from a generated dataset mentioned in the paper titled Turkish language resources: Morphological parser, morphological disambiguator and web corpus.
## Evaluation
Test Accuracy: 0.9874
Precision: 0.9874
Recall: 0.9874
F1 Score: 0.9874
**It should be used with caution as these scores are too high.
### Testing Data, Factors & Metrics
#### Testing Data
A testing split data was created from the training data
#### Summary
This model aims to create an affix identifier for Turkish.
## Model Examination [optional]
I have just created it, so further testing needed to check if it actually works. Additionally, you should check it if it works before using it.
[More Information Needed]
## Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** Free Colab T4 GPU
- **Hours used:** ~2.5 hours
- **Cloud Provider:** Google
- **Compute Region:** Europe
- **Carbon Emitted:** [More Information Needed]
## Citation [optional]
**APA:**
Sak, H., Güngör, T., & Saraçlar, M. (2008). Turkish language resources: Morphological parser, morphological disambiguator and web corpus.
In Advances in natural language processing (pp. 417-427). Springer Berlin Heidelberg.
## Model Card Authors [optional]
Kaan Bayar
## Model Card Contact
[email protected] |
pcuenq/siglip-base-patch16-224 | pcuenq | 2024-01-09T13:12:34Z | 90 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"siglip",
"zero-shot-image-classification",
"vision",
"arxiv:2303.15343",
"arxiv:2209.06794",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | zero-shot-image-classification | 2024-01-09T13:12:34Z | ---
license: apache-2.0
tags:
- vision
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
candidate_labels: playing music, playing sports
example_title: Cat & Dog
---
# SigLIP (base-sized model)
SigLIP model pre-trained on WebLi at resolution 224x224. It was introduced in the paper [Sigmoid Loss for Language Image Pre-Training](https://arxiv.org/abs/2303.15343) by Zhai et al. and first released in [this repository](https://github.com/google-research/big_vision).
Disclaimer: The team releasing SigLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
SigLIP is [CLIP](https://huggingface.co/docs/transformers/model_doc/clip), a multimodal model, with a better loss function. The sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. This allows further scaling up the batch size, while also performing better at smaller batch sizes.
A TLDR of SigLIP by one of the authors can be found [here](https://twitter.com/giffmana/status/1692641733459267713).
## Intended uses & limitations
You can use the raw model for tasks like zero-shot image classification and image-text retrieval. See the [model hub](https://huggingface.co/models?search=google/siglip) to look for
other versions on a task that interests you.
### How to use
Here is how to use this model to perform zero-shot image classification:
```python
from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("google/siglip-base-patch16-224")
processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-224")
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
texts = ["a photo of 2 cats", "a photo of 2 dogs"]
inputs = processor(text=texts, images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image
probs = torch.sigmoid(logits_per_image) # these are the probabilities
print(f"{probs[0][0]:.1%} that image 0 is '{texts[0]}'")
```
Alternatively, one can leverage the pipeline API which abstracts away the complexity for the user:
```
from transformers import pipeline
from PIL import Image
import requests
# load pipe
image_classifier = pipeline(task="zero-shot-image-classification", model="google/siglip-base-patch16-224")
# load image
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
# inference
outputs = image_classifier(image, candidate_labels=["2 cats", "a plane", "a remote"])
outputs = [{"score": round(output["score"], 4), "label": output["label"] } for output in outputs]
print(outputs)
```
For more code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/siglip.html#).
## Training procedure
### Training data
SigLIP is pre-trained on the English image-text pairs of the WebLI dataset [(Chen et al., 2023)](https://arxiv.org/abs/2209.06794).
### Preprocessing
Images are resized/rescaled to the same resolution (224x224) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).
Texts are tokenized and padded to the same length (64 tokens).
### Compute
The model was trained on 16 TPU-v4 chips for three days.
## Evaluation results
Evaluation of SigLIP compared to CLIP is shown below (taken from the paper).
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/siglip_table.jpeg"
alt="drawing" width="600"/>
### BibTeX entry and citation info
```bibtex
@misc{zhai2023sigmoid,
title={Sigmoid Loss for Language Image Pre-Training},
author={Xiaohua Zhai and Basil Mustafa and Alexander Kolesnikov and Lucas Beyer},
year={2023},
eprint={2303.15343},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
``` |
baltop/deep_500 | baltop | 2024-01-09T13:11:50Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:deepseek-ai/deepseek-coder-6.7b-instruct",
"base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct",
"region:us"
] | null | 2024-01-09T13:11:34Z | ---
library_name: peft
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
baltop/deep_400 | baltop | 2024-01-09T13:11:16Z | 3 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:deepseek-ai/deepseek-coder-6.7b-instruct",
"base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct",
"region:us"
] | null | 2024-01-09T13:10:59Z | ---
library_name: peft
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
baltop/deep_300 | baltop | 2024-01-09T13:10:34Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:deepseek-ai/deepseek-coder-6.7b-instruct",
"base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct",
"region:us"
] | null | 2024-01-09T13:10:13Z | ---
library_name: peft
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
khoa-klaytn/bge-small-en-v1.5-angle | khoa-klaytn | 2024-01-09T12:51:40Z | 336 | 4 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"mteb",
"en",
"arxiv:2310.07554",
"arxiv:2309.07597",
"license:mit",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-01-09T12:41:49Z | ---
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
- mteb
model-index:
- name: bge-small-en-v1.5-angle
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 73.79104477611939
- type: ap
value: 37.21923821573361
- type: f1
value: 68.0914945617093
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 92.75377499999999
- type: ap
value: 89.46766124546022
- type: f1
value: 92.73884001331487
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 46.986
- type: f1
value: 46.55936786727896
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 35.846000000000004
- type: map_at_10
value: 51.388
- type: map_at_100
value: 52.132999999999996
- type: map_at_1000
value: 52.141000000000005
- type: map_at_3
value: 47.037
- type: map_at_5
value: 49.579
- type: mrr_at_1
value: 36.558
- type: mrr_at_10
value: 51.658
- type: mrr_at_100
value: 52.402
- type: mrr_at_1000
value: 52.410000000000004
- type: mrr_at_3
value: 47.345
- type: mrr_at_5
value: 49.797999999999995
- type: ndcg_at_1
value: 35.846000000000004
- type: ndcg_at_10
value: 59.550000000000004
- type: ndcg_at_100
value: 62.596
- type: ndcg_at_1000
value: 62.759
- type: ndcg_at_3
value: 50.666999999999994
- type: ndcg_at_5
value: 55.228
- type: precision_at_1
value: 35.846000000000004
- type: precision_at_10
value: 8.542
- type: precision_at_100
value: 0.984
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 20.389
- type: precision_at_5
value: 14.438
- type: recall_at_1
value: 35.846000000000004
- type: recall_at_10
value: 85.42
- type: recall_at_100
value: 98.43499999999999
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 61.166
- type: recall_at_5
value: 72.191
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 47.402770198163594
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 40.01545436974177
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 62.586465273207196
- type: mrr
value: 74.42169019038825
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 85.1891186537969
- type: cos_sim_spearman
value: 83.75492046087288
- type: euclidean_pearson
value: 84.11766204805357
- type: euclidean_spearman
value: 84.01456493126516
- type: manhattan_pearson
value: 84.2132950502772
- type: manhattan_spearman
value: 83.89227298813377
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 85.74025974025975
- type: f1
value: 85.71493566466381
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 38.467181385006434
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 34.719496037339056
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 29.587000000000003
- type: map_at_10
value: 41.114
- type: map_at_100
value: 42.532
- type: map_at_1000
value: 42.661
- type: map_at_3
value: 37.483
- type: map_at_5
value: 39.652
- type: mrr_at_1
value: 36.338
- type: mrr_at_10
value: 46.763
- type: mrr_at_100
value: 47.393
- type: mrr_at_1000
value: 47.445
- type: mrr_at_3
value: 43.538
- type: mrr_at_5
value: 45.556000000000004
- type: ndcg_at_1
value: 36.338
- type: ndcg_at_10
value: 47.658
- type: ndcg_at_100
value: 52.824000000000005
- type: ndcg_at_1000
value: 54.913999999999994
- type: ndcg_at_3
value: 41.989
- type: ndcg_at_5
value: 44.944
- type: precision_at_1
value: 36.338
- type: precision_at_10
value: 9.156
- type: precision_at_100
value: 1.4789999999999999
- type: precision_at_1000
value: 0.196
- type: precision_at_3
value: 20.076
- type: precision_at_5
value: 14.85
- type: recall_at_1
value: 29.587000000000003
- type: recall_at_10
value: 60.746
- type: recall_at_100
value: 82.157
- type: recall_at_1000
value: 95.645
- type: recall_at_3
value: 44.821
- type: recall_at_5
value: 52.819
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.239
- type: map_at_10
value: 39.989000000000004
- type: map_at_100
value: 41.196
- type: map_at_1000
value: 41.325
- type: map_at_3
value: 37.261
- type: map_at_5
value: 38.833
- type: mrr_at_1
value: 37.516
- type: mrr_at_10
value: 46.177
- type: mrr_at_100
value: 46.806
- type: mrr_at_1000
value: 46.849000000000004
- type: mrr_at_3
value: 44.002
- type: mrr_at_5
value: 45.34
- type: ndcg_at_1
value: 37.516
- type: ndcg_at_10
value: 45.586
- type: ndcg_at_100
value: 49.897000000000006
- type: ndcg_at_1000
value: 51.955
- type: ndcg_at_3
value: 41.684
- type: ndcg_at_5
value: 43.617
- type: precision_at_1
value: 37.516
- type: precision_at_10
value: 8.522
- type: precision_at_100
value: 1.374
- type: precision_at_1000
value: 0.184
- type: precision_at_3
value: 20.105999999999998
- type: precision_at_5
value: 14.152999999999999
- type: recall_at_1
value: 30.239
- type: recall_at_10
value: 55.03
- type: recall_at_100
value: 73.375
- type: recall_at_1000
value: 86.29599999999999
- type: recall_at_3
value: 43.269000000000005
- type: recall_at_5
value: 48.878
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.338
- type: map_at_10
value: 50.468999999999994
- type: map_at_100
value: 51.553000000000004
- type: map_at_1000
value: 51.608
- type: map_at_3
value: 47.107
- type: map_at_5
value: 49.101
- type: mrr_at_1
value: 44.201
- type: mrr_at_10
value: 54.057
- type: mrr_at_100
value: 54.764
- type: mrr_at_1000
value: 54.791000000000004
- type: mrr_at_3
value: 51.56699999999999
- type: mrr_at_5
value: 53.05
- type: ndcg_at_1
value: 44.201
- type: ndcg_at_10
value: 56.379000000000005
- type: ndcg_at_100
value: 60.645
- type: ndcg_at_1000
value: 61.73499999999999
- type: ndcg_at_3
value: 50.726000000000006
- type: ndcg_at_5
value: 53.58500000000001
- type: precision_at_1
value: 44.201
- type: precision_at_10
value: 9.141
- type: precision_at_100
value: 1.216
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 22.654
- type: precision_at_5
value: 15.723999999999998
- type: recall_at_1
value: 38.338
- type: recall_at_10
value: 70.30499999999999
- type: recall_at_100
value: 88.77199999999999
- type: recall_at_1000
value: 96.49799999999999
- type: recall_at_3
value: 55.218
- type: recall_at_5
value: 62.104000000000006
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.682
- type: map_at_10
value: 33.498
- type: map_at_100
value: 34.461000000000006
- type: map_at_1000
value: 34.544000000000004
- type: map_at_3
value: 30.503999999999998
- type: map_at_5
value: 32.216
- type: mrr_at_1
value: 27.683999999999997
- type: mrr_at_10
value: 35.467999999999996
- type: mrr_at_100
value: 36.32
- type: mrr_at_1000
value: 36.386
- type: mrr_at_3
value: 32.618
- type: mrr_at_5
value: 34.262
- type: ndcg_at_1
value: 27.683999999999997
- type: ndcg_at_10
value: 38.378
- type: ndcg_at_100
value: 43.288
- type: ndcg_at_1000
value: 45.413
- type: ndcg_at_3
value: 32.586
- type: ndcg_at_5
value: 35.499
- type: precision_at_1
value: 27.683999999999997
- type: precision_at_10
value: 5.864
- type: precision_at_100
value: 0.882
- type: precision_at_1000
value: 0.11
- type: precision_at_3
value: 13.446
- type: precision_at_5
value: 9.718
- type: recall_at_1
value: 25.682
- type: recall_at_10
value: 51.712
- type: recall_at_100
value: 74.446
- type: recall_at_1000
value: 90.472
- type: recall_at_3
value: 36.236000000000004
- type: recall_at_5
value: 43.234
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.073999999999998
- type: map_at_10
value: 24.352999999999998
- type: map_at_100
value: 25.438
- type: map_at_1000
value: 25.545
- type: map_at_3
value: 21.614
- type: map_at_5
value: 23.104
- type: mrr_at_1
value: 19.776
- type: mrr_at_10
value: 28.837000000000003
- type: mrr_at_100
value: 29.755
- type: mrr_at_1000
value: 29.817
- type: mrr_at_3
value: 26.201999999999998
- type: mrr_at_5
value: 27.714
- type: ndcg_at_1
value: 19.776
- type: ndcg_at_10
value: 29.701
- type: ndcg_at_100
value: 35.307
- type: ndcg_at_1000
value: 37.942
- type: ndcg_at_3
value: 24.764
- type: ndcg_at_5
value: 27.025
- type: precision_at_1
value: 19.776
- type: precision_at_10
value: 5.659
- type: precision_at_100
value: 0.971
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 12.065
- type: precision_at_5
value: 8.905000000000001
- type: recall_at_1
value: 16.073999999999998
- type: recall_at_10
value: 41.647
- type: recall_at_100
value: 66.884
- type: recall_at_1000
value: 85.91499999999999
- type: recall_at_3
value: 27.916
- type: recall_at_5
value: 33.729
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 28.444999999999997
- type: map_at_10
value: 38.218999999999994
- type: map_at_100
value: 39.595
- type: map_at_1000
value: 39.709
- type: map_at_3
value: 35.586
- type: map_at_5
value: 36.895
- type: mrr_at_1
value: 34.841
- type: mrr_at_10
value: 44.106
- type: mrr_at_100
value: 44.98
- type: mrr_at_1000
value: 45.03
- type: mrr_at_3
value: 41.979
- type: mrr_at_5
value: 43.047999999999995
- type: ndcg_at_1
value: 34.841
- type: ndcg_at_10
value: 43.922
- type: ndcg_at_100
value: 49.504999999999995
- type: ndcg_at_1000
value: 51.675000000000004
- type: ndcg_at_3
value: 39.858
- type: ndcg_at_5
value: 41.408
- type: precision_at_1
value: 34.841
- type: precision_at_10
value: 7.872999999999999
- type: precision_at_100
value: 1.2449999999999999
- type: precision_at_1000
value: 0.161
- type: precision_at_3
value: 18.993
- type: precision_at_5
value: 13.032
- type: recall_at_1
value: 28.444999999999997
- type: recall_at_10
value: 54.984
- type: recall_at_100
value: 78.342
- type: recall_at_1000
value: 92.77
- type: recall_at_3
value: 42.842999999999996
- type: recall_at_5
value: 47.247
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.072
- type: map_at_10
value: 32.354
- type: map_at_100
value: 33.800000000000004
- type: map_at_1000
value: 33.908
- type: map_at_3
value: 29.232000000000003
- type: map_at_5
value: 31.049
- type: mrr_at_1
value: 29.110000000000003
- type: mrr_at_10
value: 38.03
- type: mrr_at_100
value: 39.032
- type: mrr_at_1000
value: 39.086999999999996
- type: mrr_at_3
value: 35.407
- type: mrr_at_5
value: 36.76
- type: ndcg_at_1
value: 29.110000000000003
- type: ndcg_at_10
value: 38.231
- type: ndcg_at_100
value: 44.425
- type: ndcg_at_1000
value: 46.771
- type: ndcg_at_3
value: 33.095
- type: ndcg_at_5
value: 35.459
- type: precision_at_1
value: 29.110000000000003
- type: precision_at_10
value: 7.215000000000001
- type: precision_at_100
value: 1.2109999999999999
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 16.058
- type: precision_at_5
value: 11.644
- type: recall_at_1
value: 23.072
- type: recall_at_10
value: 50.285999999999994
- type: recall_at_100
value: 76.596
- type: recall_at_1000
value: 92.861
- type: recall_at_3
value: 35.702
- type: recall_at_5
value: 42.152
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.937916666666666
- type: map_at_10
value: 33.755250000000004
- type: map_at_100
value: 34.955999999999996
- type: map_at_1000
value: 35.070499999999996
- type: map_at_3
value: 30.98708333333333
- type: map_at_5
value: 32.51491666666666
- type: mrr_at_1
value: 29.48708333333333
- type: mrr_at_10
value: 37.92183333333334
- type: mrr_at_100
value: 38.76583333333333
- type: mrr_at_1000
value: 38.82466666666667
- type: mrr_at_3
value: 35.45125
- type: mrr_at_5
value: 36.827000000000005
- type: ndcg_at_1
value: 29.48708333333333
- type: ndcg_at_10
value: 39.05225
- type: ndcg_at_100
value: 44.25983333333334
- type: ndcg_at_1000
value: 46.568333333333335
- type: ndcg_at_3
value: 34.271583333333325
- type: ndcg_at_5
value: 36.483916666666666
- type: precision_at_1
value: 29.48708333333333
- type: precision_at_10
value: 6.865749999999999
- type: precision_at_100
value: 1.1195833333333332
- type: precision_at_1000
value: 0.15058333333333335
- type: precision_at_3
value: 15.742083333333333
- type: precision_at_5
value: 11.221916666666667
- type: recall_at_1
value: 24.937916666666666
- type: recall_at_10
value: 50.650416666666665
- type: recall_at_100
value: 73.55383333333334
- type: recall_at_1000
value: 89.61691666666667
- type: recall_at_3
value: 37.27808333333334
- type: recall_at_5
value: 42.99475
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.947
- type: map_at_10
value: 30.575000000000003
- type: map_at_100
value: 31.465
- type: map_at_1000
value: 31.558000000000003
- type: map_at_3
value: 28.814
- type: map_at_5
value: 29.738999999999997
- type: mrr_at_1
value: 26.994
- type: mrr_at_10
value: 33.415
- type: mrr_at_100
value: 34.18
- type: mrr_at_1000
value: 34.245
- type: mrr_at_3
value: 31.621
- type: mrr_at_5
value: 32.549
- type: ndcg_at_1
value: 26.994
- type: ndcg_at_10
value: 34.482
- type: ndcg_at_100
value: 38.915
- type: ndcg_at_1000
value: 41.355
- type: ndcg_at_3
value: 31.139
- type: ndcg_at_5
value: 32.589
- type: precision_at_1
value: 26.994
- type: precision_at_10
value: 5.322
- type: precision_at_100
value: 0.8160000000000001
- type: precision_at_1000
value: 0.11100000000000002
- type: precision_at_3
value: 13.344000000000001
- type: precision_at_5
value: 8.988
- type: recall_at_1
value: 23.947
- type: recall_at_10
value: 43.647999999999996
- type: recall_at_100
value: 63.851
- type: recall_at_1000
value: 82.0
- type: recall_at_3
value: 34.288000000000004
- type: recall_at_5
value: 38.117000000000004
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.197
- type: map_at_10
value: 22.968
- type: map_at_100
value: 24.095
- type: map_at_1000
value: 24.217
- type: map_at_3
value: 20.771
- type: map_at_5
value: 21.995
- type: mrr_at_1
value: 19.511
- type: mrr_at_10
value: 26.55
- type: mrr_at_100
value: 27.500999999999998
- type: mrr_at_1000
value: 27.578999999999997
- type: mrr_at_3
value: 24.421
- type: mrr_at_5
value: 25.604
- type: ndcg_at_1
value: 19.511
- type: ndcg_at_10
value: 27.386
- type: ndcg_at_100
value: 32.828
- type: ndcg_at_1000
value: 35.739
- type: ndcg_at_3
value: 23.405
- type: ndcg_at_5
value: 25.255
- type: precision_at_1
value: 19.511
- type: precision_at_10
value: 5.017
- type: precision_at_100
value: 0.91
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 11.023
- type: precision_at_5
value: 8.025
- type: recall_at_1
value: 16.197
- type: recall_at_10
value: 37.09
- type: recall_at_100
value: 61.778
- type: recall_at_1000
value: 82.56599999999999
- type: recall_at_3
value: 26.034000000000002
- type: recall_at_5
value: 30.762
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.41
- type: map_at_10
value: 33.655
- type: map_at_100
value: 34.892
- type: map_at_1000
value: 34.995
- type: map_at_3
value: 30.94
- type: map_at_5
value: 32.303
- type: mrr_at_1
value: 29.477999999999998
- type: mrr_at_10
value: 37.443
- type: mrr_at_100
value: 38.383
- type: mrr_at_1000
value: 38.440000000000005
- type: mrr_at_3
value: 34.949999999999996
- type: mrr_at_5
value: 36.228
- type: ndcg_at_1
value: 29.477999999999998
- type: ndcg_at_10
value: 38.769
- type: ndcg_at_100
value: 44.245000000000005
- type: ndcg_at_1000
value: 46.593
- type: ndcg_at_3
value: 33.623
- type: ndcg_at_5
value: 35.766
- type: precision_at_1
value: 29.477999999999998
- type: precision_at_10
value: 6.455
- type: precision_at_100
value: 1.032
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 14.893999999999998
- type: precision_at_5
value: 10.485
- type: recall_at_1
value: 25.41
- type: recall_at_10
value: 50.669
- type: recall_at_100
value: 74.084
- type: recall_at_1000
value: 90.435
- type: recall_at_3
value: 36.679
- type: recall_at_5
value: 41.94
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.339
- type: map_at_10
value: 31.852000000000004
- type: map_at_100
value: 33.411
- type: map_at_1000
value: 33.62
- type: map_at_3
value: 28.929
- type: map_at_5
value: 30.542
- type: mrr_at_1
value: 28.063
- type: mrr_at_10
value: 36.301
- type: mrr_at_100
value: 37.288
- type: mrr_at_1000
value: 37.349
- type: mrr_at_3
value: 33.663
- type: mrr_at_5
value: 35.165
- type: ndcg_at_1
value: 28.063
- type: ndcg_at_10
value: 37.462
- type: ndcg_at_100
value: 43.620999999999995
- type: ndcg_at_1000
value: 46.211
- type: ndcg_at_3
value: 32.68
- type: ndcg_at_5
value: 34.981
- type: precision_at_1
value: 28.063
- type: precision_at_10
value: 7.1739999999999995
- type: precision_at_100
value: 1.486
- type: precision_at_1000
value: 0.23500000000000001
- type: precision_at_3
value: 15.217
- type: precision_at_5
value: 11.265
- type: recall_at_1
value: 23.339
- type: recall_at_10
value: 48.376999999999995
- type: recall_at_100
value: 76.053
- type: recall_at_1000
value: 92.455
- type: recall_at_3
value: 34.735
- type: recall_at_5
value: 40.71
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 18.925
- type: map_at_10
value: 26.017000000000003
- type: map_at_100
value: 27.034000000000002
- type: map_at_1000
value: 27.156000000000002
- type: map_at_3
value: 23.604
- type: map_at_5
value: 24.75
- type: mrr_at_1
value: 20.333000000000002
- type: mrr_at_10
value: 27.915
- type: mrr_at_100
value: 28.788000000000004
- type: mrr_at_1000
value: 28.877999999999997
- type: mrr_at_3
value: 25.446999999999996
- type: mrr_at_5
value: 26.648
- type: ndcg_at_1
value: 20.333000000000002
- type: ndcg_at_10
value: 30.673000000000002
- type: ndcg_at_100
value: 35.618
- type: ndcg_at_1000
value: 38.517
- type: ndcg_at_3
value: 25.71
- type: ndcg_at_5
value: 27.679
- type: precision_at_1
value: 20.333000000000002
- type: precision_at_10
value: 4.9910000000000005
- type: precision_at_100
value: 0.8130000000000001
- type: precision_at_1000
value: 0.117
- type: precision_at_3
value: 11.029
- type: precision_at_5
value: 7.8740000000000006
- type: recall_at_1
value: 18.925
- type: recall_at_10
value: 43.311
- type: recall_at_100
value: 66.308
- type: recall_at_1000
value: 87.49
- type: recall_at_3
value: 29.596
- type: recall_at_5
value: 34.245
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 13.714
- type: map_at_10
value: 23.194
- type: map_at_100
value: 24.976000000000003
- type: map_at_1000
value: 25.166
- type: map_at_3
value: 19.709
- type: map_at_5
value: 21.523999999999997
- type: mrr_at_1
value: 30.619000000000003
- type: mrr_at_10
value: 42.563
- type: mrr_at_100
value: 43.386
- type: mrr_at_1000
value: 43.423
- type: mrr_at_3
value: 39.555
- type: mrr_at_5
value: 41.268
- type: ndcg_at_1
value: 30.619000000000003
- type: ndcg_at_10
value: 31.836
- type: ndcg_at_100
value: 38.652
- type: ndcg_at_1000
value: 42.088
- type: ndcg_at_3
value: 26.733
- type: ndcg_at_5
value: 28.435
- type: precision_at_1
value: 30.619000000000003
- type: precision_at_10
value: 9.751999999999999
- type: precision_at_100
value: 1.71
- type: precision_at_1000
value: 0.23500000000000001
- type: precision_at_3
value: 19.935
- type: precision_at_5
value: 14.984
- type: recall_at_1
value: 13.714
- type: recall_at_10
value: 37.26
- type: recall_at_100
value: 60.546
- type: recall_at_1000
value: 79.899
- type: recall_at_3
value: 24.325
- type: recall_at_5
value: 29.725
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.462
- type: map_at_10
value: 18.637
- type: map_at_100
value: 26.131999999999998
- type: map_at_1000
value: 27.607
- type: map_at_3
value: 13.333
- type: map_at_5
value: 15.654000000000002
- type: mrr_at_1
value: 66.25
- type: mrr_at_10
value: 74.32600000000001
- type: mrr_at_100
value: 74.60900000000001
- type: mrr_at_1000
value: 74.62
- type: mrr_at_3
value: 72.667
- type: mrr_at_5
value: 73.817
- type: ndcg_at_1
value: 53.87499999999999
- type: ndcg_at_10
value: 40.028999999999996
- type: ndcg_at_100
value: 44.199
- type: ndcg_at_1000
value: 51.629999999999995
- type: ndcg_at_3
value: 44.113
- type: ndcg_at_5
value: 41.731
- type: precision_at_1
value: 66.25
- type: precision_at_10
value: 31.900000000000002
- type: precision_at_100
value: 10.043000000000001
- type: precision_at_1000
value: 1.926
- type: precision_at_3
value: 47.417
- type: precision_at_5
value: 40.65
- type: recall_at_1
value: 8.462
- type: recall_at_10
value: 24.293
- type: recall_at_100
value: 50.146
- type: recall_at_1000
value: 74.034
- type: recall_at_3
value: 14.967
- type: recall_at_5
value: 18.682000000000002
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 47.84499999999999
- type: f1
value: 42.48106691979349
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 74.034
- type: map_at_10
value: 82.76
- type: map_at_100
value: 82.968
- type: map_at_1000
value: 82.98299999999999
- type: map_at_3
value: 81.768
- type: map_at_5
value: 82.418
- type: mrr_at_1
value: 80.048
- type: mrr_at_10
value: 87.64999999999999
- type: mrr_at_100
value: 87.712
- type: mrr_at_1000
value: 87.713
- type: mrr_at_3
value: 87.01100000000001
- type: mrr_at_5
value: 87.466
- type: ndcg_at_1
value: 80.048
- type: ndcg_at_10
value: 86.643
- type: ndcg_at_100
value: 87.361
- type: ndcg_at_1000
value: 87.606
- type: ndcg_at_3
value: 85.137
- type: ndcg_at_5
value: 86.016
- type: precision_at_1
value: 80.048
- type: precision_at_10
value: 10.372
- type: precision_at_100
value: 1.093
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 32.638
- type: precision_at_5
value: 20.177
- type: recall_at_1
value: 74.034
- type: recall_at_10
value: 93.769
- type: recall_at_100
value: 96.569
- type: recall_at_1000
value: 98.039
- type: recall_at_3
value: 89.581
- type: recall_at_5
value: 91.906
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.5
- type: map_at_10
value: 32.857
- type: map_at_100
value: 34.589
- type: map_at_1000
value: 34.778
- type: map_at_3
value: 29.160999999999998
- type: map_at_5
value: 31.033
- type: mrr_at_1
value: 40.123
- type: mrr_at_10
value: 48.776
- type: mrr_at_100
value: 49.495
- type: mrr_at_1000
value: 49.539
- type: mrr_at_3
value: 46.605000000000004
- type: mrr_at_5
value: 47.654
- type: ndcg_at_1
value: 40.123
- type: ndcg_at_10
value: 40.343
- type: ndcg_at_100
value: 46.56
- type: ndcg_at_1000
value: 49.777
- type: ndcg_at_3
value: 37.322
- type: ndcg_at_5
value: 37.791000000000004
- type: precision_at_1
value: 40.123
- type: precision_at_10
value: 11.08
- type: precision_at_100
value: 1.752
- type: precision_at_1000
value: 0.232
- type: precision_at_3
value: 24.897
- type: precision_at_5
value: 17.809
- type: recall_at_1
value: 20.5
- type: recall_at_10
value: 46.388
- type: recall_at_100
value: 69.552
- type: recall_at_1000
value: 89.011
- type: recall_at_3
value: 33.617999999999995
- type: recall_at_5
value: 38.211
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 39.135999999999996
- type: map_at_10
value: 61.673
- type: map_at_100
value: 62.562
- type: map_at_1000
value: 62.62
- type: map_at_3
value: 58.467999999999996
- type: map_at_5
value: 60.463
- type: mrr_at_1
value: 78.271
- type: mrr_at_10
value: 84.119
- type: mrr_at_100
value: 84.29299999999999
- type: mrr_at_1000
value: 84.299
- type: mrr_at_3
value: 83.18900000000001
- type: mrr_at_5
value: 83.786
- type: ndcg_at_1
value: 78.271
- type: ndcg_at_10
value: 69.935
- type: ndcg_at_100
value: 73.01299999999999
- type: ndcg_at_1000
value: 74.126
- type: ndcg_at_3
value: 65.388
- type: ndcg_at_5
value: 67.906
- type: precision_at_1
value: 78.271
- type: precision_at_10
value: 14.562
- type: precision_at_100
value: 1.6969999999999998
- type: precision_at_1000
value: 0.184
- type: precision_at_3
value: 41.841
- type: precision_at_5
value: 27.087
- type: recall_at_1
value: 39.135999999999996
- type: recall_at_10
value: 72.809
- type: recall_at_100
value: 84.86200000000001
- type: recall_at_1000
value: 92.208
- type: recall_at_3
value: 62.76199999999999
- type: recall_at_5
value: 67.718
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 90.60600000000001
- type: ap
value: 86.6579587804335
- type: f1
value: 90.5938853929307
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 21.852
- type: map_at_10
value: 33.982
- type: map_at_100
value: 35.116
- type: map_at_1000
value: 35.167
- type: map_at_3
value: 30.134
- type: map_at_5
value: 32.340999999999994
- type: mrr_at_1
value: 22.479
- type: mrr_at_10
value: 34.594
- type: mrr_at_100
value: 35.672
- type: mrr_at_1000
value: 35.716
- type: mrr_at_3
value: 30.84
- type: mrr_at_5
value: 32.998
- type: ndcg_at_1
value: 22.493
- type: ndcg_at_10
value: 40.833000000000006
- type: ndcg_at_100
value: 46.357
- type: ndcg_at_1000
value: 47.637
- type: ndcg_at_3
value: 32.995999999999995
- type: ndcg_at_5
value: 36.919000000000004
- type: precision_at_1
value: 22.493
- type: precision_at_10
value: 6.465999999999999
- type: precision_at_100
value: 0.9249999999999999
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 14.030999999999999
- type: precision_at_5
value: 10.413
- type: recall_at_1
value: 21.852
- type: recall_at_10
value: 61.934999999999995
- type: recall_at_100
value: 87.611
- type: recall_at_1000
value: 97.441
- type: recall_at_3
value: 40.583999999999996
- type: recall_at_5
value: 49.992999999999995
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 93.36069311445507
- type: f1
value: 93.16456330371453
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 74.74692202462381
- type: f1
value: 58.17903579421599
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.80833893745796
- type: f1
value: 72.70786592684664
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 78.69872225958305
- type: f1
value: 78.61626934504731
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 33.058658628717694
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 30.85561739360599
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 31.290259910144385
- type: mrr
value: 32.44223046102856
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.288
- type: map_at_10
value: 12.267999999999999
- type: map_at_100
value: 15.557000000000002
- type: map_at_1000
value: 16.98
- type: map_at_3
value: 8.866
- type: map_at_5
value: 10.418
- type: mrr_at_1
value: 43.653
- type: mrr_at_10
value: 52.681
- type: mrr_at_100
value: 53.315999999999995
- type: mrr_at_1000
value: 53.357
- type: mrr_at_3
value: 51.393
- type: mrr_at_5
value: 51.903999999999996
- type: ndcg_at_1
value: 42.415000000000006
- type: ndcg_at_10
value: 34.305
- type: ndcg_at_100
value: 30.825999999999997
- type: ndcg_at_1000
value: 39.393
- type: ndcg_at_3
value: 39.931
- type: ndcg_at_5
value: 37.519999999999996
- type: precision_at_1
value: 43.653
- type: precision_at_10
value: 25.728
- type: precision_at_100
value: 7.932
- type: precision_at_1000
value: 2.07
- type: precision_at_3
value: 38.184000000000005
- type: precision_at_5
value: 32.879000000000005
- type: recall_at_1
value: 5.288
- type: recall_at_10
value: 16.195
- type: recall_at_100
value: 31.135
- type: recall_at_1000
value: 61.531000000000006
- type: recall_at_3
value: 10.313
- type: recall_at_5
value: 12.754999999999999
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 28.216
- type: map_at_10
value: 42.588
- type: map_at_100
value: 43.702999999999996
- type: map_at_1000
value: 43.739
- type: map_at_3
value: 38.177
- type: map_at_5
value: 40.754000000000005
- type: mrr_at_1
value: 31.866
- type: mrr_at_10
value: 45.189
- type: mrr_at_100
value: 46.056000000000004
- type: mrr_at_1000
value: 46.081
- type: mrr_at_3
value: 41.526999999999994
- type: mrr_at_5
value: 43.704
- type: ndcg_at_1
value: 31.837
- type: ndcg_at_10
value: 50.178
- type: ndcg_at_100
value: 54.98800000000001
- type: ndcg_at_1000
value: 55.812
- type: ndcg_at_3
value: 41.853
- type: ndcg_at_5
value: 46.153
- type: precision_at_1
value: 31.837
- type: precision_at_10
value: 8.43
- type: precision_at_100
value: 1.1119999999999999
- type: precision_at_1000
value: 0.11900000000000001
- type: precision_at_3
value: 19.023
- type: precision_at_5
value: 13.911000000000001
- type: recall_at_1
value: 28.216
- type: recall_at_10
value: 70.8
- type: recall_at_100
value: 91.857
- type: recall_at_1000
value: 97.941
- type: recall_at_3
value: 49.196
- type: recall_at_5
value: 59.072
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 71.22800000000001
- type: map_at_10
value: 85.115
- type: map_at_100
value: 85.72
- type: map_at_1000
value: 85.737
- type: map_at_3
value: 82.149
- type: map_at_5
value: 84.029
- type: mrr_at_1
value: 81.96
- type: mrr_at_10
value: 88.00200000000001
- type: mrr_at_100
value: 88.088
- type: mrr_at_1000
value: 88.089
- type: mrr_at_3
value: 87.055
- type: mrr_at_5
value: 87.715
- type: ndcg_at_1
value: 82.01
- type: ndcg_at_10
value: 88.78
- type: ndcg_at_100
value: 89.91
- type: ndcg_at_1000
value: 90.013
- type: ndcg_at_3
value: 85.957
- type: ndcg_at_5
value: 87.56
- type: precision_at_1
value: 82.01
- type: precision_at_10
value: 13.462
- type: precision_at_100
value: 1.528
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.553
- type: precision_at_5
value: 24.732000000000003
- type: recall_at_1
value: 71.22800000000001
- type: recall_at_10
value: 95.69
- type: recall_at_100
value: 99.531
- type: recall_at_1000
value: 99.98
- type: recall_at_3
value: 87.632
- type: recall_at_5
value: 92.117
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 52.31768034366916
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 60.640266772723606
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.7780000000000005
- type: map_at_10
value: 12.299
- type: map_at_100
value: 14.363000000000001
- type: map_at_1000
value: 14.71
- type: map_at_3
value: 8.738999999999999
- type: map_at_5
value: 10.397
- type: mrr_at_1
value: 23.599999999999998
- type: mrr_at_10
value: 34.845
- type: mrr_at_100
value: 35.916
- type: mrr_at_1000
value: 35.973
- type: mrr_at_3
value: 31.7
- type: mrr_at_5
value: 33.535
- type: ndcg_at_1
value: 23.599999999999998
- type: ndcg_at_10
value: 20.522000000000002
- type: ndcg_at_100
value: 28.737000000000002
- type: ndcg_at_1000
value: 34.596
- type: ndcg_at_3
value: 19.542
- type: ndcg_at_5
value: 16.958000000000002
- type: precision_at_1
value: 23.599999999999998
- type: precision_at_10
value: 10.67
- type: precision_at_100
value: 2.259
- type: precision_at_1000
value: 0.367
- type: precision_at_3
value: 18.333
- type: precision_at_5
value: 14.879999999999999
- type: recall_at_1
value: 4.7780000000000005
- type: recall_at_10
value: 21.617
- type: recall_at_100
value: 45.905
- type: recall_at_1000
value: 74.42
- type: recall_at_3
value: 11.148
- type: recall_at_5
value: 15.082999999999998
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.22372750297885
- type: cos_sim_spearman
value: 79.40972617119405
- type: euclidean_pearson
value: 80.6101072020434
- type: euclidean_spearman
value: 79.53844217225202
- type: manhattan_pearson
value: 80.57265975286111
- type: manhattan_spearman
value: 79.46335611792958
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 85.43713315520749
- type: cos_sim_spearman
value: 77.44128693329532
- type: euclidean_pearson
value: 81.63869928101123
- type: euclidean_spearman
value: 77.29512977961515
- type: manhattan_pearson
value: 81.63704185566183
- type: manhattan_spearman
value: 77.29909412738657
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 81.59451537860527
- type: cos_sim_spearman
value: 82.97994638856723
- type: euclidean_pearson
value: 82.89478688288412
- type: euclidean_spearman
value: 83.58740751053104
- type: manhattan_pearson
value: 82.69140840941608
- type: manhattan_spearman
value: 83.33665956040555
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 82.00756527711764
- type: cos_sim_spearman
value: 81.83560996841379
- type: euclidean_pearson
value: 82.07684151976518
- type: euclidean_spearman
value: 82.00913052060511
- type: manhattan_pearson
value: 82.05690778488794
- type: manhattan_spearman
value: 82.02260252019525
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.13710262895447
- type: cos_sim_spearman
value: 87.26412811156248
- type: euclidean_pearson
value: 86.94151453230228
- type: euclidean_spearman
value: 87.5363796699571
- type: manhattan_pearson
value: 86.86989424083748
- type: manhattan_spearman
value: 87.47315940781353
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 83.0230597603627
- type: cos_sim_spearman
value: 84.93344499318864
- type: euclidean_pearson
value: 84.23754743431141
- type: euclidean_spearman
value: 85.09707376597099
- type: manhattan_pearson
value: 84.04325160987763
- type: manhattan_spearman
value: 84.89353071339909
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 86.75620824563921
- type: cos_sim_spearman
value: 87.15065513706398
- type: euclidean_pearson
value: 88.26281533633521
- type: euclidean_spearman
value: 87.51963738643983
- type: manhattan_pearson
value: 88.25599267618065
- type: manhattan_spearman
value: 87.58048736047483
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 64.74645319195137
- type: cos_sim_spearman
value: 65.29996325037214
- type: euclidean_pearson
value: 67.04297794086443
- type: euclidean_spearman
value: 65.43841726694343
- type: manhattan_pearson
value: 67.39459955690904
- type: manhattan_spearman
value: 65.92864704413651
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.31291020270801
- type: cos_sim_spearman
value: 85.86473738688068
- type: euclidean_pearson
value: 85.65537275064152
- type: euclidean_spearman
value: 86.13087454209642
- type: manhattan_pearson
value: 85.43946955047609
- type: manhattan_spearman
value: 85.91568175344916
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 85.93798118350695
- type: mrr
value: 95.93536274908824
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 57.594
- type: map_at_10
value: 66.81899999999999
- type: map_at_100
value: 67.368
- type: map_at_1000
value: 67.4
- type: map_at_3
value: 64.061
- type: map_at_5
value: 65.47
- type: mrr_at_1
value: 60.667
- type: mrr_at_10
value: 68.219
- type: mrr_at_100
value: 68.655
- type: mrr_at_1000
value: 68.684
- type: mrr_at_3
value: 66.22200000000001
- type: mrr_at_5
value: 67.289
- type: ndcg_at_1
value: 60.667
- type: ndcg_at_10
value: 71.275
- type: ndcg_at_100
value: 73.642
- type: ndcg_at_1000
value: 74.373
- type: ndcg_at_3
value: 66.521
- type: ndcg_at_5
value: 68.581
- type: precision_at_1
value: 60.667
- type: precision_at_10
value: 9.433
- type: precision_at_100
value: 1.0699999999999998
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 25.556
- type: precision_at_5
value: 16.8
- type: recall_at_1
value: 57.594
- type: recall_at_10
value: 83.622
- type: recall_at_100
value: 94.167
- type: recall_at_1000
value: 99.667
- type: recall_at_3
value: 70.64399999999999
- type: recall_at_5
value: 75.983
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.85841584158416
- type: cos_sim_ap
value: 96.66996142314342
- type: cos_sim_f1
value: 92.83208020050125
- type: cos_sim_precision
value: 93.06532663316584
- type: cos_sim_recall
value: 92.60000000000001
- type: dot_accuracy
value: 99.85841584158416
- type: dot_ap
value: 96.6775307676576
- type: dot_f1
value: 92.69289729177312
- type: dot_precision
value: 94.77533960292581
- type: dot_recall
value: 90.7
- type: euclidean_accuracy
value: 99.86138613861387
- type: euclidean_ap
value: 96.6338454403108
- type: euclidean_f1
value: 92.92214357937311
- type: euclidean_precision
value: 93.96728016359918
- type: euclidean_recall
value: 91.9
- type: manhattan_accuracy
value: 99.86237623762376
- type: manhattan_ap
value: 96.60370449645053
- type: manhattan_f1
value: 92.91177970423253
- type: manhattan_precision
value: 94.7970863683663
- type: manhattan_recall
value: 91.10000000000001
- type: max_accuracy
value: 99.86237623762376
- type: max_ap
value: 96.6775307676576
- type: max_f1
value: 92.92214357937311
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 60.77977058695198
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 35.2725272535638
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 53.64052466362125
- type: mrr
value: 54.533067014684654
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 30.677624219206578
- type: cos_sim_spearman
value: 30.121368518123447
- type: dot_pearson
value: 30.69870088041608
- type: dot_spearman
value: 29.61284927093751
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.22
- type: map_at_10
value: 1.855
- type: map_at_100
value: 9.885
- type: map_at_1000
value: 23.416999999999998
- type: map_at_3
value: 0.637
- type: map_at_5
value: 1.024
- type: mrr_at_1
value: 88.0
- type: mrr_at_10
value: 93.067
- type: mrr_at_100
value: 93.067
- type: mrr_at_1000
value: 93.067
- type: mrr_at_3
value: 92.667
- type: mrr_at_5
value: 93.067
- type: ndcg_at_1
value: 82.0
- type: ndcg_at_10
value: 75.899
- type: ndcg_at_100
value: 55.115
- type: ndcg_at_1000
value: 48.368
- type: ndcg_at_3
value: 79.704
- type: ndcg_at_5
value: 78.39699999999999
- type: precision_at_1
value: 88.0
- type: precision_at_10
value: 79.60000000000001
- type: precision_at_100
value: 56.06
- type: precision_at_1000
value: 21.206
- type: precision_at_3
value: 84.667
- type: precision_at_5
value: 83.2
- type: recall_at_1
value: 0.22
- type: recall_at_10
value: 2.078
- type: recall_at_100
value: 13.297
- type: recall_at_1000
value: 44.979
- type: recall_at_3
value: 0.6689999999999999
- type: recall_at_5
value: 1.106
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.258
- type: map_at_10
value: 10.439
- type: map_at_100
value: 16.89
- type: map_at_1000
value: 18.407999999999998
- type: map_at_3
value: 5.668
- type: map_at_5
value: 7.718
- type: mrr_at_1
value: 32.653
- type: mrr_at_10
value: 51.159
- type: mrr_at_100
value: 51.714000000000006
- type: mrr_at_1000
value: 51.714000000000006
- type: mrr_at_3
value: 47.959
- type: mrr_at_5
value: 50.407999999999994
- type: ndcg_at_1
value: 29.592000000000002
- type: ndcg_at_10
value: 26.037
- type: ndcg_at_100
value: 37.924
- type: ndcg_at_1000
value: 49.126999999999995
- type: ndcg_at_3
value: 30.631999999999998
- type: ndcg_at_5
value: 28.571
- type: precision_at_1
value: 32.653
- type: precision_at_10
value: 22.857
- type: precision_at_100
value: 7.754999999999999
- type: precision_at_1000
value: 1.529
- type: precision_at_3
value: 34.014
- type: precision_at_5
value: 29.796
- type: recall_at_1
value: 2.258
- type: recall_at_10
value: 16.554
- type: recall_at_100
value: 48.439
- type: recall_at_1000
value: 82.80499999999999
- type: recall_at_3
value: 7.283
- type: recall_at_5
value: 10.732
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 69.8858
- type: ap
value: 13.835684144362109
- type: f1
value: 53.803351693244586
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 60.50650820599886
- type: f1
value: 60.84357825979259
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 48.52131044852134
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 85.59337187816654
- type: cos_sim_ap
value: 73.23925826533437
- type: cos_sim_f1
value: 67.34693877551021
- type: cos_sim_precision
value: 62.40432237730752
- type: cos_sim_recall
value: 73.13984168865434
- type: dot_accuracy
value: 85.31322644096085
- type: dot_ap
value: 72.30723963807422
- type: dot_f1
value: 66.47051612112296
- type: dot_precision
value: 62.0792305930845
- type: dot_recall
value: 71.53034300791556
- type: euclidean_accuracy
value: 85.61125350181797
- type: euclidean_ap
value: 73.32843720487845
- type: euclidean_f1
value: 67.36549633745895
- type: euclidean_precision
value: 64.60755813953489
- type: euclidean_recall
value: 70.36939313984169
- type: manhattan_accuracy
value: 85.63509566668654
- type: manhattan_ap
value: 73.16658488311325
- type: manhattan_f1
value: 67.20597386434349
- type: manhattan_precision
value: 63.60424028268551
- type: manhattan_recall
value: 71.2401055408971
- type: max_accuracy
value: 85.63509566668654
- type: max_ap
value: 73.32843720487845
- type: max_f1
value: 67.36549633745895
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.33779640625606
- type: cos_sim_ap
value: 84.83868375898157
- type: cos_sim_f1
value: 77.16506154017773
- type: cos_sim_precision
value: 74.62064005753327
- type: cos_sim_recall
value: 79.88912842623961
- type: dot_accuracy
value: 88.02732176815307
- type: dot_ap
value: 83.95089283763002
- type: dot_f1
value: 76.29635101196631
- type: dot_precision
value: 73.31771720613288
- type: dot_recall
value: 79.52725592854944
- type: euclidean_accuracy
value: 88.44452206310397
- type: euclidean_ap
value: 84.98384576824827
- type: euclidean_f1
value: 77.29311047696697
- type: euclidean_precision
value: 74.51232583065381
- type: euclidean_recall
value: 80.28949799815214
- type: manhattan_accuracy
value: 88.47362906042613
- type: manhattan_ap
value: 84.91421462218432
- type: manhattan_f1
value: 77.05107637204792
- type: manhattan_precision
value: 74.74484256243214
- type: manhattan_recall
value: 79.50415768401602
- type: max_accuracy
value: 88.47362906042613
- type: max_ap
value: 84.98384576824827
- type: max_f1
value: 77.29311047696697
license: mit
language:
- en
---
Finetuned using the same data & library as [WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1)
<h1 align="center">FlagEmbedding</h1>
<h4 align="center">
<p>
<a href=#model-list>Model List</a> |
<a href=#frequently-asked-questions>FAQ</a> |
<a href=#usage>Usage</a> |
<a href="#evaluation">Evaluation</a> |
<a href="#train">Train</a> |
<a href="#contact">Contact</a> |
<a href="#citation">Citation</a> |
<a href="#license">License</a>
<p>
</h4>
More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
[English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
And it also can be used in vector databases for LLMs.
************* 🌟**Updates**🌟 *************
- 10/12/2023: Release [LLM-Embedder](./FlagEmbedding/llm_embedder/README.md), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Paper](https://arxiv.org/pdf/2310.07554.pdf) :fire:
- 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
- 09/15/2023: The [masive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
- 09/12/2023: New models:
- **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
- **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
<details>
<summary>More</summary>
<!-- ### More -->
- 09/07/2023: Update [fine-tune code](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md): Add script to mine hard negatives and support adding instruction during fine-tuning.
- 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [this](#using-langchain); C-MTEB **leaderboard** is [available](https://huggingface.co/spaces/mteb/leaderboard).
- 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗**
- 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!** :tada: :tada:
- 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset.
</details>
## Model List
`bge` is short for `BAAI general embedding`.
| Model | Language | | Description | query instruction for retrieval [1] |
|:-------------------------------|:--------:| :--------:| :--------:|:--------:|
| [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章:` |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章:` |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章:` |
| [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章:` |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章:` |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章:` |
[1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** needs to be added to passages.
[2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.
For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results.
All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI.
If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models .
## Frequently asked questions
<details>
<summary>1. How to fine-tune bge embedding model?</summary>
<!-- ### How to fine-tune bge embedding model? -->
Following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to prepare data and fine-tune your model.
Some suggestions:
- Mine hard negatives following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives), which can improve the retrieval performance.
- If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity.
- If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker.
</details>
<details>
<summary>2. The similarity score between two dissimilar sentences is higher than 0.5</summary>
<!-- ### The similarity score between two dissimilar sentences is higher than 0.5 -->
**Suggest to use bge v1.5, which alleviates the issue of the similarity distribution.**
Since we finetune the models by contrastive learning with a temperature of 0.01,
the similarity distribution of the current BGE model is about in the interval \[0.6, 1\].
So a similarity score greater than 0.5 does not indicate that the two sentences are similar.
For downstream tasks, such as passage retrieval or semantic similarity,
**what matters is the relative order of the scores, not the absolute value.**
If you need to filter similar sentences based on a similarity threshold,
please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9).
</details>
<details>
<summary>3. When does the query instruction need to be used</summary>
<!-- ### When does the query instruction need to be used -->
For the `bge-*-v1.5`, we improve its retrieval ability when not using instruction.
No instruction only has a slight degradation in retrieval performance compared with using instruction.
So you can generate embedding without instruction in all cases for convenience.
For a retrieval task that uses short queries to find long related documents,
it is recommended to add instructions for these short queries.
**The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task.**
In all cases, the documents/passages do not need to add the instruction.
</details>
## Usage
### Usage for Embedding Model
Here are some examples for using `bge` models with
[FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers).
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding.
```python
from FlagEmbedding import FlagModel
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = FlagModel('BAAI/bge-large-zh-v1.5',
query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章:",
use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
embeddings_1 = model.encode(sentences_1)
embeddings_2 = model.encode(sentences_2)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query
# corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
q_embeddings = model.encode_queries(queries)
p_embeddings = model.encode(passages)
scores = q_embeddings @ p_embeddings.T
```
For the value of the argument `query_instruction_for_retrieval`, see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list).
By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs.
You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable.
#### Using Sentence-Transformers
You can also use the `bge` models with [sentence-transformers](https://www.SBERT.net):
```
pip install -U sentence-transformers
```
```python
from sentence_transformers import SentenceTransformer
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
```
For s2p(short query to long passage) retrieval task,
each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)).
But the instruction is not needed for passages.
```python
from sentence_transformers import SentenceTransformer
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
instruction = "为这个句子生成表示以用于检索相关文章:"
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)
scores = q_embeddings @ p_embeddings.T
```
#### Using Langchain
You can use `bge` in langchain like this:
```python
from langchain.embeddings import HuggingFaceBgeEmbeddings
model_name = "BAAI/bge-large-en-v1.5"
model_kwargs = {'device': 'cuda'}
encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
model = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
query_instruction="为这个句子生成表示以用于检索相关文章:"
)
model.query_instruction = "为这个句子生成表示以用于检索相关文章:"
```
#### Using HuggingFace Transformers
With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Sentences we want sentence embeddings for
sentences = ["样例数据-1", "样例数据-2"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh-v1.5')
model = AutoModel.from_pretrained('BAAI/bge-large-zh-v1.5')
model.eval()
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages)
# encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, cls pooling.
sentence_embeddings = model_output[0][:, 0]
# normalize embeddings
sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:", sentence_embeddings)
```
### Usage for Reranker
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding.
You can get a relevance score by inputting query and passage to the reranker.
The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range.
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
Get relevance scores (higher scores indicate more relevance):
```python
from FlagEmbedding import FlagReranker
reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score)
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores)
```
#### Using Huggingface transformers
```python
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large')
model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-large')
model.eval()
pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
with torch.no_grad():
inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
print(scores)
```
## Evaluation
`baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!**
For more details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md).
- **MTEB**:
| Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) |
|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | **64.23** | **54.29** | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 |
| [bge-large-en](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 |
| [bge-base-en](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 |
| [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 |
| [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 |
| [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 |
| [bge-small-en](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 |
| [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 |
| [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 |
| [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 |
| [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 |
| [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 |
| [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 |
| [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 |
| [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 |
- **C-MTEB**:
We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks.
Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction.
| Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| [**BAAI/bge-large-zh-v1.5**](https://huggingface.co/BAAI/bge-large-zh-v1.5) | 1024 | **64.53** | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 |
| [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 |
| [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 |
| [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 |
| [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 |
| [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 |
| [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 |
| [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 |
| [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 |
| [text2vec-base](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 |
| [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 |
- **Reranking**:
See [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/) for evaluation script.
| Model | T2Reranking | T2RerankingZh2En\* | T2RerankingEn2Zh\* | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 |
| multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 |
| multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 |
| multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 |
| m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 |
| m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 |
| bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 |
| bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 |
\* : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks
## Train
### BAAI Embedding
We pre-train the models using [retromae](https://github.com/staoxiao/RetroMAE) and train them on large-scale pairs data using contrastive learning.
**You can fine-tune the embedding model on your data following our [examples](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).**
We also provide a [pre-train example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain).
Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned.
More training details for bge see [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md).
### BGE Reranker
Cross-encoder will perform full-attention over the input pair,
which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model.
Therefore, it can be used to re-rank the top-k documents returned by embedding model.
We train the cross-encoder on a multilingual pair data,
The data format is the same as embedding model, so you can fine-tune it easily following our [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker).
More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
## Contact
If you have any question or suggestion related to this project, feel free to open an issue or pull request.
You also can email Shitao Xiao([email protected]) and Zheng Liu([email protected]).
## Citation
If you find this repository useful, please consider giving a star :star: and citation
```
@misc{bge_embedding,
title={C-Pack: Packaged Resources To Advance General Chinese Embedding},
author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
year={2023},
eprint={2309.07597},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## License
FlagEmbedding is licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.
|
dhruvilHV/initial_ViT_model | dhruvilHV | 2024-01-09T12:48:25Z | 177 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:fair_face",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-01-08T09:49:25Z | ---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- fair_face
metrics:
- accuracy
model-index:
- name: initial_ViT_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: fair_face
type: fair_face
config: '0.25'
split: validation
args: '0.25'
metrics:
- name: Accuracy
type: accuracy
value: 0.21252510498448055
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# initial_ViT_model
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the fair_face dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6347
- Accuracy: 0.2125
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 4.7855 | 0.15 | 50 | 4.6444 | 0.0511 |
| 4.4242 | 0.29 | 100 | 4.2124 | 0.1418 |
| 4.0596 | 0.44 | 150 | 3.9402 | 0.1744 |
| 3.859 | 0.59 | 200 | 3.7823 | 0.1956 |
| 3.7392 | 0.74 | 250 | 3.6877 | 0.2105 |
| 3.6424 | 0.88 | 300 | 3.6347 | 0.2125 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
ugursa/FinancialBERT-Yahoo-Finance-Sentiment-Analysis | ugursa | 2024-01-09T12:33:23Z | 102 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:ugursa/Yahoo-Finance-News-Sentences",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-06T14:42:13Z | ---
datasets:
- ugursa/Yahoo-Finance-News-Sentences
language:
- en
metrics:
- accuracy
- f1
- precision
- recall
library_name: transformers
pipeline_tag: text-classification
widget:
- text: "Microsoft's financial backing for ChatGPT maker OpenAI may be subject to EU merger rules, EU antitrust regulators said on Tuesday, underscoring a similar warning from its UK peer in December."
example_title: "Bearish Sentence"
- text: "Volumes for CME lithium, launched in 2021, climbed to 20,307 metric tons in 2023 from 468 tons in 2022."
example_title: "Bullish Sentence"
- text: "Investors will get a window into America's largest banks later when the CEOs of JPMorgan Chase (JPM), Goldman Sachs (GS), and Bank of America (BAC), among others, give testimony before the Senate’s banking committee."
example_title: "Neutral Sentence"
--- |
darinchau/checkpoints | darinchau | 2024-01-09T12:22:35Z | 61 | 0 | transformers | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:darinchau/checkpoints",
"base_model:finetune:darinchau/checkpoints",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-01-09T03:09:38Z | ---
license: apache-2.0
base_model: darinchau/checkpoints
tags:
- generated_from_trainer
model-index:
- name: checkpoints
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# checkpoints
This model is a fine-tuned version of [darinchau/checkpoints](https://huggingface.co/darinchau/checkpoints) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.8289
- eval_cer: 79.9622
- eval_runtime: 31.6459
- eval_samples_per_second: 3.16
- eval_steps_per_second: 0.221
- epoch: 35.11
- step: 3300
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
gsl22/ellis-v1-emotion-leadership12 | gsl22 | 2024-01-09T12:18:18Z | 92 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T12:13:14Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ellis-v1-emotion-leadership12
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ellis-v1-emotion-leadership12
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3768
- Accuracy: 0.8757
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.425 | 1.0 | 3154 | 0.3768 | 0.8757 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
papahawk/devi-7b | papahawk | 2024-01-09T12:12:44Z | 13 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"conversational",
"en",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"arxiv:2305.18290",
"arxiv:2310.16944",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:finetune:HuggingFaceH4/zephyr-7b-beta",
"license:mit",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-07T05:37:39Z | ---
tags:
- generated_from_trainer
license: mit
datasets:
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
base_model: HuggingFaceH4/zephyr-7b-beta
pipeline_tag: text-generation
model-index:
- name: devi-7b
description: "Initial fork of Zephyr 7B β, with plans for GGML integration and further development."
results:
# AI2 Reasoning Challenge (25-Shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
name: normalized accuracy
value: 62.03071672354948
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# HellaSwag (10-shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
name: normalized accuracy
value: 84.35570603465445
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# DROP (3-shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: Drop (3-Shot)
type: drop
split: validation
args:
num_few_shot: 3
metrics:
- type: f1
name: f1 score
value: 9.662437080536909
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# TruthfulQA (0-shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 57.44916942762855
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# GSM8k (5-shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
name: accuracy
value: 12.736921910538287
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# MMLU (5-Shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
name: accuracy
value: 61.07
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# Winogrande (5-shot)
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
name: accuracy
value: 77.74269928966061
source:
name: Open LLM Leaderboard
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
# AlpacaEval (taken from model card)
- task:
type: text-generation
name: Text Generation
dataset:
name: AlpacaEval
type: tatsu-lab/alpaca_eval
metrics:
- type: unknown
name: win rate
value: 0.9060
source:
url: https://tatsu-lab.github.io/alpaca_eval/
# MT-Bench (taken from model card)
- task:
type: text-generation
name: Text Generation
dataset:
name: MT-Bench
type: unknown
metrics:
- type: unknown
name: score
value: 7.34
source:
url: https://huggingface.co/spaces/lmsys/mt-bench
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
<h2 style='text-align: center'>Devi 7B</h2>
<h2 style='text-align: center'>Fork of Zephyr 7B β</h2>
<h2 style='text-align: center '><em>All thanks to HuggingFaceH4 for their work!</em> </h2>
<img src="https://alt-web.xyz/images/rainbow.png" alt="Rainbow Solutions" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
## Model description
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **License:** MIT
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/huggingface/alignment-handbook
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
- **Chatbot Arena:** Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org
## Performance
At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
| Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
|-------------|-----|----|---------------|--------------|
| StableLM-Tuned-α | 7B| dSFT |2.75| -|
| MPT-Chat | 7B |dSFT |5.42| -|
| Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
| Mistral-Instructv0.1 | 7B| - | 6.84 |-|
| Zephyr-7b-α |7B| dDPO| 6.88| -|
| **Zephyr-7b-β** 🪁 | **7B** | **dDPO** | **7.34** | **90.60** |
| Falcon-Instruct | 40B |dSFT |5.17 |45.71|
| Guanaco | 65B | SFT |6.41| 71.80|
| Llama2-Chat | 70B |RLHF |6.86| 92.66|
| Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
| WizardLM v1.0 | 70B |dSFT |7.71 |-|
| Xwin-LM v0.1 | 70B |dPPO |- |95.57|
| GPT-3.5-turbo | - |RLHF |7.94 |89.37|
| Claude 2 | - |RLHF |8.06| 91.36|
| GPT-4 | -| RLHF |8.99| 95.28|
In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:

However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.
## Intended uses & limitations
The model was initially fine-tuned on a filtered and preprocessed of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
You can find the datasets used for training Zephyr-7B-β [here](https://huggingface.co/collections/HuggingFaceH4/zephyr-7b-6538c6d6d5ddd1cbb1744a66)
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
```
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
## Training and evaluation data
During DPO training, this model achieves the following results on the evaluation set:
- Loss: 0.7496
- Rewards/chosen: -4.5221
- Rewards/rejected: -8.3184
- Rewards/accuracies: 0.7812
- Rewards/margins: 3.7963
- Logps/rejected: -340.1541
- Logps/chosen: -299.4561
- Logits/rejected: -2.3081
- Logits/chosen: -2.3531
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
### Training results
The table below shows the full set of DPO training metrics:
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6284 | 0.05 | 100 | 0.6098 | 0.0425 | -0.1872 | 0.7344 | 0.2297 | -258.8416 | -253.8099 | -2.7976 | -2.8234 |
| 0.4908 | 0.1 | 200 | 0.5426 | -0.0279 | -0.6842 | 0.75 | 0.6563 | -263.8124 | -254.5145 | -2.7719 | -2.7960 |
| 0.5264 | 0.15 | 300 | 0.5324 | 0.0414 | -0.9793 | 0.7656 | 1.0207 | -266.7627 | -253.8209 | -2.7892 | -2.8122 |
| 0.5536 | 0.21 | 400 | 0.4957 | -0.0185 | -1.5276 | 0.7969 | 1.5091 | -272.2460 | -254.4203 | -2.8542 | -2.8764 |
| 0.5362 | 0.26 | 500 | 0.5031 | -0.2630 | -1.5917 | 0.7812 | 1.3287 | -272.8869 | -256.8653 | -2.8702 | -2.8958 |
| 0.5966 | 0.31 | 600 | 0.5963 | -0.2993 | -1.6491 | 0.7812 | 1.3499 | -273.4614 | -257.2279 | -2.8778 | -2.8986 |
| 0.5014 | 0.36 | 700 | 0.5382 | -0.2859 | -1.4750 | 0.75 | 1.1891 | -271.7204 | -257.0942 | -2.7659 | -2.7869 |
| 0.5334 | 0.41 | 800 | 0.5677 | -0.4289 | -1.8968 | 0.7969 | 1.4679 | -275.9378 | -258.5242 | -2.7053 | -2.7265 |
| 0.5251 | 0.46 | 900 | 0.5772 | -0.2116 | -1.3107 | 0.7344 | 1.0991 | -270.0768 | -256.3507 | -2.8463 | -2.8662 |
| 0.5205 | 0.52 | 1000 | 0.5262 | -0.3792 | -1.8585 | 0.7188 | 1.4793 | -275.5552 | -258.0276 | -2.7893 | -2.7979 |
| 0.5094 | 0.57 | 1100 | 0.5433 | -0.6279 | -1.9368 | 0.7969 | 1.3089 | -276.3377 | -260.5136 | -2.7453 | -2.7536 |
| 0.5837 | 0.62 | 1200 | 0.5349 | -0.3780 | -1.9584 | 0.7656 | 1.5804 | -276.5542 | -258.0154 | -2.7643 | -2.7756 |
| 0.5214 | 0.67 | 1300 | 0.5732 | -1.0055 | -2.2306 | 0.7656 | 1.2251 | -279.2761 | -264.2903 | -2.6986 | -2.7113 |
| 0.6914 | 0.72 | 1400 | 0.5137 | -0.6912 | -2.1775 | 0.7969 | 1.4863 | -278.7448 | -261.1467 | -2.7166 | -2.7275 |
| 0.4655 | 0.77 | 1500 | 0.5090 | -0.7987 | -2.2930 | 0.7031 | 1.4943 | -279.8999 | -262.2220 | -2.6651 | -2.6838 |
| 0.5731 | 0.83 | 1600 | 0.5312 | -0.8253 | -2.3520 | 0.7812 | 1.5268 | -280.4902 | -262.4876 | -2.6543 | -2.6728 |
| 0.5233 | 0.88 | 1700 | 0.5206 | -0.4573 | -2.0951 | 0.7812 | 1.6377 | -277.9205 | -258.8084 | -2.6870 | -2.7097 |
| 0.5593 | 0.93 | 1800 | 0.5231 | -0.5508 | -2.2000 | 0.7969 | 1.6492 | -278.9703 | -259.7433 | -2.6221 | -2.6519 |
| 0.4967 | 0.98 | 1900 | 0.5290 | -0.5340 | -1.9570 | 0.8281 | 1.4230 | -276.5395 | -259.5749 | -2.6564 | -2.6878 |
| 0.0921 | 1.03 | 2000 | 0.5368 | -1.1376 | -3.1615 | 0.7812 | 2.0239 | -288.5854 | -265.6111 | -2.6040 | -2.6345 |
| 0.0733 | 1.08 | 2100 | 0.5453 | -1.1045 | -3.4451 | 0.7656 | 2.3406 | -291.4208 | -265.2799 | -2.6289 | -2.6595 |
| 0.0972 | 1.14 | 2200 | 0.5571 | -1.6915 | -3.9823 | 0.8125 | 2.2908 | -296.7934 | -271.1505 | -2.6471 | -2.6709 |
| 0.1058 | 1.19 | 2300 | 0.5789 | -1.0621 | -3.8941 | 0.7969 | 2.8319 | -295.9106 | -264.8563 | -2.5527 | -2.5798 |
| 0.2423 | 1.24 | 2400 | 0.5455 | -1.1963 | -3.5590 | 0.7812 | 2.3627 | -292.5599 | -266.1981 | -2.5414 | -2.5784 |
| 0.1177 | 1.29 | 2500 | 0.5889 | -1.8141 | -4.3942 | 0.7969 | 2.5801 | -300.9120 | -272.3761 | -2.4802 | -2.5189 |
| 0.1213 | 1.34 | 2600 | 0.5683 | -1.4608 | -3.8420 | 0.8125 | 2.3812 | -295.3901 | -268.8436 | -2.4774 | -2.5207 |
| 0.0889 | 1.39 | 2700 | 0.5890 | -1.6007 | -3.7337 | 0.7812 | 2.1330 | -294.3068 | -270.2423 | -2.4123 | -2.4522 |
| 0.0995 | 1.45 | 2800 | 0.6073 | -1.5519 | -3.8362 | 0.8281 | 2.2843 | -295.3315 | -269.7538 | -2.4685 | -2.5050 |
| 0.1145 | 1.5 | 2900 | 0.5790 | -1.7939 | -4.2876 | 0.8438 | 2.4937 | -299.8461 | -272.1744 | -2.4272 | -2.4674 |
| 0.0644 | 1.55 | 3000 | 0.5735 | -1.7285 | -4.2051 | 0.8125 | 2.4766 | -299.0209 | -271.5201 | -2.4193 | -2.4574 |
| 0.0798 | 1.6 | 3100 | 0.5537 | -1.7226 | -4.2850 | 0.8438 | 2.5624 | -299.8200 | -271.4610 | -2.5367 | -2.5696 |
| 0.1013 | 1.65 | 3200 | 0.5575 | -1.5715 | -3.9813 | 0.875 | 2.4098 | -296.7825 | -269.9498 | -2.4926 | -2.5267 |
| 0.1254 | 1.7 | 3300 | 0.5905 | -1.6412 | -4.4703 | 0.8594 | 2.8291 | -301.6730 | -270.6473 | -2.5017 | -2.5340 |
| 0.085 | 1.76 | 3400 | 0.6133 | -1.9159 | -4.6760 | 0.8438 | 2.7601 | -303.7296 | -273.3941 | -2.4614 | -2.4960 |
| 0.065 | 1.81 | 3500 | 0.6074 | -1.8237 | -4.3525 | 0.8594 | 2.5288 | -300.4951 | -272.4724 | -2.4597 | -2.5004 |
| 0.0755 | 1.86 | 3600 | 0.5836 | -1.9252 | -4.4005 | 0.8125 | 2.4753 | -300.9748 | -273.4872 | -2.4327 | -2.4716 |
| 0.0746 | 1.91 | 3700 | 0.5789 | -1.9280 | -4.4906 | 0.8125 | 2.5626 | -301.8762 | -273.5149 | -2.4686 | -2.5115 |
| 0.1348 | 1.96 | 3800 | 0.6015 | -1.8658 | -4.2428 | 0.8281 | 2.3769 | -299.3976 | -272.8936 | -2.4943 | -2.5393 |
| 0.0217 | 2.01 | 3900 | 0.6122 | -2.3335 | -4.9229 | 0.8281 | 2.5894 | -306.1988 | -277.5699 | -2.4841 | -2.5272 |
| 0.0219 | 2.07 | 4000 | 0.6522 | -2.9890 | -6.0164 | 0.8281 | 3.0274 | -317.1334 | -284.1248 | -2.4105 | -2.4545 |
| 0.0119 | 2.12 | 4100 | 0.6922 | -3.4777 | -6.6749 | 0.7969 | 3.1972 | -323.7187 | -289.0121 | -2.4272 | -2.4699 |
| 0.0153 | 2.17 | 4200 | 0.6993 | -3.2406 | -6.6775 | 0.7969 | 3.4369 | -323.7453 | -286.6413 | -2.4047 | -2.4465 |
| 0.011 | 2.22 | 4300 | 0.7178 | -3.7991 | -7.4397 | 0.7656 | 3.6406 | -331.3667 | -292.2260 | -2.3843 | -2.4290 |
| 0.0072 | 2.27 | 4400 | 0.6840 | -3.3269 | -6.8021 | 0.8125 | 3.4752 | -324.9908 | -287.5042 | -2.4095 | -2.4536 |
| 0.0197 | 2.32 | 4500 | 0.7013 | -3.6890 | -7.3014 | 0.8125 | 3.6124 | -329.9841 | -291.1250 | -2.4118 | -2.4543 |
| 0.0182 | 2.37 | 4600 | 0.7476 | -3.8994 | -7.5366 | 0.8281 | 3.6372 | -332.3356 | -293.2291 | -2.4163 | -2.4565 |
| 0.0125 | 2.43 | 4700 | 0.7199 | -4.0560 | -7.5765 | 0.8438 | 3.5204 | -332.7345 | -294.7952 | -2.3699 | -2.4100 |
| 0.0082 | 2.48 | 4800 | 0.7048 | -3.6613 | -7.1356 | 0.875 | 3.4743 | -328.3255 | -290.8477 | -2.3925 | -2.4303 |
| 0.0118 | 2.53 | 4900 | 0.6976 | -3.7908 | -7.3152 | 0.8125 | 3.5244 | -330.1224 | -292.1431 | -2.3633 | -2.4047 |
| 0.0118 | 2.58 | 5000 | 0.7198 | -3.9049 | -7.5557 | 0.8281 | 3.6508 | -332.5271 | -293.2844 | -2.3764 | -2.4194 |
| 0.006 | 2.63 | 5100 | 0.7506 | -4.2118 | -7.9149 | 0.8125 | 3.7032 | -336.1194 | -296.3530 | -2.3407 | -2.3860 |
| 0.0143 | 2.68 | 5200 | 0.7408 | -4.2433 | -7.9802 | 0.8125 | 3.7369 | -336.7721 | -296.6682 | -2.3509 | -2.3946 |
| 0.0057 | 2.74 | 5300 | 0.7552 | -4.3392 | -8.0831 | 0.7969 | 3.7439 | -337.8013 | -297.6275 | -2.3388 | -2.3842 |
| 0.0138 | 2.79 | 5400 | 0.7404 | -4.2395 | -7.9762 | 0.8125 | 3.7367 | -336.7322 | -296.6304 | -2.3286 | -2.3737 |
| 0.0079 | 2.84 | 5500 | 0.7525 | -4.4466 | -8.2196 | 0.7812 | 3.7731 | -339.1662 | -298.7007 | -2.3200 | -2.3641 |
| 0.0077 | 2.89 | 5600 | 0.7520 | -4.5586 | -8.3485 | 0.7969 | 3.7899 | -340.4545 | -299.8206 | -2.3078 | -2.3517 |
| 0.0094 | 2.94 | 5700 | 0.7527 | -4.5542 | -8.3509 | 0.7812 | 3.7967 | -340.4790 | -299.7773 | -2.3062 | -2.3510 |
| 0.0054 | 2.99 | 5800 | 0.7520 | -4.5169 | -8.3079 | 0.7812 | 3.7911 | -340.0493 | -299.4038 | -2.3081 | -2.3530 |
### Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.14.0
## Citation
If you find Zephyr-7B-β is useful in your work, please cite it with:
```
@misc{tunstall2023zephyr,
title={Zephyr: Direct Distillation of LM Alignment},
author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
year={2023},
eprint={2310.16944},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 52.15 |
| ARC (25-shot) | 62.03 |
| HellaSwag (10-shot) | 84.36 |
| MMLU (5-shot) | 61.07 |
| TruthfulQA (0-shot) | 57.45 |
| Winogrande (5-shot) | 77.74 |
| GSM8K (5-shot) | 12.74 |
| DROP (3-shot) | 9.66 | |
Harshitha0813/intent-classification | Harshitha0813 | 2024-01-09T12:03:07Z | 44 | 0 | transformers | [
"transformers",
"tf",
"xlm-roberta",
"text-classification",
"generated_from_keras_callback",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-05T06:47:17Z | ---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_keras_callback
model-index:
- name: Harshitha0813/intent-classification
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Harshitha0813/intent-classification
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.5007
- Validation Loss: 1.4990
- Train Accuracy: 0.4564
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 8, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 1.5007 | 1.4990 | 0.4564 | 0 |
### Framework versions
- Transformers 4.32.1
- TensorFlow 2.15.0
- Datasets 2.12.0
- Tokenizers 0.13.2
|
samwell/dqn-SpaceInvadersNoFrameskip-v41 | samwell | 2024-01-09T12:02:43Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T12:02:12Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 570.50 +/- 203.91
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga samwell -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga samwell -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga samwell
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
gagan3012/MetaModelv3 | gagan3012 | 2024-01-09T12:01:23Z | 1,549 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"MetaModelv3",
"merge",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-05T22:55:00Z | ---
license: apache-2.0
tags:
- MetaModelv3
- merge
---
# MetaModelv3
This model is a hybrid of the following models and is trained using the following configuration:
* [jeonsworld/CarbonVillain-en-10.7B-v4](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v4)
* [jeonsworld/CarbonVillain-en-10.7B-v2](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v2)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_gagan3012__MetaModelv3)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 74.39 |
| ARC (25-shot) | 71.16 |
| HellaSwag (10-shot) | 88.39 |
| MMLU (5-shot) | 66.32 |
| TruthfulQA (0-shot) | 71.86 |
| Winogrande (5-shot) | 83.35 |
| GSM8K (5-shot) | 65.28 |
|
gagan3012/MetaModelv2 | gagan3012 | 2024-01-09T12:00:35Z | 1,543 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"MetaModelv2",
"merge",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-03T15:04:33Z | ---
license: apache-2.0
tags:
- MetaModelv2
- merge
---
# MetaModelv2
This model is a hybrid of the following models and is trained using the following configuration:
* [VAGOsolutions/SauerkrautLM-SOLAR-Instruct](https://huggingface.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct)
* [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_gagan3012__MetaModelv2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 74.24 |
| ARC (25-shot) | 71.08 |
| HellaSwag (10-shot) | 88.56 |
| MMLU (5-shot) | 66.29 |
| TruthfulQA (0-shot) | 71.94 |
| Winogrande (5-shot) | 83.11 |
| GSM8K (5-shot) | 64.44 |
|
gagan3012/MetaModel | gagan3012 | 2024-01-09T11:59:50Z | 1,550 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-03T11:26:23Z | ---
license: apache-2.0
tags:
- merge
- mergekit
---
# MetaModel
This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):
* [jeonsworld/CarbonVillain-en-10.7B-v4](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v4)
* [kekmodel/StopCarbon-10.7B-v5](https://huggingface.co/kekmodel/StopCarbon-10.7B-v5)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: jeonsworld/CarbonVillain-en-10.7B-v4
layer_range: [0, 48]
- model: kekmodel/StopCarbon-10.7B-v5
layer_range: [0, 48]
merge_method: slerp
base_model: jeonsworld/CarbonVillain-en-10.7B-v4
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
# Dataset Card for Evaluation run of gagan3012/MetaModel
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [gagan3012/MetaModel](https://huggingface.co/gagan3012/MetaModel) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_gagan3012__MetaModel",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2024-01-04T14:09:43.780941](https://huggingface.co/datasets/open-llm-leaderboard/details_gagan3012__MetaModel/blob/main/results_2024-01-04T14-09-43.780941.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.6664380298886512,
"acc_stderr": 0.031642195230944255,
"acc_norm": 0.6671639222858992,
"acc_norm_stderr": 0.03228745343467652,
"mc1": 0.5691554467564259,
"mc1_stderr": 0.01733527247533237,
"mc2": 0.7184177934834866,
"mc2_stderr": 0.014995634120330182
},
"harness|arc:challenge|25": {
"acc": 0.6843003412969283,
"acc_stderr": 0.013582571095815291,
"acc_norm": 0.7107508532423208,
"acc_norm_stderr": 0.01325001257939344
},
"harness|hellaswag|10": {
"acc": 0.7132045409281019,
"acc_stderr": 0.004513409114983828,
"acc_norm": 0.8844851623182632,
"acc_norm_stderr": 0.0031898897894046684
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.43,
"acc_stderr": 0.049756985195624284,
"acc_norm": 0.43,
"acc_norm_stderr": 0.049756985195624284
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6148148148148148,
"acc_stderr": 0.04203921040156279,
"acc_norm": 0.6148148148148148,
"acc_norm_stderr": 0.04203921040156279
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.743421052631579,
"acc_stderr": 0.0355418036802569,
"acc_norm": 0.743421052631579,
"acc_norm_stderr": 0.0355418036802569
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6830188679245283,
"acc_stderr": 0.02863723563980089,
"acc_norm": 0.6830188679245283,
"acc_norm_stderr": 0.02863723563980089
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7638888888888888,
"acc_stderr": 0.03551446610810826,
"acc_norm": 0.7638888888888888,
"acc_norm_stderr": 0.03551446610810826
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.47,
"acc_stderr": 0.050161355804659205,
"acc_norm": 0.47,
"acc_norm_stderr": 0.050161355804659205
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.48,
"acc_stderr": 0.05021167315686781,
"acc_norm": 0.48,
"acc_norm_stderr": 0.05021167315686781
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.32,
"acc_stderr": 0.046882617226215034,
"acc_norm": 0.32,
"acc_norm_stderr": 0.046882617226215034
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6647398843930635,
"acc_stderr": 0.03599586301247077,
"acc_norm": 0.6647398843930635,
"acc_norm_stderr": 0.03599586301247077
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.38235294117647056,
"acc_stderr": 0.04835503696107223,
"acc_norm": 0.38235294117647056,
"acc_norm_stderr": 0.04835503696107223
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.625531914893617,
"acc_stderr": 0.03163910665367291,
"acc_norm": 0.625531914893617,
"acc_norm_stderr": 0.03163910665367291
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.4824561403508772,
"acc_stderr": 0.04700708033551038,
"acc_norm": 0.4824561403508772,
"acc_norm_stderr": 0.04700708033551038
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.6413793103448275,
"acc_stderr": 0.039966295748767186,
"acc_norm": 0.6413793103448275,
"acc_norm_stderr": 0.039966295748767186
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.5,
"acc_stderr": 0.025751310131230234,
"acc_norm": 0.5,
"acc_norm_stderr": 0.025751310131230234
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.42857142857142855,
"acc_stderr": 0.0442626668137991,
"acc_norm": 0.42857142857142855,
"acc_norm_stderr": 0.0442626668137991
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.35,
"acc_norm_stderr": 0.047937248544110196
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.8129032258064516,
"acc_stderr": 0.022185710092252252,
"acc_norm": 0.8129032258064516,
"acc_norm_stderr": 0.022185710092252252
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5073891625615764,
"acc_stderr": 0.035176035403610105,
"acc_norm": 0.5073891625615764,
"acc_norm_stderr": 0.035176035403610105
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.72,
"acc_stderr": 0.04512608598542128,
"acc_norm": 0.72,
"acc_norm_stderr": 0.04512608598542128
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.8121212121212121,
"acc_stderr": 0.03050193405942914,
"acc_norm": 0.8121212121212121,
"acc_norm_stderr": 0.03050193405942914
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.8636363636363636,
"acc_stderr": 0.024450155973189835,
"acc_norm": 0.8636363636363636,
"acc_norm_stderr": 0.024450155973189835
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8963730569948186,
"acc_stderr": 0.021995311963644244,
"acc_norm": 0.8963730569948186,
"acc_norm_stderr": 0.021995311963644244
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6692307692307692,
"acc_stderr": 0.02385479568097114,
"acc_norm": 0.6692307692307692,
"acc_norm_stderr": 0.02385479568097114
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.37037037037037035,
"acc_stderr": 0.02944316932303154,
"acc_norm": 0.37037037037037035,
"acc_norm_stderr": 0.02944316932303154
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.7142857142857143,
"acc_stderr": 0.029344572500634332,
"acc_norm": 0.7142857142857143,
"acc_norm_stderr": 0.029344572500634332
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.3708609271523179,
"acc_stderr": 0.03943966699183629,
"acc_norm": 0.3708609271523179,
"acc_norm_stderr": 0.03943966699183629
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8422018348623853,
"acc_stderr": 0.01563002297009246,
"acc_norm": 0.8422018348623853,
"acc_norm_stderr": 0.01563002297009246
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5740740740740741,
"acc_stderr": 0.03372343271653062,
"acc_norm": 0.5740740740740741,
"acc_norm_stderr": 0.03372343271653062
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8578431372549019,
"acc_stderr": 0.02450980392156862,
"acc_norm": 0.8578431372549019,
"acc_norm_stderr": 0.02450980392156862
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8565400843881856,
"acc_stderr": 0.022818291821017012,
"acc_norm": 0.8565400843881856,
"acc_norm_stderr": 0.022818291821017012
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.672645739910314,
"acc_stderr": 0.03149384670994131,
"acc_norm": 0.672645739910314,
"acc_norm_stderr": 0.03149384670994131
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7557251908396947,
"acc_stderr": 0.03768335959728743,
"acc_norm": 0.7557251908396947,
"acc_norm_stderr": 0.03768335959728743
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7851239669421488,
"acc_stderr": 0.037494924487096966,
"acc_norm": 0.7851239669421488,
"acc_norm_stderr": 0.037494924487096966
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8055555555555556,
"acc_stderr": 0.038260763248848646,
"acc_norm": 0.8055555555555556,
"acc_norm_stderr": 0.038260763248848646
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.754601226993865,
"acc_stderr": 0.03380939813943354,
"acc_norm": 0.754601226993865,
"acc_norm_stderr": 0.03380939813943354
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.4732142857142857,
"acc_stderr": 0.047389751192741546,
"acc_norm": 0.4732142857142857,
"acc_norm_stderr": 0.047389751192741546
},
"harness|hendrycksTest-management|5": {
"acc": 0.8446601941747572,
"acc_stderr": 0.035865947385739734,
"acc_norm": 0.8446601941747572,
"acc_norm_stderr": 0.035865947385739734
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8589743589743589,
"acc_stderr": 0.02280138253459753,
"acc_norm": 0.8589743589743589,
"acc_norm_stderr": 0.02280138253459753
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.7,
"acc_stderr": 0.046056618647183814,
"acc_norm": 0.7,
"acc_norm_stderr": 0.046056618647183814
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8084291187739464,
"acc_stderr": 0.014072859310451949,
"acc_norm": 0.8084291187739464,
"acc_norm_stderr": 0.014072859310451949
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7572254335260116,
"acc_stderr": 0.023083658586984204,
"acc_norm": 0.7572254335260116,
"acc_norm_stderr": 0.023083658586984204
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.39664804469273746,
"acc_stderr": 0.016361354769822468,
"acc_norm": 0.39664804469273746,
"acc_norm_stderr": 0.016361354769822468
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7581699346405228,
"acc_stderr": 0.024518195641879334,
"acc_norm": 0.7581699346405228,
"acc_norm_stderr": 0.024518195641879334
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7202572347266881,
"acc_stderr": 0.025494259350694905,
"acc_norm": 0.7202572347266881,
"acc_norm_stderr": 0.025494259350694905
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7777777777777778,
"acc_stderr": 0.02313237623454333,
"acc_norm": 0.7777777777777778,
"acc_norm_stderr": 0.02313237623454333
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.5035460992907801,
"acc_stderr": 0.02982674915328092,
"acc_norm": 0.5035460992907801,
"acc_norm_stderr": 0.02982674915328092
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.49478487614080835,
"acc_stderr": 0.012769541449652547,
"acc_norm": 0.49478487614080835,
"acc_norm_stderr": 0.012769541449652547
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.75,
"acc_stderr": 0.026303648393696036,
"acc_norm": 0.75,
"acc_norm_stderr": 0.026303648393696036
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6813725490196079,
"acc_stderr": 0.018850084696468712,
"acc_norm": 0.6813725490196079,
"acc_norm_stderr": 0.018850084696468712
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6818181818181818,
"acc_stderr": 0.04461272175910509,
"acc_norm": 0.6818181818181818,
"acc_norm_stderr": 0.04461272175910509
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.746938775510204,
"acc_stderr": 0.027833023871399677,
"acc_norm": 0.746938775510204,
"acc_norm_stderr": 0.027833023871399677
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8258706467661692,
"acc_stderr": 0.026814951200421603,
"acc_norm": 0.8258706467661692,
"acc_norm_stderr": 0.026814951200421603
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.91,
"acc_stderr": 0.028762349126466125,
"acc_norm": 0.91,
"acc_norm_stderr": 0.028762349126466125
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5783132530120482,
"acc_stderr": 0.038444531817709175,
"acc_norm": 0.5783132530120482,
"acc_norm_stderr": 0.038444531817709175
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.7777777777777778,
"acc_stderr": 0.03188578017686398,
"acc_norm": 0.7777777777777778,
"acc_norm_stderr": 0.03188578017686398
},
"harness|truthfulqa:mc|0": {
"mc1": 0.5691554467564259,
"mc1_stderr": 0.01733527247533237,
"mc2": 0.7184177934834866,
"mc2_stderr": 0.014995634120330182
},
"harness|winogrande|5": {
"acc": 0.8342541436464088,
"acc_stderr": 0.010450899545370632
},
"harness|gsm8k|5": {
"acc": 0.6535253980288097,
"acc_stderr": 0.013107179054313398
}
}
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_gagan3012__MetaModel)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 74.4 |
| ARC (25-shot) | 71.08 |
| HellaSwag (10-shot) | 88.45 |
| MMLU (5-shot) | 66.26 |
| TruthfulQA (0-shot) | 71.84 |
| Winogrande (5-shot) | 83.43 |
| GSM8K (5-shot) | 65.35 |
|
Spanicin/Fulcrum_Aura | Spanicin | 2024-01-09T11:51:32Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"OpenPipe/mistral-ft-optimized-1218",
"HuggingFaceH4/zephyr-7b-beta",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T11:47:42Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- OpenPipe/mistral-ft-optimized-1218
- HuggingFaceH4/zephyr-7b-beta
---
# Fulcrum_Aura
Fulcrum_Aura is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: HuggingFaceH4/zephyr-7b-beta
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Spanicin/Fulcrum_Aura"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
researchworkai/Sentiment-roBERTa-Twitter | researchworkai | 2024-01-09T11:49:19Z | 147 | 1 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"roberta",
"text-classification",
"en",
"dataset:tweet_eval",
"arxiv:2010.12421",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-08T18:56:54Z | ---
datasets:
- tweet_eval
language:
- en
---
# Twitter-roBERTa for Sentiment Analysis
This is a roBERTa model trained on ~58M tweets and finetuned for sentiment analysis with the TweetEval benchmark. This model is suitable for English.
- Reference Paper: [_TweetEval_ (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
- Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
<b>Labels</b>:
0 -> Negative;
1 -> Neutral;
2 -> Positive
## Example of classification
```python
from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer
import numpy as np
from scipy.special import softmax
import csv
import urllib.request
# Preprocess text (username and link placeholders)
def preprocess(text):
new_text = []
for t in text.split(" "):
t = '@user' if t.startswith('@') and len(t) > 1 else t
t = 'http' if t.startswith('http') else t
new_text.append(t)
return " ".join(new_text)
# Tasks:
# emoji, emotion, hate, irony, offensive, sentiment
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
task='sentiment'
MODEL = f"researchworkai/Sentiment-roBERTa-Twitter-{task}"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
# download label mapping
labels=[]
mapping_link = f"https://raw.githubusercontent.com/researchworkai/tweeteval/main/datasets/{task}/mapping.txt"
with urllib.request.urlopen(mapping_link) as f:
html = f.read().decode('utf-8').split("\n")
csvreader = csv.reader(html, delimiter='\t')
labels = [row[1] for row in csvreader if len(row) > 1]
# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
model.save_pretrained(MODEL)
text = "Good night 😊"
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)
# # TF
# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
# model.save_pretrained(MODEL)
# text = "Good night 😊"
# encoded_input = tokenizer(text, return_tensors='tf')
# output = model(encoded_input)
# scores = output[0][0].numpy()
# scores = softmax(scores)
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
l = labels[ranking[i]]
s = scores[ranking[i]]
print(f"{i+1}) {l} {np.round(float(s), 4)}")
```
Output:
```
1) positive 0.8466
2) neutral 0.1458
3) negative 0.0076
```
### BibTeX entry and citation info
Please cite the [reference paper](https://aclanthology.org/2020.findings-emnlp.148/) if you use this model.
```bibtex
@inproceedings{barbieri-etal-2020-tweeteval,
title = "{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification",
author = "Barbieri, Francesco and
Camacho-Collados, Jose and
Espinosa Anke, Luis and
Neves, Leonardo",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.148",
doi = "10.18653/v1/2020.findings-emnlp.148",
pages = "1644--1650"
}
``` |
jysssacc/roberta-base_IA3_lr5e-05_bs4_epoch5_wd0.01 | jysssacc | 2024-01-09T11:48:29Z | 1 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:adapter:FacebookAI/roberta-base",
"license:mit",
"region:us"
] | null | 2024-01-09T11:42:47Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: roberta-base
model-index:
- name: roberta-base_IA3_lr5e-05_bs4_epoch5_wd0.01
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base_IA3_lr5e-05_bs4_epoch5_wd0.01
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 15.1197
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 19.9021 | 1.0 | 157 | 21.8572 |
| 19.0595 | 2.0 | 314 | 20.8634 |
| 18.1837 | 3.0 | 471 | 18.9005 |
| 15.0565 | 4.0 | 628 | 16.2004 |
| 13.4717 | 5.0 | 785 | 15.1197 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0 |
divinitas-jyi/ppo-LunarLander-v2 | divinitas-jyi | 2024-01-09T11:46:30Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T09:21:09Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: ppo-MlpPolicy
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 285.31 +/- 19.02
name: mean_reward
verified: false
---
# **ppo-MlpPolicy** Agent playing **LunarLander-v2**
This is a trained model of a **ppo-MlpPolicy** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Joy28/videomae-base-finetuned-subset-200epochs | Joy28 | 2024-01-09T11:41:50Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-base",
"base_model:finetune:MCG-NJU/videomae-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | video-classification | 2024-01-08T01:53:32Z | ---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-subset-200epochs
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# videomae-base-finetuned-subset-200epochs
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7635
- Accuracy: 0.7407
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 11100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 0.6058 | 0.01 | 56 | 0.7442 | 0.7880 |
| 0.4908 | 1.01 | 112 | 0.7775 | 0.7558 |
| 0.5326 | 2.01 | 168 | 0.7973 | 0.7419 |
| 0.4768 | 3.01 | 224 | 0.8451 | 0.7281 |
| 0.4243 | 4.01 | 280 | 0.9361 | 0.6728 |
| 0.6921 | 5.01 | 336 | 0.8979 | 0.7097 |
| 0.3182 | 6.01 | 392 | 0.8852 | 0.7235 |
| 0.6085 | 7.01 | 448 | 0.9224 | 0.7097 |
| 0.4067 | 8.01 | 504 | 0.9631 | 0.6682 |
| 0.47 | 9.01 | 560 | 0.9193 | 0.7465 |
| 0.5058 | 10.01 | 616 | 0.8967 | 0.7650 |
| 0.4187 | 11.01 | 672 | 0.7403 | 0.7834 |
| 0.6033 | 12.01 | 728 | 1.0005 | 0.6221 |
| 0.5032 | 13.01 | 784 | 1.1420 | 0.5899 |
| 0.5967 | 14.01 | 840 | 1.2590 | 0.5484 |
| 0.3103 | 15.01 | 896 | 0.9723 | 0.6544 |
| 0.4201 | 16.01 | 952 | 1.1665 | 0.6406 |
| 0.6246 | 17.01 | 1008 | 1.2497 | 0.4977 |
| 0.6306 | 18.01 | 1064 | 1.3829 | 0.5668 |
| 0.4179 | 19.01 | 1120 | 1.0787 | 0.5806 |
| 0.5468 | 20.01 | 1176 | 1.1144 | 0.5714 |
| 0.4166 | 21.01 | 1232 | 0.7674 | 0.6912 |
| 0.3844 | 22.01 | 1288 | 0.9260 | 0.6959 |
| 0.5138 | 23.01 | 1344 | 0.9093 | 0.7097 |
| 0.792 | 24.01 | 1400 | 0.7327 | 0.7465 |
| 0.5944 | 25.01 | 1456 | 0.8933 | 0.7650 |
| 0.4855 | 26.01 | 1512 | 0.9830 | 0.6636 |
| 0.6896 | 27.01 | 1568 | 0.7896 | 0.6590 |
| 0.3617 | 28.01 | 1624 | 0.8900 | 0.6544 |
| 0.6362 | 29.01 | 1680 | 1.0237 | 0.6912 |
| 0.6475 | 30.01 | 1736 | 1.1399 | 0.6037 |
| 0.5088 | 31.01 | 1792 | 0.7190 | 0.7742 |
| 0.7271 | 32.01 | 1848 | 0.9492 | 0.6359 |
| 0.3171 | 33.01 | 1904 | 0.9431 | 0.7281 |
| 0.5847 | 34.01 | 1960 | 0.7997 | 0.7235 |
| 0.4703 | 35.01 | 2016 | 0.9506 | 0.7051 |
| 0.4995 | 36.01 | 2072 | 1.0830 | 0.7005 |
| 0.5682 | 37.01 | 2128 | 1.0100 | 0.7005 |
| 0.6424 | 38.01 | 2184 | 0.9587 | 0.6452 |
| 0.5897 | 39.01 | 2240 | 0.8807 | 0.7097 |
| 0.5222 | 40.01 | 2296 | 1.1219 | 0.6682 |
| 0.5239 | 41.01 | 2352 | 1.0848 | 0.6406 |
| 0.5957 | 42.01 | 2408 | 0.9640 | 0.6866 |
| 0.5279 | 43.01 | 2464 | 1.0291 | 0.5853 |
| 0.3545 | 44.01 | 2520 | 0.8908 | 0.6636 |
| 0.6066 | 45.01 | 2576 | 1.2505 | 0.6406 |
| 0.3658 | 46.01 | 2632 | 0.8362 | 0.6866 |
| 0.5454 | 47.01 | 2688 | 1.3975 | 0.5622 |
| 0.5956 | 48.01 | 2744 | 0.8236 | 0.6590 |
| 0.4107 | 49.01 | 2800 | 1.2610 | 0.6267 |
| 0.462 | 50.01 | 2856 | 1.2553 | 0.6406 |
| 0.4837 | 51.01 | 2912 | 1.0389 | 0.6359 |
| 0.621 | 52.01 | 2968 | 0.8281 | 0.7235 |
| 0.4293 | 53.01 | 3024 | 1.0426 | 0.6267 |
| 0.4255 | 54.01 | 3080 | 1.2942 | 0.5806 |
| 0.5607 | 55.01 | 3136 | 1.1234 | 0.6498 |
| 0.3104 | 56.01 | 3192 | 1.0643 | 0.6590 |
| 0.3335 | 57.01 | 3248 | 1.2160 | 0.6590 |
| 0.4232 | 58.01 | 3304 | 1.3532 | 0.5806 |
| 0.6238 | 59.01 | 3360 | 0.9208 | 0.7005 |
| 0.369 | 60.01 | 3416 | 1.2186 | 0.5530 |
| 0.3874 | 61.01 | 3472 | 1.1746 | 0.6452 |
| 0.3421 | 62.01 | 3528 | 1.2017 | 0.5945 |
| 0.4243 | 63.01 | 3584 | 1.0288 | 0.6728 |
| 0.2806 | 64.01 | 3640 | 0.8483 | 0.7419 |
| 0.5357 | 65.01 | 3696 | 1.0890 | 0.6359 |
| 0.5155 | 66.01 | 3752 | 1.1885 | 0.6359 |
| 0.4367 | 67.01 | 3808 | 1.0738 | 0.6820 |
| 0.48 | 68.01 | 3864 | 1.0894 | 0.6866 |
| 0.4703 | 69.01 | 3920 | 1.2252 | 0.6498 |
| 0.4531 | 70.01 | 3976 | 1.0584 | 0.6498 |
| 0.2898 | 71.01 | 4032 | 1.7486 | 0.5576 |
| 0.3684 | 72.01 | 4088 | 1.0524 | 0.6406 |
| 0.2752 | 73.01 | 4144 | 1.2744 | 0.6728 |
| 0.3092 | 74.01 | 4200 | 1.3918 | 0.5806 |
| 0.3507 | 75.01 | 4256 | 1.4599 | 0.6544 |
| 0.4722 | 76.01 | 4312 | 1.0549 | 0.7143 |
| 0.4059 | 77.01 | 4368 | 1.2727 | 0.6728 |
| 0.2734 | 78.01 | 4424 | 1.1258 | 0.6959 |
| 0.4168 | 79.01 | 4480 | 0.9788 | 0.7189 |
| 0.4456 | 80.01 | 4536 | 1.4757 | 0.6544 |
| 0.4519 | 81.01 | 4592 | 1.2796 | 0.6820 |
| 0.5283 | 82.01 | 4648 | 1.2542 | 0.7051 |
| 0.4738 | 83.01 | 4704 | 1.2781 | 0.6083 |
| 0.2128 | 84.01 | 4760 | 1.0077 | 0.6866 |
| 0.3262 | 85.01 | 4816 | 1.0287 | 0.6820 |
| 0.3631 | 86.01 | 4872 | 1.3574 | 0.6544 |
| 0.4085 | 87.01 | 4928 | 1.1976 | 0.7235 |
| 0.3582 | 88.01 | 4984 | 1.4126 | 0.6544 |
| 0.3564 | 89.01 | 5040 | 1.3488 | 0.6406 |
| 0.4207 | 90.01 | 5096 | 1.0565 | 0.7005 |
| 0.4307 | 91.01 | 5152 | 0.9833 | 0.7281 |
| 0.3863 | 92.01 | 5208 | 0.9340 | 0.6912 |
| 0.2949 | 93.01 | 5264 | 0.9835 | 0.7143 |
| 0.2957 | 94.01 | 5320 | 1.1397 | 0.7235 |
| 0.3767 | 95.01 | 5376 | 1.4135 | 0.6221 |
| 0.4949 | 96.01 | 5432 | 1.0483 | 0.7189 |
| 0.3058 | 97.01 | 5488 | 1.8241 | 0.5530 |
| 0.3406 | 98.01 | 5544 | 1.7386 | 0.5760 |
| 0.2319 | 99.01 | 5600 | 1.4739 | 0.6175 |
| 0.5261 | 100.01 | 5656 | 1.0822 | 0.7143 |
| 0.4181 | 101.01 | 5712 | 1.2876 | 0.6728 |
| 0.243 | 102.01 | 5768 | 1.0783 | 0.7235 |
| 0.2603 | 103.01 | 5824 | 1.4557 | 0.6129 |
| 0.4892 | 104.01 | 5880 | 1.2557 | 0.6912 |
| 0.3073 | 105.01 | 5936 | 1.3899 | 0.5991 |
| 0.3601 | 106.01 | 5992 | 1.2048 | 0.6820 |
| 0.4371 | 107.01 | 6048 | 1.3645 | 0.6866 |
| 0.5712 | 108.01 | 6104 | 1.2281 | 0.6636 |
| 0.3697 | 109.01 | 6160 | 1.4402 | 0.6544 |
| 0.2978 | 110.01 | 6216 | 1.3769 | 0.6912 |
| 0.303 | 111.01 | 6272 | 1.3096 | 0.6959 |
| 0.4606 | 112.01 | 6328 | 1.2236 | 0.7005 |
| 0.2554 | 113.01 | 6384 | 1.2662 | 0.6959 |
| 0.3033 | 114.01 | 6440 | 1.2476 | 0.6406 |
| 0.3025 | 115.01 | 6496 | 1.0474 | 0.7143 |
| 0.3513 | 116.01 | 6552 | 1.4692 | 0.6452 |
| 0.4205 | 117.01 | 6608 | 1.2675 | 0.6912 |
| 0.3898 | 118.01 | 6664 | 1.4018 | 0.6590 |
| 0.2184 | 119.01 | 6720 | 1.2402 | 0.6959 |
| 0.319 | 120.01 | 6776 | 1.0747 | 0.7097 |
| 0.2455 | 121.01 | 6832 | 1.3515 | 0.7051 |
| 0.2138 | 122.01 | 6888 | 1.5175 | 0.6682 |
| 0.3805 | 123.01 | 6944 | 1.4817 | 0.6820 |
| 0.3942 | 124.01 | 7000 | 1.5235 | 0.6221 |
| 0.2207 | 125.01 | 7056 | 1.6295 | 0.5945 |
| 0.2217 | 126.01 | 7112 | 1.3348 | 0.6912 |
| 0.3173 | 127.01 | 7168 | 1.3566 | 0.7097 |
| 0.4952 | 128.01 | 7224 | 1.2188 | 0.7327 |
| 0.3238 | 129.01 | 7280 | 1.2574 | 0.7143 |
| 0.1525 | 130.01 | 7336 | 1.5508 | 0.6313 |
| 0.2518 | 131.01 | 7392 | 1.3058 | 0.6912 |
| 0.4523 | 132.01 | 7448 | 1.7539 | 0.6313 |
| 0.3732 | 133.01 | 7504 | 1.4478 | 0.6820 |
| 0.2432 | 134.01 | 7560 | 1.3595 | 0.6912 |
| 0.2798 | 135.01 | 7616 | 1.5007 | 0.6866 |
| 0.3436 | 136.01 | 7672 | 1.3162 | 0.7465 |
| 0.3033 | 137.01 | 7728 | 1.3700 | 0.7051 |
| 0.3457 | 138.01 | 7784 | 1.1052 | 0.7465 |
| 0.1381 | 139.01 | 7840 | 1.5786 | 0.6959 |
| 0.3067 | 140.01 | 7896 | 1.5155 | 0.6912 |
| 0.269 | 141.01 | 7952 | 1.2751 | 0.7512 |
| 0.2646 | 142.01 | 8008 | 1.6017 | 0.6774 |
| 0.3933 | 143.01 | 8064 | 1.4294 | 0.7005 |
| 0.6315 | 144.01 | 8120 | 1.3814 | 0.6866 |
| 0.2814 | 145.01 | 8176 | 1.1689 | 0.7512 |
| 0.2749 | 146.01 | 8232 | 1.3208 | 0.7005 |
| 0.3966 | 147.01 | 8288 | 1.2817 | 0.7189 |
| 0.1787 | 148.01 | 8344 | 1.4568 | 0.7189 |
| 0.3006 | 149.01 | 8400 | 1.3312 | 0.7143 |
| 0.2871 | 150.01 | 8456 | 1.5808 | 0.6452 |
| 0.2018 | 151.01 | 8512 | 1.6682 | 0.6267 |
| 0.2698 | 152.01 | 8568 | 1.4281 | 0.6590 |
| 0.162 | 153.01 | 8624 | 1.4369 | 0.7051 |
| 0.3961 | 154.01 | 8680 | 1.3771 | 0.7143 |
| 0.4034 | 155.01 | 8736 | 1.5444 | 0.6452 |
| 0.2462 | 156.01 | 8792 | 1.4677 | 0.6728 |
| 0.2564 | 157.01 | 8848 | 1.6085 | 0.6590 |
| 0.2905 | 158.01 | 8904 | 1.3037 | 0.6912 |
| 0.2762 | 159.01 | 8960 | 1.3974 | 0.7051 |
| 0.1604 | 160.01 | 9016 | 1.5176 | 0.6959 |
| 0.2399 | 161.01 | 9072 | 1.4504 | 0.7143 |
| 0.3398 | 162.01 | 9128 | 1.4675 | 0.6728 |
| 0.2495 | 163.01 | 9184 | 1.3757 | 0.7005 |
| 0.3076 | 164.01 | 9240 | 1.3699 | 0.7051 |
| 0.2491 | 165.01 | 9296 | 1.4333 | 0.7005 |
| 0.1666 | 166.01 | 9352 | 1.6465 | 0.6313 |
| 0.1871 | 167.01 | 9408 | 1.6614 | 0.6544 |
| 0.2169 | 168.01 | 9464 | 1.8141 | 0.6175 |
| 0.3918 | 169.01 | 9520 | 1.3402 | 0.7097 |
| 0.2697 | 170.01 | 9576 | 1.4295 | 0.6774 |
| 0.2261 | 171.01 | 9632 | 1.5952 | 0.6452 |
| 0.1894 | 172.01 | 9688 | 1.5468 | 0.6590 |
| 0.1714 | 173.01 | 9744 | 1.4434 | 0.6636 |
| 0.3137 | 174.01 | 9800 | 1.5525 | 0.6313 |
| 0.267 | 175.01 | 9856 | 1.6447 | 0.6452 |
| 0.0797 | 176.01 | 9912 | 1.5593 | 0.6682 |
| 0.2698 | 177.01 | 9968 | 1.3952 | 0.7005 |
| 0.1364 | 178.01 | 10024 | 1.6720 | 0.6498 |
| 0.2342 | 179.01 | 10080 | 1.6315 | 0.6682 |
| 0.1909 | 180.01 | 10136 | 1.5374 | 0.7051 |
| 0.2234 | 181.01 | 10192 | 1.5861 | 0.7097 |
| 0.3425 | 182.01 | 10248 | 1.5664 | 0.6912 |
| 0.4092 | 183.01 | 10304 | 1.6135 | 0.6774 |
| 0.2427 | 184.01 | 10360 | 1.5366 | 0.6866 |
| 0.3751 | 185.01 | 10416 | 1.5561 | 0.6959 |
| 0.1831 | 186.01 | 10472 | 1.6049 | 0.7005 |
| 0.2207 | 187.01 | 10528 | 1.6072 | 0.6959 |
| 0.1096 | 188.01 | 10584 | 1.5016 | 0.7097 |
| 0.2417 | 189.01 | 10640 | 1.5027 | 0.7097 |
| 0.2974 | 190.01 | 10696 | 1.4897 | 0.7097 |
| 0.2296 | 191.01 | 10752 | 1.4927 | 0.7235 |
| 0.3323 | 192.01 | 10808 | 1.4947 | 0.7235 |
| 0.3002 | 193.01 | 10864 | 1.5225 | 0.7143 |
| 0.23 | 194.01 | 10920 | 1.4965 | 0.7189 |
| 0.3147 | 195.01 | 10976 | 1.5123 | 0.7051 |
| 0.1344 | 196.01 | 11032 | 1.5192 | 0.7051 |
| 0.1843 | 197.01 | 11088 | 1.5235 | 0.7097 |
| 0.1902 | 198.0 | 11100 | 1.5238 | 0.7097 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1
- Datasets 2.16.1
- Tokenizers 0.15.0
|
qmeeus/whisper-small-multilingual-spoken-ner-end2end-lora | qmeeus | 2024-01-09T11:41:33Z | 3 | 0 | peft | [
"peft",
"safetensors",
"whisper",
"generated_from_trainer",
"dataset:facebook/voxpopuli",
"base_model:openai/whisper-small",
"base_model:adapter:openai/whisper-small",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2024-01-09T11:35:29Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-small
datasets:
- facebook/voxpopuli
metrics:
- wer
model-index:
- name: WhisperForSpokenNER-end2end
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: facebook/voxpopuli de+es+fr+nl
type: facebook/voxpopuli
split: de+es+fr+nl
metrics:
- type: wer
value: 0.38886263390044107
name: Wer
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# WhisperForSpokenNER-end2end
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the facebook/voxpopuli de+es+fr+nl dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3381
- Wer: 0.3889
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 2.3436 | 0.36 | 200 | 1.8791 | 0.8871 |
| 1.1682 | 0.71 | 400 | 1.0307 | 0.5048 |
| 0.7321 | 1.07 | 600 | 0.6300 | 0.3665 |
| 0.4564 | 1.43 | 800 | 0.4381 | 0.3515 |
| 0.4095 | 1.79 | 1000 | 0.4027 | 0.3330 |
| 0.3813 | 2.14 | 1200 | 0.3847 | 0.3360 |
| 0.3667 | 2.5 | 1400 | 0.3734 | 0.3392 |
| 0.3583 | 2.86 | 1600 | 0.3649 | 0.3490 |
| 0.3454 | 3.22 | 1800 | 0.3588 | 0.3572 |
| 0.3422 | 3.57 | 2000 | 0.3537 | 0.3705 |
| 0.3371 | 3.93 | 2200 | 0.3503 | 0.3811 |
| 0.3291 | 4.29 | 2400 | 0.3475 | 0.3678 |
| 0.324 | 4.65 | 2600 | 0.3451 | 0.3670 |
| 0.3262 | 5.0 | 2800 | 0.3431 | 0.3710 |
| 0.3168 | 5.36 | 3000 | 0.3419 | 0.3847 |
| 0.3178 | 5.72 | 3200 | 0.3406 | 0.3833 |
| 0.3136 | 6.08 | 3400 | 0.3400 | 0.3853 |
| 0.3092 | 6.43 | 3600 | 0.3393 | 0.3896 |
| 0.3106 | 6.79 | 3800 | 0.3389 | 0.3900 |
| 0.3057 | 7.15 | 4000 | 0.3388 | 0.3803 |
| 0.3087 | 7.51 | 4200 | 0.3383 | 0.3941 |
| 0.308 | 7.86 | 4400 | 0.3382 | 0.3874 |
| 0.3036 | 8.22 | 4600 | 0.3381 | 0.3896 |
| 0.3087 | 8.58 | 4800 | 0.3380 | 0.3910 |
| 0.3079 | 8.94 | 5000 | 0.3381 | 0.3889 |
### Framework versions
- PEFT 0.7.1.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
|
VegetaSama/bert_key | VegetaSama | 2024-01-09T11:39:55Z | 4 | 0 | bertopic | [
"bertopic",
"text-classification",
"region:us"
] | text-classification | 2024-01-09T11:38:15Z |
---
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
---
# bert_key
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
## Usage
To use this model, please install BERTopic:
```
pip install -U bertopic
```
You can use the model as follows:
```python
from bertopic import BERTopic
topic_model = BERTopic.load("VegetaSama/bert_key")
topic_model.get_topic_info()
```
## Topic overview
* Number of topics: 17
* Number of training documents: 10000
<details>
<summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|----------|----------------|-----------------|-------|
| -1 | restaurant - meal - sandwich - food - lunch | 86 | -1_restaurant_meal_sandwich_food |
| 0 | restaurant - drinks - dinner - bar - steak | 2059 | 0_restaurant_drinks_dinner_bar |
| 1 | mexican food - tacos - taco - chips salsa - salsa | 2789 | 1_mexican food_tacos_taco_chips salsa |
| 2 | shop - shopping - nordstrom - store - customer service | 731 | 2_shop_shopping_nordstrom_store |
| 3 | thai food - chinese food - pad thai - thai - fried rice | 701 | 3_thai food_chinese food_pad thai_thai |
| 4 | best pizza - pizza good - good pizza - pizza - pizzeria | 594 | 4_best pizza_pizza good_good pizza_pizza |
| 5 | scottsdale - phoenix - restaurant - bbq - arizona | 586 | 5_scottsdale_phoenix_restaurant_bbq |
| 6 | burger - good burger - burgers - burger fries - restaurant | 443 | 6_burger_good burger_burgers_burger fries |
| 7 | restaurant - hostess - dinner - waiter - waitress | 354 | 7_restaurant_hostess_dinner_waiter |
| 8 | best sushi - sushi - sushi place - sushi bar - spicy tuna | 321 | 8_best sushi_sushi_sushi place_sushi bar |
| 9 | manicure - massage - pedicure - salon - nail | 294 | 9_manicure_massage_pedicure_salon |
| 10 | hotels - hotel - resort - marriott - amenities | 288 | 10_hotels_hotel_resort_marriott |
| 11 | coffee shop - coffee - starbucks - coffee shops - good coffee | 215 | 11_coffee shop_coffee_starbucks_coffee shops |
| 12 | breakfast - pancakes - protein pancakes - bakery - lunch | 211 | 12_breakfast_pancakes_protein pancakes_bakery |
| 13 | hike - hiking - trails - trail - south mountain | 135 | 13_hike_hiking_trails_trail |
| 14 | downtown phoenix - central phoenix - restaurants - phoenix area - phoenix | 105 | 14_downtown phoenix_central phoenix_restaurants_phoenix area |
| 15 | vets - vet - veterinary - pets - petsmart | 88 | 15_vets_vet_veterinary_pets |
</details>
## Training hyperparameters
* calculate_probabilities: True
* language: None
* low_memory: False
* min_topic_size: 10
* n_gram_range: (1, 1)
* nr_topics: None
* seed_topic_list: None
* top_n_words: 5
* verbose: True
* zeroshot_min_similarity: 0.7
* zeroshot_topic_list: None
## Framework versions
* Numpy: 1.24.3
* HDBSCAN: 0.8.33
* UMAP: 0.5.5
* Pandas: 2.0.3
* Scikit-Learn: 1.3.0
* Sentence-transformers: 2.2.2
* Transformers: 4.32.1
* Numba: 0.58.1
* Plotly: 5.9.0
* Python: 3.11.5
|
hynky/codellama-7b-sft-lora-func-names-java-4bit | hynky | 2024-01-09T11:35:40Z | 4 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:codellama/CodeLlama-7b-hf",
"base_model:adapter:codellama/CodeLlama-7b-hf",
"region:us"
] | null | 2023-12-29T13:39:19Z | ---
library_name: peft
base_model: codellama/CodeLlama-7b-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
```
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
config = PeftConfig.from_pretrained("hynky/codellama-7b-sft-lora-func-names-java-4bit")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf",
torch_dtype='auto',
device_map='auto',
offload_folder="offload",
offload_state_dict = True)
model = PeftModel.from_pretrained(model, "hynky/codellama-7b-sft-lora-func-names-java-4bit")
def generate_code(sample, max_new_tokens=200):
batch = tokenizer(sample, return_tensors='pt').to(device)
with torch.cuda.amp.autocast():
output_tokens = model.generate(**batch, max_new_tokens=max_new_tokens)
return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
print(generate_code("public class AddTwoIntegers("))
```
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
### Framework versions
- PEFT 0.6.0
|
Aedelon/ppo-Huggy | Aedelon | 2024-01-09T11:28:33Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2024-01-09T11:28:29Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: Aedelon/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Spanicin/Fulcrum_Nova | Spanicin | 2024-01-09T11:19:20Z | 12 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"OpenPipe/mistral-ft-optimized-1218",
"mlabonne/NeuralHermes-2.5-Mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T11:15:00Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B
---
# Fulcrum_Nova
Fulcrum_Nova is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Spanicin/Fulcrum_Nova"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
slay/mistral_7b_guanaco | slay | 2024-01-09T11:18:36Z | 1 | 0 | peft | [
"peft",
"safetensors",
"mistral",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2024-01-07T19:47:19Z | ---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1 |
wave1art/q-taxi-v3 | wave1art | 2024-01-09T11:15:45Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T11:15:42Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="wave1art/q-taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Rinchindugar/my_awesome_opus_books_model | Rinchindugar | 2024-01-09T11:13:49Z | 5 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-01-08T04:54:45Z | ---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: my_awesome_opus_books_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_opus_books_model
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6068
- Bleu: 5.6146
- Gen Len: 17.628
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 1.8511 | 1.0 | 6355 | 1.6309 | 5.4324 | 17.638 |
| 1.8186 | 2.0 | 12710 | 1.6068 | 5.6146 | 17.628 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
s3nh/Eileithyia-toxicqa | s3nh | 2024-01-09T11:13:46Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:Undi95/toxicqa-Llama2-13B",
"base_model:merge:Undi95/toxicqa-Llama2-13B",
"base_model:athirdpath/Eileithyia-13B",
"base_model:merge:athirdpath/Eileithyia-13B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T11:09:31Z | ---
base_model:
- Undi95/toxicqa-Llama2-13B
- athirdpath/Eileithyia-13B
tags:
- mergekit
- merge
---
# Eileithyia-toxicqa
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [Undi95/toxicqa-Llama2-13B](https://huggingface.co/Undi95/toxicqa-Llama2-13B)
* [athirdpath/Eileithyia-13B](https://huggingface.co/athirdpath/Eileithyia-13B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: Undi95/toxicqa-Llama2-13B
dtype: float16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.3, 0.6, 0.4, 0.8, 1.0]
- filter: mlp
value: [0.7, 0.4, 0.6, 0.2, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 32]
model: athirdpath/Eileithyia-13B
- layer_range: [0, 32]
model: Undi95/toxicqa-Llama2-13B
```
|
ntc-ai/SDXL-LoRA-slider.Crystal-Ball-Photography | ntc-ai | 2024-01-09T11:13:32Z | 40 | 0 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion-xl",
"lora",
"template:sd-lora",
"template:sdxl-lora",
"sdxl-sliders",
"ntcai.xyz-sliders",
"concept",
"en",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:mit",
"region:us"
] | text-to-image | 2024-01-09T11:13:29Z |
---
language:
- en
thumbnail: "images/evaluate/Crystal Ball Photography.../Crystal Ball Photography_17_3.0.png"
widget:
- text: Crystal Ball Photography
output:
url: images/Crystal Ball Photography_17_3.0.png
- text: Crystal Ball Photography
output:
url: images/Crystal Ball Photography_19_3.0.png
- text: Crystal Ball Photography
output:
url: images/Crystal Ball Photography_20_3.0.png
- text: Crystal Ball Photography
output:
url: images/Crystal Ball Photography_21_3.0.png
- text: Crystal Ball Photography
output:
url: images/Crystal Ball Photography_22_3.0.png
tags:
- text-to-image
- stable-diffusion-xl
- lora
- template:sd-lora
- template:sdxl-lora
- sdxl-sliders
- ntcai.xyz-sliders
- concept
- diffusers
license: "mit"
inference: false
instance_prompt: "Crystal Ball Photography"
base_model: "stabilityai/stable-diffusion-xl-base-1.0"
---
# ntcai.xyz slider - Crystal Ball Photography (SDXL LoRA)
| Strength: -3 | Strength: 0 | Strength: 3 |
| --- | --- | --- |
| <img src="images/Crystal Ball Photography_17_-3.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_17_0.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_17_3.0.png" width=256 height=256 /> |
| <img src="images/Crystal Ball Photography_19_-3.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_19_0.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_19_3.0.png" width=256 height=256 /> |
| <img src="images/Crystal Ball Photography_20_-3.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_20_0.0.png" width=256 height=256 /> | <img src="images/Crystal Ball Photography_20_3.0.png" width=256 height=256 /> |
## Download
Weights for this model are available in Safetensors format.
## Trigger words
You can apply this LoRA with trigger words for additional effect:
```
Crystal Ball Photography
```
## Use in diffusers
```python
from diffusers import StableDiffusionXLPipeline
from diffusers import EulerAncestralDiscreteScheduler
import torch
pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors")
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
# Load the LoRA
pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.Crystal-Ball-Photography', weight_name='Crystal Ball Photography.safetensors', adapter_name="Crystal Ball Photography")
# Activate the LoRA
pipe.set_adapters(["Crystal Ball Photography"], adapter_weights=[2.0])
prompt = "medieval rich kingpin sitting in a tavern, Crystal Ball Photography"
negative_prompt = "nsfw"
width = 512
height = 512
num_inference_steps = 10
guidance_scale = 2
image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0]
image.save('result.png')
```
## Support the Patreon
If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI).
By joining our Patreon, you'll gain access to an ever-growing library of over 960+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities.
Your support on Patreon will allow us to continue developing and refining new models.
## Other resources
- [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs
- [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
|
FeleliHasima/Urakata_Style | FeleliHasima | 2024-01-09T11:07:01Z | 2 | 3 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:Lykon/AnyLoRA",
"base_model:adapter:Lykon/AnyLoRA",
"license:unknown",
"region:us"
] | text-to-image | 2024-01-09T11:06:56Z | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: <lora:urakata20140107:1>,hatsune miku,stage,
parameters:
negative_prompt: >-
verybadimagenegative_v1.3, negative_hand-neg, (worst quality:2), (low
quality:2), (normal quality:2), lowres, normal quality, ((monochrome)),
((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331),
(duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331),
mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad
proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331),
(extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051),
(unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad
hands, missing fingers, (((extra arms and legs))),
output:
url: images/001.png
- text: '<lora:urakata20140107:1>,cityhousemaid,maid headdress,maid apron, '
parameters:
negative_prompt: >-
verybadimagenegative_v1.3, negative_hand-neg, (worst quality:2), (low
quality:2), (normal quality:2), lowres, normal quality, ((monochrome)),
((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331),
(duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331),
mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.21), (bad
proportions:1.331), extra limbs, (disfigured:1.331), (missing arms:1.331),
(extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051),
(unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad
hands, missing fingers, (((extra arms and legs))),
output:
url: images/002.png
- text: 1girl,<lora:urakata001010:1>,miko,
parameters:
negative_prompt: FastNegativeV2,
output:
url: images/003.png
- text: 1girl,<lora:urakata001010:1>,maid,
parameters:
negative_prompt: FastNegativeV2,
output:
url: images/004.png
base_model: Lykon/AnyLoRA
instance_prompt: urakata
license: unknown
---
# 裏方/Urakata Style
<Gallery />
## Model description
イラストレーター 裏方の画風lycorisです。
学習に使用した画像は全て自作したものであり、イラストレーター本人の著作物は一切使用していません。
このモデルはどういう使い方をしてもらっても構いません。
This model represents the art style lycoris of the illustrator "Urakata".
All images used for training are self-made, and no works of the illustrator themselves have been used.
You may use this model in any way you see fit.
## Trigger words
You should use `urakata` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/FeleliHasima/Urakata_Style/tree/main) them in the Files & versions tab.
|
shaikhussain2344/distilbert-base-uncased-finetuned-imdb-1 | shaikhussain2344 | 2024-01-09T11:05:04Z | 55 | 0 | transformers | [
"transformers",
"tf",
"distilbert",
"fill-mask",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2024-01-09T11:00:57Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: shaikhussain2344/distilbert-base-uncased-finetuned-imdb-1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# shaikhussain2344/distilbert-base-uncased-finetuned-imdb-1
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.8442
- Validation Loss: 2.5619
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -688, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 2.8442 | 2.5619 | 0 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
ashutoshsharma58/indian_food_image_detection | ashutoshsharma58 | 2024-01-09T10:46:00Z | 175 | 0 | transformers | [
"transformers",
"pytorch",
"vit",
"image-classification",
"code",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-01-06T12:07:26Z | ---
license: apache-2.0
language:
- en
tags:
- code
---
### Model Description
This model classifies the uploaded imgage into various Indian cuisines. The categories are:
adhirasam, aloo_gobi, aloo_matar, aloo_methi, aloo_shimla_mirch, aloo_tikki, anarsa, ariselu, bandar_laddu, basundi, bhatura, bhindi_masala,
biryani, boondi, butter_chicken, chak_hao_kheer, cham_cham, chana_masala, chapati, chhena_kheeri, chicken_razala, chicken_tikka,chicken_tikka_masala,
chikki, daal_baati_churma, daal_puri, dal_makhani, dal_tadka, dharwad_pedha, doodhpak, double_ka_meetha, dum_aloo, gajar_ka_halwa, gavvalu, ghevar,
gulab_jamun, imarti, jalebi, kachori, kadai_paneer, kadhi_pakoda, kajjikaya, kakinada_khaja, kalakand, karela_bharta, kofta, kuzhi_paniyaram,
lassi, ledikeni, litti_chokha, lyangcha, maach_jhol, makki_di_roti_sarson_da_saag, malapua, misi_roti, misti_doi, modak, mysore_pak, naan, navrattan_korma,
palak_paneer, paneer_butter_masala, phirni, pithe, poha, poornalu, pootharekulu, qubani_ka_meetha, rabri, ras_malai, rasgulla, sandesh, shankarpali,
sheer_korma, sheera, shrikhand, sohan_halwa, sohan_papdi, sutar_feni, unni_appam
- **Developed by:** [Ashutosh Sharma]
|
cnat-08/BarbenheimerClassifier5 | cnat-08 | 2024-01-09T10:34:24Z | 0 | 0 | fastai | [
"fastai",
"region:us"
] | null | 2024-01-09T10:33:52Z | ---
tags:
- fastai
---
# Amazing!
🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
|
alexandreacff/zephyr_7b_1enem_apostilas_1ksteps_linear_warmup | alexandreacff | 2024-01-09T10:32:51Z | 5 | 0 | peft | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:HuggingFaceH4/zephyr-7b-alpha",
"base_model:adapter:HuggingFaceH4/zephyr-7b-alpha",
"license:mit",
"region:us"
] | null | 2024-01-08T13:08:53Z | ---
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-alpha
model-index:
- name: zephyr_7b_1enem_apostilas_1ksteps_linear_warmup
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# zephyr_7b_1enem_apostilas_1ksteps_linear_warmup
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- training_steps: 1000
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 1.13.0+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0 |
wcyat/whisper-small-yue-lora | wcyat | 2024-01-09T10:15:39Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"arxiv:1910.09700",
"base_model:wcyat/whisper-small-yue",
"base_model:adapter:wcyat/whisper-small-yue",
"region:us"
] | null | 2024-01-09T08:45:34Z | ---
library_name: peft
base_model: wcyat/whisper-small-yue
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
aimlnerd/bert-finetuned-legalentity-ner-accelerate | aimlnerd | 2024-01-09T10:14:48Z | 103 | 1 | transformers | [
"transformers",
"safetensors",
"bert",
"token-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2024-01-09T08:40:44Z | ---
license: apache-2.0
---
# Extract Legal Entities from Insurance Documents using BERT transfomers
This model is a fine tuned BERT transfomers for NER of legal entities in Life Insurance demand letters.
Dataset is publicly available here
https://github.com/aws-samples/aws-legal-entity-extraction.git
The model extracts the following entities:
* Law Firm
* Law Office Address
* Insurance Company
* Insurance Company Address
* Policy Holder Name
* Beneficiary Name
* Policy Number
* Payout
* Required Action
* Sender
## HF Space
https://huggingface.co/spaces/aimlnerd/legal-entity-ner-transformers
This space expose the model as gradio app and contains, training dataset and code for training.
Dataset consists of legal requisition/demand letters for Life Insurance, however this approach can be used across any industry & document which may benefit from spatial data in NER training.
## Data preprocessing
The OCRed data is present as JSON here ```data/raw_data/annotations```.
I wrote this code to convert the JSON data in format suitable for HF TokenClassification
```source/services/ner/awscomprehend_2_ner_format.py```
## Finetuning BERT Transformers model
```source/services/ner/train/train.py```
This code fine tune the BERT model and uploads to huggingface
|
jysssacc/roberta-base_PrefixTuning_lr5e-05_bs4_epoch1_wd0.01 | jysssacc | 2024-01-09T10:02:26Z | 1 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:adapter:FacebookAI/roberta-base",
"license:mit",
"region:us"
] | null | 2024-01-09T10:02:03Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: roberta-base
model-index:
- name: roberta-base_PrefixTuning_lr5e-05_bs4_epoch1_wd0.01
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base_PrefixTuning_lr5e-05_bs4_epoch1_wd0.01
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 19.1081
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 13.3356 | 1.0 | 157 | 19.1081 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0 |
jysssacc/opt-350m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01 | jysssacc | 2024-01-09T09:59:07Z | 3 | 0 | peft | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:facebook/opt-350m",
"base_model:adapter:facebook/opt-350m",
"license:other",
"region:us"
] | null | 2024-01-08T00:32:54Z | ---
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/opt-350m
model-index:
- name: opt-350m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# opt-350m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 7.3679
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 9.7195 | 1.0 | 157 | 9.7698 |
| 9.4441 | 2.0 | 314 | 9.3700 |
| 9.1944 | 3.0 | 471 | 8.7393 |
| 8.663 | 4.0 | 628 | 8.3164 |
| 8.4504 | 5.0 | 785 | 8.0815 |
| 8.201 | 6.0 | 942 | 7.9094 |
| 8.0965 | 7.0 | 1099 | 7.7845 |
| 7.9382 | 8.0 | 1256 | 7.6983 |
| 7.7828 | 9.0 | 1413 | 7.6242 |
| 7.7907 | 10.0 | 1570 | 7.5654 |
| 7.7221 | 11.0 | 1727 | 7.5225 |
| 7.5905 | 12.0 | 1884 | 7.4850 |
| 7.5802 | 13.0 | 2041 | 7.4554 |
| 7.5914 | 14.0 | 2198 | 7.4319 |
| 7.5632 | 15.0 | 2355 | 7.4102 |
| 7.4937 | 16.0 | 2512 | 7.3961 |
| 7.4921 | 17.0 | 2669 | 7.3838 |
| 7.457 | 18.0 | 2826 | 7.3748 |
| 7.5307 | 19.0 | 2983 | 7.3697 |
| 7.4599 | 20.0 | 3140 | 7.3679 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0 |
duyne/distilbert-base-uncased-finetuned-emotion | duyne | 2024-01-09T09:55:42Z | 92 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-08-14T14:31:20Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.921
- name: F1
type: f1
value: 0.9209278298716373
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2239
- Accuracy: 0.921
- F1: 0.9209
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 250 | 0.3194 | 0.907 | 0.9061 |
| No log | 2.0 | 500 | 0.2239 | 0.921 | 0.9209 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1 | mmnga | 2024-01-09T09:52:44Z | 28 | 18 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"conversational",
"fr",
"it",
"de",
"es",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-12-16T19:09:26Z | ---
language:
- fr
- it
- de
- es
- en
license: apache-2.0
tags:
- moe
inference: false
---
# Model Card for Mixtral-Fusion-4x7B-Instruct-v0.1
This model is an experimental model created by merging [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) experts.
# How we merged experts
Changed to merge using slerp.
[Discussion](https://huggingface.co/mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1/discussions/2)
[old merge version](https://huggingface.co/mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1/tree/v0.1.0)
~~We simply take the average of every two experts.weight.~~
~~The same goes for gate.weight.~~
# How To Convert
use colab cpu-high-memory.
[convert_mixtral_8x7b_to_4x7b.ipynb](https://huggingface.co/mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1/blob/main/notebook/convert_mixtral_8x7b_to_4x7b.ipynb)
# OtherModels
[mmnga/Mixtral-Extraction-4x7B-Instruct-v0.1](https://huggingface.co/mmnga/Mixtral-Extraction-4x7B-Instruct-v0.1)
# Usage
~~~python
pip install git+https://github.com/huggingface/transformers --upgrade
pip install torch accelerate bitsandbytes flash_attn
~~~
~~~python
from transformers import AutoTokenizer, AutoModelForCausalLM, MixtralForCausalLM
import torch
model_name_or_path = "mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = MixtralForCausalLM.from_pretrained(model_name_or_path, load_in_8bit=True)
text = "[INST] What was John Holt's vision on education? [/INST] "
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
~~~
|
mmnga/TinyMixtral-x8-Clonebase-7b | mmnga | 2024-01-09T09:52:08Z | 29 | 4 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-12-17T17:22:25Z | ---
language:
- en
license: apache-2.0
tags:
- moe
inference: false
---
# Model Card for TinyMixtral-x8-Clonebase-7b
This model is based on [TinyLlama-1.1B](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T), converted to a mistral model, and then placed the clone in mixtral.
**This model was created experimentally for training a small mixtral.**
**Without Train, the performance of this model is the same as TinyLlama.**
# How it was made
First, since tinyllama is an llama model, I converted it to a mistral model.
After that, I cloned the FFN part and made it experts.
Since they are all the same tensor, the performance does not change.
All gates have the same value.
# How To Convert
use colab cpu-high-memory.
This model was created with experts=8, but since it is a clone, you can create as many experts as you like.
[tinyllama_to_mixtral_clonebase.ipynb](https://huggingface.co/mmnga/TinyMixtral-x8-Clonebase-7b/blob/main/notebook/tinyllama_to_mixtral_clonebase.ipynb)
# revision
[main TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/mmnga/TinyMixtral-x8-Clonebase-7b)
[old TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/mmnga/TinyMixtral-x8-Clonebase-7b/tree/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
# Usage
~~~python
pip install transformers --upgrade
pip install flash_attn bitsandbytes accelerate
~~~
~~~python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name_or_path = "mmnga/TinyMixtral-x8-Clonebase-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", load_in_8bit=True)
prompt = "Introducing the recipe for today's dinner."
with torch.no_grad():
token_ids = tokenizer.encode(prompt, return_tensors="pt")
output_ids = model.generate(
token_ids.to(model.device),
do_sample=True,
max_new_tokens=128,
repetition_penalty=1.5
)
output = tokenizer.decode(output_ids[0])
print(output)
~~~ |
Naati101/tb | Naati101 | 2024-01-09T09:47:58Z | 0 | 0 | keras | [
"keras",
"tf-keras",
"image-classification",
"medical",
"region:us"
] | image-classification | 2024-01-09T09:47:19Z | ---
library_name: keras
tags:
- image-classification
- medical
---
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
| :-- | :-- |
| name | Adam |
| weight_decay | None |
| clipnorm | None |
| global_clipnorm | None |
| clipvalue | None |
| use_ema | False |
| ema_momentum | 0.99 |
| ema_overwrite_frequency | None |
| jit_compile | True |
| is_legacy_optimizer | False |
| learning_rate | 0.0010000000474974513 |
| beta_1 | 0.9 |
| beta_2 | 0.999 |
| epsilon | 1e-07 |
| amsgrad | False |
| training_precision | float32 |
## Model Plot
<details>
<summary>View Model Plot</summary>

</details> |
Gayathri142214002/Pegasus_paraphraser_Com_9 | Gayathri142214002 | 2024-01-09T09:46:09Z | 139 | 0 | transformers | [
"transformers",
"safetensors",
"pegasus",
"text2text-generation",
"generated_from_trainer",
"base_model:Gayathri142214002/Pegasus_paraphraser_Com_8",
"base_model:finetune:Gayathri142214002/Pegasus_paraphraser_Com_8",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-01-09T09:21:40Z | ---
license: apache-2.0
base_model: Gayathri142214002/Pegasus_paraphraser_Com_8
tags:
- generated_from_trainer
model-index:
- name: Pegasus_paraphraser_Com_9
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Pegasus_paraphraser_Com_9
This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser_Com_8](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser_Com_8) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
racheltong/va_openai-whisper-tiny-en-colab_0.001_10 | racheltong | 2024-01-09T09:43:17Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:openai/whisper-tiny",
"base_model:adapter:openai/whisper-tiny",
"region:us"
] | null | 2024-01-09T09:43:06Z | ---
library_name: peft
base_model: openai/whisper-tiny
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
ybelkada/test-tags-model | ybelkada | 2024-01-09T09:34:10Z | 178 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"en",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T09:27:19Z | ---
language: en
tags:
- transformers
- trl
- dpo
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** en
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
HackerCIS/distilbert-base-uncased-finetuned-emotion | HackerCIS | 2024-01-09T09:29:43Z | 92 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T09:11:34Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9175
- name: F1
type: f1
value: 0.9173530455189519
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2326
- Accuracy: 0.9175
- F1: 0.9174
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8354 | 1.0 | 250 | 0.3426 | 0.901 | 0.8997 |
| 0.263 | 2.0 | 500 | 0.2326 | 0.9175 | 0.9174 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Arim/temp | Arim | 2024-01-09T09:10:14Z | 0 | 0 | null | [
"region:us"
] | null | 2023-12-20T06:36:20Z | upload custom base model for lora training |
decruz07/llama-2-7b-miniguanaco | decruz07 | 2024-01-09T09:01:11Z | 1,484 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T08:28:34Z | ---
license: apache-2.0
---
## llama-2-7b-miniguanaco
This is my first model, with LLama-2-7b model finetuned with miniguanaco datasets.
This is a simple finetune based off a Google Colab notebook. Finetune instructions were from Labonne's first tutorial.
To run it:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
model_path = "decruz07/llama-2-7b-miniguanaco"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
|
0x7o/nanoFialka-v1 | 0x7o | 2024-01-09T09:00:16Z | 103 | 4 | transformers | [
"transformers",
"onnx",
"safetensors",
"gpt2",
"text-generation",
"ru",
"dataset:0x7194633/fialka-v3-data",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-05T08:53:01Z | ---
license: apache-2.0
datasets:
- 0x7194633/fialka-v3-data
language:
- ru
pipeline_tag: text-generation
---
# Nano Fialka v1.0
## Description
This is a test model trained for non-serious tasks. For a production environment, use [Fialka 13B](https://huggingface.co/collections/0x7194633/fialka-llms-658a87c2003ceee6937a0d2e).
## Usage
The model has a query format as in zephyr.
```
<|user|>
Что такое мем?</s>
<|assistant|>
Мем (англ. meme) — это единица культурной информации, которая распространяется в социальных сетях и других онлайн-платформах с помощью цифровых технологий или через физический контакт. Мемы могут быть связаны между собой тематически или иметь общие черты, такие как использование определенных слов или фраз для создания определенного настроения или выражения эмоций. Они также могут содержать информацию о культуре, истории или науке, которую можно использовать для обучения новым вещам или расширения кругозора.
``` |
tuanHenry/distilbert_base_uncased_Movies_genre_predict | tuanHenry | 2024-01-09T08:47:03Z | 96 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-01-09T08:46:43Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0750
- Accuracy: 0.6202
- F1: 0.6107
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 0.02 | 20 | 2.2641 | 0.2781 | 0.1211 |
| No log | 0.04 | 40 | 2.0495 | 0.2786 | 0.1221 |
| No log | 0.05 | 60 | 1.8930 | 0.4343 | 0.3708 |
| No log | 0.07 | 80 | 1.8073 | 0.4046 | 0.3218 |
| No log | 0.09 | 100 | 1.7021 | 0.4710 | 0.4005 |
| No log | 0.11 | 120 | 1.6779 | 0.4715 | 0.4077 |
| No log | 0.12 | 140 | 1.6050 | 0.4804 | 0.4139 |
| No log | 0.14 | 160 | 1.5298 | 0.5032 | 0.4416 |
| No log | 0.16 | 180 | 1.4980 | 0.5037 | 0.4427 |
| No log | 0.18 | 200 | 1.4566 | 0.5112 | 0.4553 |
| No log | 0.19 | 220 | 1.4303 | 0.5295 | 0.4736 |
| No log | 0.21 | 240 | 1.4033 | 0.5340 | 0.4835 |
| No log | 0.23 | 260 | 1.4549 | 0.5052 | 0.4588 |
| No log | 0.25 | 280 | 1.3637 | 0.5404 | 0.5032 |
| No log | 0.26 | 300 | 1.3285 | 0.5473 | 0.5067 |
| No log | 0.28 | 320 | 1.3536 | 0.5454 | 0.5199 |
| No log | 0.3 | 340 | 1.3069 | 0.5528 | 0.5166 |
| No log | 0.32 | 360 | 1.2906 | 0.5464 | 0.5134 |
| No log | 0.33 | 380 | 1.2867 | 0.5612 | 0.5355 |
| No log | 0.35 | 400 | 1.2854 | 0.5493 | 0.5145 |
| No log | 0.37 | 420 | 1.2707 | 0.5702 | 0.5465 |
| No log | 0.39 | 440 | 1.2698 | 0.5667 | 0.5484 |
| No log | 0.41 | 460 | 1.2531 | 0.5766 | 0.5637 |
| No log | 0.42 | 480 | 1.2348 | 0.5801 | 0.5592 |
| No log | 0.44 | 500 | 1.2392 | 0.5756 | 0.5531 |
| No log | 0.46 | 520 | 1.2110 | 0.5821 | 0.5584 |
| No log | 0.48 | 540 | 1.2050 | 0.5771 | 0.5546 |
| No log | 0.49 | 560 | 1.2078 | 0.5756 | 0.5482 |
| No log | 0.51 | 580 | 1.2088 | 0.5776 | 0.5518 |
| No log | 0.53 | 600 | 1.1987 | 0.5905 | 0.5758 |
| No log | 0.55 | 620 | 1.1893 | 0.5761 | 0.5548 |
| No log | 0.56 | 640 | 1.1991 | 0.5801 | 0.5667 |
| No log | 0.58 | 660 | 1.1939 | 0.5865 | 0.5755 |
| No log | 0.6 | 680 | 1.1701 | 0.5875 | 0.5653 |
| No log | 0.62 | 700 | 1.1852 | 0.5870 | 0.5709 |
| No log | 0.63 | 720 | 1.1699 | 0.5845 | 0.5668 |
| No log | 0.65 | 740 | 1.1778 | 0.5910 | 0.5731 |
| No log | 0.67 | 760 | 1.1546 | 0.5984 | 0.5806 |
| No log | 0.69 | 780 | 1.1720 | 0.5890 | 0.5687 |
| No log | 0.7 | 800 | 1.1554 | 0.5940 | 0.5730 |
| No log | 0.72 | 820 | 1.1454 | 0.5910 | 0.5748 |
| No log | 0.74 | 840 | 1.1457 | 0.6034 | 0.5893 |
| No log | 0.76 | 860 | 1.1631 | 0.5935 | 0.5663 |
| No log | 0.78 | 880 | 1.1277 | 0.6059 | 0.5930 |
| No log | 0.79 | 900 | 1.1291 | 0.5984 | 0.5839 |
| No log | 0.81 | 920 | 1.1345 | 0.5954 | 0.5826 |
| No log | 0.83 | 940 | 1.1253 | 0.6034 | 0.5868 |
| No log | 0.85 | 960 | 1.1397 | 0.5989 | 0.5899 |
| No log | 0.86 | 980 | 1.1223 | 0.6009 | 0.5890 |
| No log | 0.88 | 1000 | 1.1363 | 0.6059 | 0.5917 |
| No log | 0.9 | 1020 | 1.1391 | 0.5944 | 0.5787 |
| No log | 0.92 | 1040 | 1.1480 | 0.5860 | 0.5732 |
| No log | 0.93 | 1060 | 1.1065 | 0.6063 | 0.5925 |
| No log | 0.95 | 1080 | 1.1250 | 0.5984 | 0.5844 |
| No log | 0.97 | 1100 | 1.1344 | 0.5935 | 0.5835 |
| No log | 0.99 | 1120 | 1.1452 | 0.5880 | 0.5700 |
| 1.3609 | 1.0 | 1140 | 1.1084 | 0.6093 | 0.5960 |
| 1.3609 | 1.02 | 1160 | 1.1079 | 0.6098 | 0.6006 |
| 1.3609 | 1.04 | 1180 | 1.1178 | 0.6073 | 0.5951 |
| 1.3609 | 1.06 | 1200 | 1.1267 | 0.6004 | 0.5878 |
| 1.3609 | 1.07 | 1220 | 1.1084 | 0.6098 | 0.5977 |
| 1.3609 | 1.09 | 1240 | 1.1109 | 0.6039 | 0.5910 |
| 1.3609 | 1.11 | 1260 | 1.1142 | 0.6078 | 0.5968 |
| 1.3609 | 1.13 | 1280 | 1.1218 | 0.6024 | 0.5915 |
| 1.3609 | 1.15 | 1300 | 1.0929 | 0.6197 | 0.6057 |
| 1.3609 | 1.16 | 1320 | 1.1001 | 0.6108 | 0.5995 |
| 1.3609 | 1.18 | 1340 | 1.1049 | 0.6068 | 0.5993 |
| 1.3609 | 1.2 | 1360 | 1.1019 | 0.6098 | 0.5971 |
| 1.3609 | 1.22 | 1380 | 1.1140 | 0.6029 | 0.5942 |
| 1.3609 | 1.23 | 1400 | 1.0981 | 0.6078 | 0.5991 |
| 1.3609 | 1.25 | 1420 | 1.1129 | 0.6078 | 0.5965 |
| 1.3609 | 1.27 | 1440 | 1.0896 | 0.6173 | 0.6076 |
| 1.3609 | 1.29 | 1460 | 1.1062 | 0.6059 | 0.5935 |
| 1.3609 | 1.3 | 1480 | 1.1038 | 0.6143 | 0.5996 |
| 1.3609 | 1.32 | 1500 | 1.0906 | 0.6182 | 0.6072 |
| 1.3609 | 1.34 | 1520 | 1.0883 | 0.6182 | 0.6099 |
| 1.3609 | 1.36 | 1540 | 1.1114 | 0.6024 | 0.5955 |
| 1.3609 | 1.37 | 1560 | 1.0884 | 0.6158 | 0.6044 |
| 1.3609 | 1.39 | 1580 | 1.0994 | 0.6088 | 0.6021 |
| 1.3609 | 1.41 | 1600 | 1.0857 | 0.6187 | 0.6055 |
| 1.3609 | 1.43 | 1620 | 1.1067 | 0.6098 | 0.6027 |
| 1.3609 | 1.44 | 1640 | 1.0845 | 0.6237 | 0.6167 |
| 1.3609 | 1.46 | 1660 | 1.0899 | 0.6177 | 0.6065 |
| 1.3609 | 1.48 | 1680 | 1.0925 | 0.6177 | 0.6067 |
| 1.3609 | 1.5 | 1700 | 1.0831 | 0.6148 | 0.6042 |
| 1.3609 | 1.52 | 1720 | 1.0988 | 0.6108 | 0.6017 |
| 1.3609 | 1.53 | 1740 | 1.0810 | 0.6173 | 0.6069 |
| 1.3609 | 1.55 | 1760 | 1.0857 | 0.6163 | 0.6049 |
| 1.3609 | 1.57 | 1780 | 1.1003 | 0.6103 | 0.5985 |
| 1.3609 | 1.59 | 1800 | 1.0861 | 0.6143 | 0.6045 |
| 1.3609 | 1.6 | 1820 | 1.1024 | 0.6073 | 0.5976 |
| 1.3609 | 1.62 | 1840 | 1.0786 | 0.6222 | 0.6094 |
| 1.3609 | 1.64 | 1860 | 1.0984 | 0.6088 | 0.5968 |
| 1.3609 | 1.66 | 1880 | 1.0750 | 0.6227 | 0.6146 |
| 1.3609 | 1.67 | 1900 | 1.0849 | 0.6108 | 0.6029 |
| 1.3609 | 1.69 | 1920 | 1.0787 | 0.6192 | 0.6102 |
| 1.3609 | 1.71 | 1940 | 1.0831 | 0.6133 | 0.6036 |
| 1.3609 | 1.73 | 1960 | 1.0739 | 0.6197 | 0.6136 |
| 1.3609 | 1.74 | 1980 | 1.0766 | 0.6187 | 0.6092 |
| 1.3609 | 1.76 | 2000 | 1.0778 | 0.6207 | 0.6119 |
| 1.3609 | 1.78 | 2020 | 1.0739 | 0.6168 | 0.6053 |
| 1.3609 | 1.8 | 2040 | 1.0736 | 0.6182 | 0.6066 |
| 1.3609 | 1.81 | 2060 | 1.0723 | 0.6212 | 0.6107 |
| 1.3609 | 1.83 | 2080 | 1.0792 | 0.6222 | 0.6126 |
| 1.3609 | 1.85 | 2100 | 1.0823 | 0.6177 | 0.6091 |
| 1.3609 | 1.87 | 2120 | 1.0706 | 0.6197 | 0.6094 |
| 1.3609 | 1.89 | 2140 | 1.0729 | 0.6217 | 0.6107 |
| 1.3609 | 1.9 | 2160 | 1.0728 | 0.6202 | 0.6094 |
| 1.3609 | 1.92 | 2180 | 1.0754 | 0.6187 | 0.6083 |
| 1.3609 | 1.94 | 2200 | 1.0775 | 0.6192 | 0.6094 |
| 1.3609 | 1.96 | 2220 | 1.0773 | 0.6187 | 0.6090 |
| 1.3609 | 1.97 | 2240 | 1.0767 | 0.6177 | 0.6082 |
| 1.3609 | 1.99 | 2260 | 1.0750 | 0.6202 | 0.6107 |
### Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0
|
fblgit/UNAversal-2x7B-v1 | fblgit | 2024-01-09T08:46:15Z | 1,488 | 3 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"llama-factory",
"lora",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T07:44:56Z | ---
license: apache-2.0
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: UNAversal-2x7B-v1
results: []
---
# UNAversal-2x7B-v1
Merely Phase 1 UNA, only MLP's and its kinda of a beta. The goal was to produce a small but powerful MoE.
This is a 2 MoE model, of 7B each expert. Based on intel-neural series v3.
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|--------------|-------|------|-----:|----------|-----:|---|-----:|
|arc_challenge |Yaml |none | 25|acc |0.7133|± |0.0132|
| | |none | 25|acc_norm |0.7235|± |0.0131|
|arc_easy |Yaml |none | 0|acc |0.8674|± |0.0070|
| | |none | 0|acc_norm |0.8291|± |0.0077|
|boolq |Yaml |none | 0|acc |0.8768|± |0.0057|
|lambada_openai|Yaml |none | 0|perplexity|3.6656|± |0.0841|
| | |none | 0|acc |0.7017|± |0.0064|
|mathqa |Yaml |none | 0|acc |0.3474|± |0.0087|
| | |none | 0|acc_norm |0.3585|± |0.0088|
|piqa |Yaml |none | 0|acc |0.8411|± |0.0085|
| | |none | 0|acc_norm |0.8526|± |0.0083|
|sciq |Yaml |none | 0|acc |0.9600|± |0.0062|
| | |none | 0|acc_norm |0.9370|± |0.0077| |
uttam333/layoutlm-custom | uttam333 | 2024-01-09T08:41:02Z | 61 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"layoutlm",
"token-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2024-01-09T08:34:30Z | ---
tags:
- generated_from_trainer
model-index:
- name: layoutlm-custom
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# layoutlm-custom
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1583
- Noise: {'precision': 0.8818897637795275, 'recall': 0.8736349453978159, 'f1': 0.8777429467084641, 'number': 641}
- Signal: {'precision': 0.861198738170347, 'recall': 0.853125, 'f1': 0.8571428571428572, 'number': 640}
- Overall Precision: 0.8716
- Overall Recall: 0.8634
- Overall F1: 0.8675
- Overall Accuracy: 0.9656
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Noise | Signal | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.3882 | 1.0 | 18 | 0.2617 | {'precision': 0.6654804270462633, 'recall': 0.5834633385335414, 'f1': 0.6217788861180383, 'number': 641} | {'precision': 0.6149732620320856, 'recall': 0.5390625, 'f1': 0.5745212323064114, 'number': 640} | 0.6402 | 0.5613 | 0.5982 | 0.8986 |
| 0.1694 | 2.0 | 36 | 0.1752 | {'precision': 0.7387820512820513, 'recall': 0.719188767550702, 'f1': 0.7288537549407115, 'number': 641} | {'precision': 0.709470304975923, 'recall': 0.690625, 'f1': 0.6999208234362629, 'number': 640} | 0.7241 | 0.7049 | 0.7144 | 0.9296 |
| 0.1039 | 3.0 | 54 | 0.1356 | {'precision': 0.7865168539325843, 'recall': 0.7644305772230889, 'f1': 0.7753164556962026, 'number': 641} | {'precision': 0.77491961414791, 'recall': 0.753125, 'f1': 0.7638668779714739, 'number': 640} | 0.7807 | 0.7588 | 0.7696 | 0.9439 |
| 0.064 | 4.0 | 72 | 0.1342 | {'precision': 0.8220472440944881, 'recall': 0.8143525741029641, 'f1': 0.8181818181818181, 'number': 641} | {'precision': 0.8028391167192429, 'recall': 0.7953125, 'f1': 0.7990580847723705, 'number': 640} | 0.8125 | 0.8048 | 0.8086 | 0.9522 |
| 0.0433 | 5.0 | 90 | 0.1241 | {'precision': 0.8544303797468354, 'recall': 0.8424336973478939, 'f1': 0.8483896307934014, 'number': 641} | {'precision': 0.8320126782884311, 'recall': 0.8203125, 'f1': 0.8261211644374509, 'number': 640} | 0.8432 | 0.8314 | 0.8373 | 0.9601 |
| 0.0293 | 6.0 | 108 | 0.1274 | {'precision': 0.8650793650793651, 'recall': 0.8502340093603744, 'f1': 0.8575924468922109, 'number': 641} | {'precision': 0.8378378378378378, 'recall': 0.8234375, 'f1': 0.830575256107171, 'number': 640} | 0.8515 | 0.8368 | 0.8441 | 0.9617 |
| 0.0199 | 7.0 | 126 | 0.1372 | {'precision': 0.8722397476340694, 'recall': 0.8627145085803433, 'f1': 0.8674509803921568, 'number': 641} | {'precision': 0.8530805687203792, 'recall': 0.84375, 'f1': 0.8483896307934015, 'number': 640} | 0.8627 | 0.8532 | 0.8579 | 0.9640 |
| 0.0139 | 8.0 | 144 | 0.1386 | {'precision': 0.8839427662957074, 'recall': 0.8673946957878315, 'f1': 0.8755905511811023, 'number': 641} | {'precision': 0.856687898089172, 'recall': 0.840625, 'f1': 0.8485804416403785, 'number': 640} | 0.8703 | 0.8540 | 0.8621 | 0.9656 |
| 0.0126 | 9.0 | 162 | 0.1467 | {'precision': 0.8829113924050633, 'recall': 0.8705148205928237, 'f1': 0.8766692851531814, 'number': 641} | {'precision': 0.8541996830427893, 'recall': 0.8421875, 'f1': 0.848151062155783, 'number': 640} | 0.8686 | 0.8564 | 0.8624 | 0.9654 |
| 0.0114 | 10.0 | 180 | 0.1531 | {'precision': 0.8694968553459119, 'recall': 0.8627145085803433, 'f1': 0.8660924040720438, 'number': 641} | {'precision': 0.8472440944881889, 'recall': 0.840625, 'f1': 0.8439215686274509, 'number': 640} | 0.8584 | 0.8517 | 0.8550 | 0.9631 |
| 0.0099 | 11.0 | 198 | 0.1581 | {'precision': 0.8703125, 'recall': 0.8689547581903276, 'f1': 0.8696330991412958, 'number': 641} | {'precision': 0.8450704225352113, 'recall': 0.84375, 'f1': 0.8444096950742768, 'number': 640} | 0.8577 | 0.8564 | 0.8570 | 0.9634 |
| 0.0064 | 12.0 | 216 | 0.1543 | {'precision': 0.8866141732283465, 'recall': 0.8783151326053042, 'f1': 0.8824451410658307, 'number': 641} | {'precision': 0.8643533123028391, 'recall': 0.85625, 'f1': 0.8602825745682888, 'number': 640} | 0.8755 | 0.8673 | 0.8714 | 0.9659 |
| 0.0059 | 13.0 | 234 | 0.1628 | {'precision': 0.8732394366197183, 'recall': 0.8705148205928237, 'f1': 0.871875, 'number': 641} | {'precision': 0.8526645768025078, 'recall': 0.85, 'f1': 0.8513302034428795, 'number': 640} | 0.8630 | 0.8603 | 0.8616 | 0.9645 |
| 0.0056 | 14.0 | 252 | 0.1587 | {'precision': 0.878740157480315, 'recall': 0.8705148205928237, 'f1': 0.8746081504702194, 'number': 641} | {'precision': 0.8580441640378549, 'recall': 0.85, 'f1': 0.8540031397174254, 'number': 640} | 0.8684 | 0.8603 | 0.8643 | 0.9651 |
| 0.005 | 15.0 | 270 | 0.1583 | {'precision': 0.8818897637795275, 'recall': 0.8736349453978159, 'f1': 0.8777429467084641, 'number': 641} | {'precision': 0.861198738170347, 'recall': 0.853125, 'f1': 0.8571428571428572, 'number': 640} | 0.8716 | 0.8634 | 0.8675 | 0.9656 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
1DS/adapter-category-mapping-beauty_baby_hpc_grocery_computer_kitchen-Llama-2-7b-chat-hf-v1 | 1DS | 2024-01-09T08:38:14Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null | 2024-01-09T08:38:13Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
amd/ese_vovnet39b | amd | 2024-01-09T08:35:03Z | 0 | 0 | null | [
"onnx",
"RyzenAI",
"vision",
"classification",
"pytorch",
"dataset:imagenet-1k",
"arxiv:1904.09730",
"license:apache-2.0",
"region:us"
] | null | 2023-12-04T09:17:27Z | ---
license: apache-2.0
datasets:
- imagenet-1k
metrics:
- accuracy
tags:
- RyzenAI
- vision
- classification
- pytorch
---
# ESE_VoVNet39b
Quantized ESE_VoVNet39b model that could be supported by [AMD Ryzen AI](https://ryzenai.docs.amd.com/en/latest/).
## Model description
VoVNet was first introduced in the paper [An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection](https://arxiv.org/abs/1904.09730). Pretrained on ImageNet-1k in timm by Ross Wightman using RandAugment RA recipe.
The model implementation is from [timm](https://huggingface.co/timm/ese_vovnet39b.ra_in1k).
## How to use
### Installation
Follow [Ryzen AI Installation](https://ryzenai.docs.amd.com/en/latest/inst.html) to prepare the environment for Ryzen AI.
Run the following script to install pre-requisites for this model.
```bash
pip install -r requirements.txt
```
### Data Preparation
Follow [ImageNet](https://huggingface.co/datasets/imagenet-1k) to prepare dataset.
### Model Evaluation
```python
python eval_onnx.py --onnx_model ese_vovnet39b_int.onnx --ipu --provider_config Path\To\vaip_config.json --data_dir /Path/To/Your/Dataset
```
### Performance
|Metric |Accuracy on IPU|
| :----: | :----: |
|Top1/Top5| 78.96% / 94.53%|
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@inproceedings{lee2019energy,
title = {An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection},
author = {Lee, Youngwan and Hwang, Joong-won and Lee, Sangrok and Bae, Yuseok and Park, Jongyoul},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019}
}
``` |
ensound/labiezione_generator | ensound | 2024-01-09T08:33:39Z | 80 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"autotrain",
"conversational",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T01:22:51Z | ---
tags:
- autotrain
- text-generation
widget:
- text: "I love AutoTrain because "
license: other
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
``` |
amd/efficientnet-es | amd | 2024-01-09T08:32:48Z | 0 | 0 | null | [
"onnx",
"RyzenAI",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1905.11946",
"license:apache-2.0",
"region:us"
] | image-classification | 2023-12-04T09:02:55Z | ---
license: apache-2.0
tags:
- RyzenAI
- image-classification
- onnx
datasets:
- imagenet-1k
---
# EfficientNet
The EfficientNet model was proposed in [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946) by Mingxing Tan and Quoc V. Le. EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models. The specific version of EfficientNet here is EfficientNet-ES (EdgeTPU-Small).
We develop a modified version that could be supported by [AMD Ryzen AI](https://ryzenai.docs.amd.com/en/latest/).
## Model description
The abstract from the paper is the following:
*Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters.*
The original code can be found [here](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet).
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?sort=trending&search=efficientnet) to look for fine-tuned versions on a task that interests you.
## How to use
### Installation
1. Follow [Ryzen AI Installation](https://ryzenai.docs.amd.com/en/latest/inst.html) to prepare the environment for Ryzen AI.
2. Run the following script to install pre-requisites for this model.
```shell
pip install -r requirements.txt
```
### Test & Evaluation
- Inference one image (Image Classification):
```python
import onnxruntime
import argparse
from PIL import Image
import torchvision.transforms as transforms
parser = argparse.ArgumentParser()
parser.add_argument('--onnx_path', type=str, default="EfficientNet_int.onnx", required=False)
parser.add_argument('--image_path', type=str, required=True)
args = parser.parse_args()
def read_image():
# Read a PIL image
image = Image.open(args.image_path)
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Resize((224, 224)),
normalize,
])
img_tensor = transform(image).unsqueeze(0)
return img_tensor.numpy()
def main():
so = onnxruntime.SessionOptions()
ort_session = onnxruntime.InferenceSession(
args.onnx_path, so, providers=['CUDAExecutionProvider'])
ort_inputs = {
"WrapModel::input_0": read_image()
}
output = ort_session.run(None, ort_inputs)[0]
print("class id =", output[0].argmax())
if __name__ == "__main__":
main()
```
- Evaluate ImageNet validation dataset(50,000 images), using `eval_onnx.py` .
```shell
python eval_onnx.py --onnx_model EfficientNet_int.onnx --ipu --provider_config Path\To\vaip_config.json --data_dir /Path/To/Your/Dataset
```
### Performance
Dataset: ImageNet validation dataset (50,000 images).
| Metric | Accuracy on IPU |
| :-----------------: | :-------------: |
| top1& top5 accuracy | 77.72% / 93.78% |
## Citation
```bibtex
@article{EfficientNet,
author = {Mingxing Tan and Quoc V. Le},
title = {Searching for MobileNetV3},
year = {2019},
url = {https://arxiv.org/abs/1905.11946},
}
``` |
santhosh/madlad400-3b-ct2 | santhosh | 2024-01-09T08:27:24Z | 139 | 12 | transformers | [
"transformers",
"text2text-generation",
"text-generation-inference",
"translation",
"multilingual",
"en",
"ru",
"es",
"fr",
"de",
"it",
"pt",
"pl",
"nl",
"vi",
"tr",
"sv",
"id",
"ro",
"cs",
"zh",
"hu",
"ja",
"th",
"fi",
"fa",
"uk",
"da",
"el",
"no",
"bg",
"sk",
"ko",
"ar",
"lt",
"ca",
"sl",
"he",
"et",
"lv",
"hi",
"sq",
"ms",
"az",
"sr",
"ta",
"hr",
"kk",
"is",
"ml",
"mr",
"te",
"af",
"gl",
"fil",
"be",
"mk",
"eu",
"bn",
"ka",
"mn",
"bs",
"uz",
"ur",
"sw",
"yue",
"ne",
"kn",
"kaa",
"gu",
"si",
"cy",
"eo",
"la",
"hy",
"ky",
"tg",
"ga",
"mt",
"my",
"km",
"tt",
"so",
"ku",
"ps",
"pa",
"rw",
"lo",
"ha",
"dv",
"fy",
"lb",
"ckb",
"mg",
"gd",
"am",
"ug",
"ht",
"grc",
"hmn",
"sd",
"jv",
"mi",
"tk",
"ceb",
"yi",
"ba",
"fo",
"or",
"xh",
"su",
"kl",
"ny",
"sm",
"sn",
"co",
"zu",
"ig",
"yo",
"pap",
"st",
"haw",
"as",
"oc",
"cv",
"lus",
"tet",
"gsw",
"sah",
"br",
"rm",
"sa",
"bo",
"om",
"se",
"ce",
"cnh",
"ilo",
"hil",
"udm",
"os",
"lg",
"ti",
"vec",
"ts",
"tyv",
"kbd",
"ee",
"iba",
"av",
"kha",
"to",
"tn",
"nso",
"fj",
"zza",
"ak",
"ada",
"otq",
"dz",
"bua",
"cfm",
"ln",
"chm",
"gn",
"krc",
"wa",
"hif",
"yua",
"srn",
"war",
"rom",
"bik",
"pam",
"sg",
"lu",
"ady",
"kbp",
"syr",
"ltg",
"myv",
"iso",
"kac",
"bho",
"ay",
"kum",
"qu",
"za",
"pag",
"ngu",
"ve",
"pck",
"zap",
"tyz",
"hui",
"bbc",
"tzo",
"tiv",
"ksd",
"gom",
"min",
"ang",
"nhe",
"bgp",
"nzi",
"nnb",
"nv",
"zxx",
"bci",
"kv",
"new",
"mps",
"alt",
"meu",
"bew",
"fon",
"iu",
"abt",
"mgh",
"mnw",
"tvl",
"dov",
"tlh",
"ho",
"kw",
"mrj",
"meo",
"crh",
"mbt",
"emp",
"ace",
"ium",
"mam",
"gym",
"mai",
"crs",
"pon",
"ubu",
"fip",
"quc",
"gv",
"kj",
"btx",
"ape",
"chk",
"rcf",
"shn",
"tzh",
"mdf",
"ppk",
"ss",
"gag",
"cab",
"kri",
"seh",
"ibb",
"tbz",
"bru",
"enq",
"ach",
"cuk",
"kmb",
"wo",
"kek",
"qub",
"tab",
"bts",
"kos",
"rwo",
"cak",
"tuc",
"bum",
"cjk",
"gil",
"stq",
"tsg",
"quh",
"mak",
"arn",
"ban",
"jiv",
"sja",
"yap",
"tcy",
"toj",
"twu",
"xal",
"amu",
"rmc",
"hus",
"nia",
"kjh",
"bm",
"guh",
"mas",
"acf",
"dtp",
"ksw",
"bzj",
"din",
"zne",
"mad",
"msi",
"mag",
"mkn",
"kg",
"lhu",
"ch",
"qvi",
"mh",
"djk",
"sus",
"mfe",
"srm",
"dyu",
"ctu",
"gui",
"pau",
"inb",
"bi",
"mni",
"guc",
"jam",
"wal",
"jac",
"bas",
"gor",
"skr",
"nyu",
"noa",
"sda",
"gub",
"nog",
"cni",
"teo",
"tdx",
"sxn",
"rki",
"nr",
"frp",
"alz",
"taj",
"lrc",
"cce",
"rn",
"jvn",
"hvn",
"nij",
"dwr",
"izz",
"msm",
"bus",
"ktu",
"chr",
"maz",
"tzj",
"suz",
"knj",
"bim",
"gvl",
"bqc",
"tca",
"pis",
"prk",
"laj",
"mel",
"qxr",
"niq",
"ahk",
"shp",
"hne",
"spp",
"koi",
"krj",
"quf",
"luz",
"agr",
"tsc",
"mqy",
"gof",
"gbm",
"miq",
"dje",
"awa",
"bjj",
"qvz",
"sjp",
"tll",
"raj",
"kjg",
"bgz",
"quy",
"cbk",
"akb",
"oj",
"ify",
"mey",
"ks",
"cac",
"brx",
"qup",
"syl",
"jax",
"ff",
"ber",
"tks",
"trp",
"mrw",
"adh",
"smt",
"srr",
"ffm",
"qvc",
"mtr",
"ann",
"aa",
"noe",
"nut",
"gyn",
"kwi",
"xmm",
"msb",
"dataset:allenai/MADLAD-400",
"arxiv:2309.04662",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | translation | 2024-01-08T10:48:41Z | ---
license: apache-2.0
language:
- multilingual
- en
- ru
- es
- fr
- de
- it
- pt
- pl
- nl
- vi
- tr
- sv
- id
- ro
- cs
- zh
- hu
- ja
- th
- fi
- fa
- uk
- da
- el
- "no"
- bg
- sk
- ko
- ar
- lt
- ca
- sl
- he
- et
- lv
- hi
- sq
- ms
- az
- sr
- ta
- hr
- kk
- is
- ml
- mr
- te
- af
- gl
- fil
- be
- mk
- eu
- bn
- ka
- mn
- bs
- uz
- ur
- sw
- yue
- ne
- kn
- kaa
- gu
- si
- cy
- eo
- la
- hy
- ky
- tg
- ga
- mt
- my
- km
- tt
- so
- ku
- ps
- pa
- rw
- lo
- ha
- dv
- fy
- lb
- ckb
- mg
- gd
- am
- ug
- ht
- grc
- hmn
- sd
- jv
- mi
- tk
- ceb
- yi
- ba
- fo
- or
- xh
- su
- kl
- ny
- sm
- sn
- co
- zu
- ig
- yo
- pap
- st
- haw
- as
- oc
- cv
- lus
- tet
- gsw
- sah
- br
- rm
- sa
- bo
- om
- se
- ce
- cnh
- ilo
- hil
- udm
- os
- lg
- ti
- vec
- ts
- tyv
- kbd
- ee
- iba
- av
- kha
- to
- tn
- nso
- fj
- zza
- ak
- ada
- otq
- dz
- bua
- cfm
- ln
- chm
- gn
- krc
- wa
- hif
- yua
- srn
- war
- rom
- bik
- pam
- sg
- lu
- ady
- kbp
- syr
- ltg
- myv
- iso
- kac
- bho
- ay
- kum
- qu
- za
- pag
- ngu
- ve
- pck
- zap
- tyz
- hui
- bbc
- tzo
- tiv
- ksd
- gom
- min
- ang
- nhe
- bgp
- nzi
- nnb
- nv
- zxx
- bci
- kv
- new
- mps
- alt
- meu
- bew
- fon
- iu
- abt
- mgh
- mnw
- tvl
- dov
- tlh
- ho
- kw
- mrj
- meo
- crh
- mbt
- emp
- ace
- ium
- mam
- gym
- mai
- crs
- pon
- ubu
- fip
- quc
- gv
- kj
- btx
- ape
- chk
- rcf
- shn
- tzh
- mdf
- ppk
- ss
- gag
- cab
- kri
- seh
- ibb
- tbz
- bru
- enq
- ach
- cuk
- kmb
- wo
- kek
- qub
- tab
- bts
- kos
- rwo
- cak
- tuc
- bum
- cjk
- gil
- stq
- tsg
- quh
- mak
- arn
- ban
- jiv
- sja
- yap
- tcy
- toj
- twu
- xal
- amu
- rmc
- hus
- nia
- kjh
- bm
- guh
- mas
- acf
- dtp
- ksw
- bzj
- din
- zne
- mad
- msi
- mag
- mkn
- kg
- lhu
- ch
- qvi
- mh
- djk
- sus
- mfe
- srm
- dyu
- ctu
- gui
- pau
- inb
- bi
- mni
- guc
- jam
- wal
- jac
- bas
- gor
- skr
- nyu
- noa
- sda
- gub
- nog
- cni
- teo
- tdx
- sxn
- rki
- nr
- frp
- alz
- taj
- lrc
- cce
- rn
- jvn
- hvn
- nij
- dwr
- izz
- msm
- bus
- ktu
- chr
- maz
- tzj
- suz
- knj
- bim
- gvl
- bqc
- tca
- pis
- prk
- laj
- mel
- qxr
- niq
- ahk
- shp
- hne
- spp
- koi
- krj
- quf
- luz
- agr
- tsc
- mqy
- gof
- gbm
- miq
- dje
- awa
- bjj
- qvz
- sjp
- tll
- raj
- kjg
- bgz
- quy
- cbk
- akb
- oj
- ify
- mey
- ks
- cac
- brx
- qup
- syl
- jax
- ff
- ber
- tks
- trp
- mrw
- adh
- smt
- srr
- ffm
- qvc
- mtr
- ann
- kaa
- aa
- noe
- nut
- gyn
- kwi
- xmm
- msb
library_name: transformers
tags:
- text2text-generation
- text-generation-inference
datasets:
- allenai/MADLAD-400
pipeline_tag: translation
---
# Model Card for MADLAD-400-3B-CT2
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Model Details](#model-details)
2. [Usage](#usage)
3. [Uses](#uses)
4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
5. [Training Details](#training-details)
6. [Evaluation](#evaluation)
7. [Environmental Impact](#environmental-impact)
8. [Citation](#citation)
# TL;DR
MADLAD-400-3B-MT is a multilingual machine translation model based on the T5 architecture that was
trained on 1 trillion tokens covering over 450 languages using publicly available data.
It is competitive with models that are significantly larger.
**Disclaimer**: [Santhosh Thottingal](https://huggingface.co/santhosh), who was not involved in this research, converted
the original models to CTranslate2 optimized model and wrote the contents of this model card based on [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt).
# Model Details
## Model Description
- **Model type:** Language model
- **Language(s) (NLP):** Multilingual (400+ languages)
- **License:** Apache 2.0
- **Related Models:** [All MADLAD-400 Checkpoints](https://huggingface.co/models?search=madlad)
- **Original Checkpoints:** [All Original MADLAD-400 Checkpoints](https://github.com/google-research/google-research/tree/master/madlad_400)
- **Resources for more information:**
- [Research paper](https://arxiv.org/abs/2309.04662)
- [GitHub Repo](https://github.com/google-research/t5x)
- [Hugging Face MADLAD-400 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/MADLAD-400) - [Pending PR](https://github.com/huggingface/transformers/pull/27471)
# Usage
Find below some example scripts on how to use the model:
## Running the model on a CPU or GPU
First, install the CTranslate2 packages that are required:
`pip install ctranslate2 sentencepiece`
```python
import ctranslate2
from sentencepiece import SentencePieceProcessor
from huggingface_hub import snapshot_download
model_name = "santhosh/madlad400-3b-ct2"
model_path = snapshot_download(model_name)
tokenizer = SentencePieceProcessor()
tokenizer.load(f"{model_path}/sentencepiece.model")
translator = ctranslate2.Translator(model_path)
input_text = "I love pizza!"
input_tokens = tokenizer.encode(f"<2{target_language}> {input_text}", out_type=str)
results = translator.translate_batch(
[input_tokens],
batch_type="tokens",
max_batch_size=1024,
beam_size=1,
no_repeat_ngram_size=1,
repetition_penalty=2,
)
translated_sentence = tokenizer.decode(results[0].hypotheses[0])
print(translated_sentence)
# Eu adoro pizza!
```
# Uses
## Direct Use and Downstream Use
> Primary intended uses: Machine Translation and multilingual NLP tasks on over 400 languages.
> Primary intended users: Research community.
## Out-of-Scope Use
> These models are trained on general domain data and are therefore not meant to
> work on domain-specific models out-of-the box. Moreover, these research models have not been assessed
> for production usecases.
# Bias, Risks, and Limitations
> We note that we evaluate on only 204 of the languages supported by these models and on machine translation
> and few-shot machine translation tasks. Users must consider use of this model carefully for their own
> usecase.
## Ethical considerations and risks
> We trained these models with MADLAD-400 and publicly available data to create baseline models that
> support NLP for over 400 languages, with a focus on languages underrepresented in large-scale corpora.
> Given that these models were trained with web-crawled datasets that may contain sensitive, offensive or
> otherwise low-quality content despite extensive preprocessing, it is still possible that these issues to the
> underlying training data may cause differences in model performance and toxic (or otherwise problematic)
> output for certain domains. Moreover, large models are dual use technologies that have specific risks
> associated with their use and development. We point the reader to surveys such as those written by
> Weidinger et al. or Bommasani et al. for a more detailed discussion of these risks, and to Liebling
> et al. for a thorough discussion of the risks of machine translation systems.
## Known Limitations
More information needed
## Sensitive Use:
More information needed
# Training Details
> We train models of various sizes: a 3B, 32-layer parameter model,
> a 7.2B 48-layer parameter model and a 10.7B 32-layer parameter model.
> We share all parameters of the model across language pairs,
> and use a Sentence Piece Model with 256k tokens shared on both the encoder and decoder
> side. Each input sentence has a <2xx> token prepended to the source sentence to indicate the target
> language.
See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
## Training Data
> For both the machine translation and language model, MADLAD-400 is used. For the machine translation
> model, a combination of parallel datasources covering 157 languages is also used. Further details are
> described in the [paper](https://arxiv.org/pdf/2309.04662.pdf).
## Training Procedure
See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
# Evaluation
## Testing Data, Factors & Metrics
> For evaluation, we used WMT, NTREX, Flores-200 and Gatones datasets as described in Section 4.3 in the [paper](https://arxiv.org/pdf/2309.04662.pdf).
> The translation quality of this model varies based on language, as seen in the paper, and likely varies on
> domain, though we have not assessed this.
## Results



See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
# Environmental Impact
More information needed
# Citation
**BibTeX:**
```bibtex
@misc{kudugunta2023madlad400,
title={MADLAD-400: A Multilingual And Document-Level Large Audited Dataset},
author={Sneha Kudugunta and Isaac Caswell and Biao Zhang and Xavier Garcia and Christopher A. Choquette-Choo and Katherine Lee and Derrick Xin and Aditya Kusupati and Romi Stella and Ankur Bapna and Orhan Firat},
year={2023},
eprint={2309.04662},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
s3nh/GOAT-Finance-7B | s3nh | 2024-01-09T08:27:09Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:AdaptLLM/finance-chat",
"base_model:merge:AdaptLLM/finance-chat",
"base_model:GOAT-AI/GOAT-7B-Community",
"base_model:merge:GOAT-AI/GOAT-7B-Community",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T08:22:54Z | ---
base_model:
- GOAT-AI/GOAT-7B-Community
- AdaptLLM/finance-chat
tags:
- mergekit
- merge
---
# GOAT-Finance-7B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [GOAT-AI/GOAT-7B-Community](https://huggingface.co/GOAT-AI/GOAT-7B-Community)
* [AdaptLLM/finance-chat](https://huggingface.co/AdaptLLM/finance-chat)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: GOAT-AI/GOAT-7B-Community
dtype: float16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.22, 0.61, 0.46, 0.77, 1.0]
- filter: mlp
value: [0.78, 0.39, 0.54, 0.23, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 32]
model: AdaptLLM/finance-chat
- layer_range: [0, 32]
model: GOAT-AI/GOAT-7B-Community
```
|
1DS/adapter-title-brand-mapping-Llama-2-7b-chat-hf-v1 | 1DS | 2024-01-09T08:23:35Z | 0 | 0 | peft | [
"peft",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null | 2024-01-09T08:23:35Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Infrence Function
def generate(title):
# Define the roles and markers
# Define the roles and markers
prompt = prompt = f"[INST]Identify the brand from the given product title.[/INST]\n\n<TITL> {title} </TITL>\n\n"custom prompt here
print("Prompt:")
print(prompt)
encoding = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(input_ids=encoding.input_ids,
attention_mask=encoding.attention_mask,
max_new_tokens=200,
do_sample=True,
temperature=0.01,
eos_token_id=tokenizer.eos_token_id,
top_k=0)
print()
# Subtract the length of input_ids from output to get only the model's response
output_text = tokenizer.decode(output[0, len(encoding.input_ids[0]):], skip_special_tokens=False)
output_text = re.sub('\n+', '\n', output_text) # remove excessive newline characters
print("Generated Assistant Response:")
print(output_text)
return output_text |
1DS/adapter-review-phrases-sentiments-Llama-2-7b-chat-hf-v2.1 | 1DS | 2024-01-09T08:21:26Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null | 2024-01-09T08:21:25Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.3.dev0
|
s3nh/beberik-Lonepino-11B-GGUF | s3nh | 2024-01-09T08:19:46Z | 1 | 2 | transformers | [
"transformers",
"gguf",
"text-generation",
"zh",
"en",
"license:openrail",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T07:30:13Z |
---
license: openrail
pipeline_tag: text-generation
library_name: transformers
language:
- zh
- en
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGUF Format model files for [This project](https://huggingface.co/beberik/Lonepino-11B).
### GGUF Specs
GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:
Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information.
Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models.
mmap compatibility: models can be loaded using mmap for fast loading and saving.
Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used.
Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user.
The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values.
This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for
inference or for identifying the model.
### Perplexity params
Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16
7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066
13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543
### inference
TODO
# Original model card
|
satcos/Reinforce-CartPole-v1 | satcos | 2024-01-09T08:15:34Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-09T08:15:20Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
freshpearYoon/medium3 | freshpearYoon | 2024-01-09T08:03:25Z | 4 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ko",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-01-09T01:54:25Z | ---
language:
- ko
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper_medium
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper_medium
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the aihub dataset.
It achieves the following results on the evaluation set:
- Cer: 15.6625
- Loss: 1.4176
- Wer: 32.4788
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-07
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:-------:|:---------------:|:-------:|
| 1.8819 | 0.01 | 100 | 11.9999 | 1.5851 | 29.7754 |
| 1.6964 | 0.02 | 200 | 14.6066 | 1.4982 | 31.2945 |
| 1.6783 | 0.02 | 300 | 14.8315 | 1.4504 | 31.7318 |
| 1.6238 | 0.03 | 400 | 15.3631 | 1.4259 | 32.1490 |
| 1.7569 | 0.04 | 500 | 15.6625 | 1.4176 | 32.4788 |
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.15.0
- Tokenizers 0.15.0
|
azambasheer99/azam-spam-detector-v1 | azambasheer99 | 2024-01-09T07:56:46Z | 0 | 0 | null | [
"license:mit",
"region:us"
] | null | 2024-01-09T07:54:07Z | ---
license: mit
---
A spam detector model to detect spam messages. Outputs 0=Ham or 1=Spam. Currently test prototype model. |
isha-ingersol/llama2-qlora-finetuned-french | isha-ingersol | 2024-01-09T07:56:46Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:adapter:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2024-01-09T07:56:27Z | ---
library_name: peft
base_model: TinyPixel/Llama-2-7B-bf16-sharded
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0 |
baichuan-inc/Baichuan-13B-Chat | baichuan-inc | 2024-01-09T07:56:42Z | 3,287 | 631 | transformers | [
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"zh",
"en",
"arxiv:2104.09864",
"arxiv:2108.12409",
"arxiv:2009.03300",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-07-08T05:58:27Z | ---
language:
- zh
- en
pipeline_tag: text-generation
inference: false
---
# Baichuan-13B-Chat
<!-- Provide a quick summary of what the model is/does. -->
## 介绍
Baichuan-13B-Chat为Baichuan-13B系列模型中对齐后的版本,预训练模型可见[Baichuan-13B-Base](https://huggingface.co/baichuan-inc/Baichuan-13B-Base)。
[Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B) 是由百川智能继 [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B) 之后开发的包含 130 亿参数的开源可商用的大规模语言模型,在权威的中文和英文 benchmark 上均取得同尺寸最好的效果。本次发布包含有预训练 ([Baichuan-13B-Base](https://huggingface.co/baichuan-inc/Baichuan-13B-Base)) 和对齐 ([Baichuan-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan-13B-Chat)) 两个版本。Baichuan-13B 有如下几个特点:
1. **更大尺寸、更多数据**:Baichuan-13B 在 [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B) 的基础上进一步扩大参数量到 130 亿,并且在高质量的语料上训练了 1.4 万亿 tokens,超过 LLaMA-13B 40%,是当前开源 13B 尺寸下训练数据量最多的模型。支持中英双语,使用 ALiBi 位置编码,上下文窗口长度为 4096。
2. **同时开源预训练和对齐模型**:预训练模型是适用开发者的“基座”,而广大普通用户对有对话功能的对齐模型具有更强的需求。因此本次开源我们同时发布了对齐模型(Baichuan-13B-Chat),具有很强的对话能力,开箱即用,几行代码即可简单的部署。
3. **更高效的推理**:为了支持更广大用户的使用,我们本次同时开源了 int8 和 int4 的量化版本,相对非量化版本在几乎没有效果损失的情况下大大降低了部署的机器资源门槛,可以部署在如 Nvidia 3090 这样的消费级显卡上。
4. **开源免费可商用**:Baichuan-13B 不仅对学术研究完全开放,开发者也仅需邮件申请并获得官方商用许可后,即可以免费商用。
Baichuan-13B-Chat is the aligned version in the Baichuan-13B series of models, and the pre-trained model can be found at [Baichuan-13B-Base](https://huggingface.co/baichuan-inc/Baichuan-13B-Base).
[Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B) is an open-source, commercially usable large-scale language model developed by Baichuan Intelligence, following [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B). With 13 billion parameters, it achieves the best performance in standard Chinese and English benchmarks among models of its size. This release includes two versions: pre-training (Baichuan-13B-Base) and alignment (Baichuan-13B-Chat). Baichuan-13B has the following features:
1. **Larger size, more data**: Baichuan-13B further expands the parameter volume to 13 billion based on [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B), and has trained 1.4 trillion tokens on high-quality corpora, exceeding LLaMA-13B by 40%. It is currently the model with the most training data in the open-source 13B size. It supports both Chinese and English, uses ALiBi position encoding, and has a context window length of 4096.
2. **Open-source pre-training and alignment models simultaneously**: The pre-training model is a "base" suitable for developers, while the general public has a stronger demand for alignment models with dialogue capabilities. Therefore, in this open-source release, we also released the alignment model (Baichuan-13B-Chat), which has strong dialogue capabilities and is ready to use. It can be easily deployed with just a few lines of code.
3. **More efficient inference**: To support a wider range of users, we have open-sourced the INT8 and INT4 quantized versions. The model can be conveniently deployed on consumer GPUs like the Nvidia 3090 with almost no performance loss.
4. **Open-source, free, and commercially usable**: Baichuan-13B is not only fully open to academic research, but developers can also use it for free commercially after applying for and receiving official commercial permission via email.
## 使用方式
如下是一个使用Baichuan-13B-Chat进行对话的示例,正确输出为"乔戈里峰。世界第二高峰———乔戈里峰西方登山者称其为k2峰,海拔高度是8611米,位于喀喇昆仑山脉的中巴边境上"
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-13B-Chat", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", device_map="auto", torch_dtype=torch.float16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan-13B-Chat")
messages = []
messages.append({"role": "user", "content": "世界上第二高的山峰是哪座"})
response = model.chat(tokenizer, messages)
print(response)
```
Here is an example of a conversation using Baichuan-13B-Chat, the correct output is "K2. The world's second highest peak - K2, also known as Mount Godwin-Austen or Chhogori, with an altitude of 8611 meters, is located on the China-Pakistan border in the Karakoram Range."
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-13B-Chat", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", device_map="auto", torch_dtype=torch.float16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan-13B-Chat")
messages = []
messages.append({"role": "user", "content": "Which moutain is the second highest one in the world?"})
response = model.chat(tokenizer, messages)
print(response)
```
## 量化部署
Baichuan-13B 支持 int8 和 int4 量化,用户只需在推理代码中简单修改两行即可实现。请注意,如果是为了节省显存而进行量化,应加载原始精度模型到 CPU 后再开始量化;避免在 `from_pretrained` 时添加 `device_map='auto'` 或者其它会导致把原始精度模型直接加载到 GPU 的行为的参数。
Baichuan-13B supports int8 and int4 quantization, users only need to make a simple two-line change in the inference code to implement it. Please note, if quantization is done to save GPU memory, the original precision model should be loaded onto the CPU before starting quantization. Avoid adding parameters such as `device_map='auto'` or others that could cause the original precision model to be loaded directly onto the GPU when executing `from_pretrained`.
使用 int8 量化 (To use int8 quantization):
```python
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", torch_dtype=torch.float16, trust_remote_code=True)
model = model.quantize(8).cuda()
```
同样的,如需使用 int4 量化 (Similarly, to use int4 quantization):
```python
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", torch_dtype=torch.float16, trust_remote_code=True)
model = model.quantize(4).cuda()
```
## 模型详情
### 模型描述
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** 百川智能(Baichuan Intelligent Technology)
- **Email**: [email protected]
- **Language(s) (NLP):** Chinese/English
- **License:** 【Community License for Baichuan-13B Model】([ZH](Baichuan-13B%20模型社区许可协议.pdf)|
[EN](Community%20License%20for%20Baichuan-13B%20Model.pdf))
**商业用途(For commercial use):** 请通过 [Email](mailto:[email protected]) 联系申请书面授权。(Contact us via [Email](mailto:[email protected]) above to apply for written authorization.)
### 模型结构
<!-- Provide the basic links for the model. -->
整体模型基于Baichuan-7B,为了获得更好的推理性能,Baichuan-13B 使用了 ALiBi 线性偏置技术,相对于 Rotary Embedding 计算量更小,对推理性能有显著提升;与标准的 LLaMA-13B 相比,生成 2000 个 tokens 的平均推理速度 (tokens/s),实测提升 31.6%:
| Model | tokens/s |
|-------------|----------|
| LLaMA-13B | 19.4 |
| Baichuan-13B| 25.4 |
具体参数和见下表
| 模型名称 | 隐含层维度 | 层数 | 头数 |词表大小 | 总参数量 | 训练数据(tokens) | 位置编码 | 最大长度 |
|-------------------------|-------|------------|------------|-----------------|--------|--------|----------------|---------|
| Baichuan-7B | 4,096 | 32 | 32 | 64,000 | 7,000,559,616 | 1.2万亿 | [RoPE](https://arxiv.org/abs/2104.09864) | 4,096 |
| Baichuan-13B | 5,120 | 40 | 40 | 64,000 | 13,264,901,120 | 1.4万亿 | [ALiBi](https://arxiv.org/abs/2108.12409) | 4,096
The overall model is based on Baichuan-7B. In order to achieve better inference performance, Baichuan-13B uses ALiBi linear bias technology, which has a smaller computational load compared to Rotary Embedding, and significantly improves inference performance. Compared with the standard LLaMA-13B, the average inference speed (tokens/s) for generating 2000 tokens has been tested to increase by 31.6%:
| Model | tokens/s |
|-------------|----------|
| LLaMA-13B | 19.4 |
| Baichuan-13B| 25.4 |
The specific parameters are as follows:
| Model Name | Hidden Size | Num Layers | Num Attention Heads |Vocab Size | Total Params | Training Dats(tokens) | Position Embedding | Max Length |
|-------------------------|-------|------------|------------|-----------------|--------|--------|----------------|---------|
| Baichuan-7B | 4,096 | 32 | 32 | 64,000 | 7,000,559,616 | 1.2万亿 | [RoPE](https://arxiv.org/abs/2104.09864) | 4,096 |
| Baichuan-13B | 5,120 | 40 | 40 | 64,000 | 13,264,901,120 | 1.4万亿 | [ALiBi](https://arxiv.org/abs/2108.12409) | 4,096
## 使用须知
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### 免责声明
我们在此声明,我们的开发团队并未基于 Baichuan-13B 模型开发任何应用,无论是在 iOS、Android、网页或任何其他平台。我们强烈呼吁所有使用者,不要利用 Baichuan-13B 模型进行任何危害国家社会安全或违法的活动。另外,我们也要求使用者不要将 Baichuan-13B 模型用于未经适当安全审查和备案的互联网服务。我们希望所有的使用者都能遵守这个原则,确保科技的发展能在规范和合法的环境下进行。
我们已经尽我们所能,来确保模型训练过程中使用的数据的合规性。然而,尽管我们已经做出了巨大的努力,但由于模型和数据的复杂性,仍有可能存在一些无法预见的问题。因此,如果由于使用 Baichuan-13B 开源模型而导致的任何问题,包括但不限于数据安全问题、公共舆论风险,或模型被误导、滥用、传播或不当利用所带来的任何风险和问题,我们将不承担任何责任。
We hereby declare that our development team has not developed any applications based on the Baichuan-13B model, whether on iOS, Android, the web, or any other platform. We strongly urge all users not to use the Baichuan-13B model for any activities that harm national social security or are illegal. In addition, we also ask users not to use the Baichuan-13B model for internet services that have not undergone appropriate security review and filing. We hope that all users will adhere to this principle to ensure that technological development takes place in a regulated and legal environment.
We have done our utmost to ensure the compliance of the data used in the model training process. However, despite our great efforts, due to the complexity of the model and data, there may still be some unforeseen issues. Therefore, we will not take any responsibility for any issues arising from the use of the Baichuan-13B open-source model, including but not limited to data security issues, public opinion risks, or any risks and problems arising from the model being misled, misused, disseminated, or improperly exploited.
## 训练详情
训练具体设置参见[Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B)。
For specific training settings, please refer to [Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B).
## 测评结果
## [C-Eval](https://cevalbenchmark.com/index.html#home)
| Model 5-shot | STEM | Social Sciences | Humanities | Others | Average |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
| Baichuan-7B | 38.2 | 52.0 | 46.2 | 39.3 | 42.8 |
| Chinese-Alpaca-Plus-13B | 35.2 | 45.6 | 40.0 | 38.2 | 38.8 |
| Vicuna-13B | 30.5 | 38.2 | 32.5 | 32.5 | 32.8 |
| Chinese-LLaMA-Plus-13B | 30.3 | 38.0 | 32.9 | 29.1 | 32.1 |
| Ziya-LLaMA-13B-Pretrain | 27.6 | 34.4 | 32.0 | 28.6 | 30.0 |
| LLaMA-13B | 27.0 | 33.6 | 27.7 | 27.6 | 28.5 |
| moss-moon-003-base (16B)| 27.0 | 29.1 | 27.2 | 26.9 | 27.4 |
| **Baichuan-13B-Base** | **45.9** | **63.5** | **57.2** | **49.3** | **52.4** |
| **Baichuan-13B-Chat** | **43.7** | **64.6** | **56.2** | **49.2** | **51.5** |
## [MMLU](https://arxiv.org/abs/2009.03300)
| Model 5-shot | STEM | Social Sciences | Humanities | Others | Average |
|-------------------------|:-----:|:---------------:|:----------:|:------:|:-------:|
| Vicuna-13B | 40.4 | 60.5 | 49.5 | 58.4 | 52.0 |
| LLaMA-13B | 36.1 | 53.0 | 44.0 | 52.8 | 46.3 |
| Chinese-Alpaca-Plus-13B | 36.9 | 48.9 | 40.5 | 50.5 | 43.9 |
| Ziya-LLaMA-13B-Pretrain | 35.6 | 47.6 | 40.1 | 49.4 | 42.9 |
| Baichuan-7B | 35.6 | 48.9 | 38.4 | 48.1 | 42.3 |
| Chinese-LLaMA-Plus-13B | 33.1 | 42.8 | 37.0 | 44.6 | 39.2 |
| moss-moon-003-base (16B)| 22.4 | 22.8 | 24.2 | 24.4 | 23.6 |
| **Baichuan-13B-Base** | **41.6** | **60.9** | **47.4** | **58.5** | **51.6** |
| **Baichuan-13B-Chat** | **40.9** | **60.9** | **48.8** | **59.0** | **52.1** |
> 说明:我们采用了 MMLU 官方的[评测方案](https://github.com/hendrycks/test)。
## [CMMLU](https://github.com/haonan-li/CMMLU)
| Model 5-shot | STEM | Humanities | Social Sciences | Others | China Specific | Average |
|-------------------------|:-----:|:----------:|:---------------:|:------:|:--------------:|:-------:|
| Baichuan-7B | 34.4 | 47.5 | 47.6 | 46.6 | 44.3 | 44.0 |
| Vicuna-13B | 31.8 | 36.2 | 37.6 | 39.5 | 34.3 | 36.3 |
| Chinese-Alpaca-Plus-13B | 29.8 | 33.4 | 33.2 | 37.9 | 32.1 | 33.4 |
| Chinese-LLaMA-Plus-13B | 28.1 | 33.1 | 35.4 | 35.1 | 33.5 | 33.0 |
| Ziya-LLaMA-13B-Pretrain | 29.0 | 30.7 | 33.8 | 34.4 | 31.9 | 32.1 |
| LLaMA-13B | 29.2 | 30.8 | 31.6 | 33.0 | 30.5 | 31.2 |
| moss-moon-003-base (16B)| 27.2 | 30.4 | 28.8 | 32.6 | 28.7 | 29.6 |
| **Baichuan-13B-Base** | **41.7** | **61.1** | **59.8** | **59.0** | **56.4** | **55.3** |
| **Baichuan-13B-Chat** | **42.8** | **62.6** | **59.7** | **59.0** | **56.1** | **55.8** |
> 说明:CMMLU 是一个综合性的中文评估基准,专门用于评估语言模型在中文语境下的知识和推理能力。我们采用了其官方的[评测方案](https://github.com/haonan-li/CMMLU)。
## 微信群组

|
jamesm808/ppo-LunarLander-v2 | jamesm808 | 2024-01-09T07:52:01Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-01-07T09:02:45Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -154.64 +/- 53.16
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF | billborkowski | 2024-01-09T07:49:49Z | 2,919 | 22 | transformers | [
"transformers",
"pytorch",
"gguf",
"llava_mistral",
"text-generation",
"mistral",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"multimodal",
"llava",
"conversational",
"en",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:quantized:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-09T04:58:30Z | ---
base_model: mistralai/Mistral-7B-v0.1
tags:
- mistral
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
- multimodal
- llava
model-index:
- name: Nous-Hermes-2-Vision
results: []
license: apache-2.0
language:
- en
---
GGUF Quants by Twobob, Thanks to @jartine and @cmp-nct for the assists
It's vicuna ref: [here](https://github.com/qnguyen3/hermes-llava/blob/173b4ef441b5371c1e7d99da7a2e7c14c77ad12f/llava/conversation.py#L252)
Caveat emptor: There is still some kind of bug in the inference that is likely to get fixed upstream. Just FYI

# Nous-Hermes-2-Vision - Mistral 7B

*In the tapestry of Greek mythology, Hermes reigns as the eloquent Messenger of the Gods, a deity who deftly bridges the realms through the art of communication. It is in homage to this divine mediator that I name this advanced LLM "Hermes," a system crafted to navigate the complex intricacies of human discourse with celestial finesse.*
## Model description
Nous-Hermes-2-Vision stands as a pioneering Vision-Language Model, leveraging advancements from the renowned **OpenHermes-2.5-Mistral-7B** by teknium. This model incorporates two pivotal enhancements, setting it apart as a cutting-edge solution:
- **SigLIP-400M Integration**: Diverging from traditional approaches that rely on substantial 3B vision encoders, Nous-Hermes-2-Vision harnesses the formidable SigLIP-400M. This strategic choice not only streamlines the model's architecture, making it more lightweight, but also capitalizes on SigLIP's remarkable capabilities. The result? A remarkable boost in performance that defies conventional expectations.
- **Custom Dataset Enriched with Function Calling**: Our model's training data includes a unique feature – function calling. This distinctive addition transforms Nous-Hermes-2-Vision into a **Vision-Language Action Model**. Developers now have a versatile tool at their disposal, primed for crafting a myriad of ingenious automations.
This project is led by [qnguyen3](https://twitter.com/stablequan) and [teknium](https://twitter.com/Teknium1).
## Training
### Dataset
- 220K from **LVIS-INSTRUCT4V**
- 60K from **ShareGPT4V**
- 150K Private **Function Calling Data**
- 50K conversations from teknium's **OpenHermes-2.5**
## Usage
### Prompt Format
- Like other LLaVA's variants, this model uses Vicuna-V1 as its prompt template. Please refer to `conv_llava_v1` in [this file](https://github.com/qnguyen3/hermes-llava/blob/main/llava/conversation.py)
- For Gradio UI, please visit this [GitHub Repo](https://github.com/qnguyen3/hermes-llava)
### Function Calling
- For functiong calling, the message should start with a `<fn_call>` tag. Here is an example:
```json
<fn_call>{
"type": "object",
"properties": {
"bus_colors": {
"type": "array",
"description": "The colors of the bus in the image.",
"items": {
"type": "string",
"enum": ["red", "blue", "green", "white"]
}
},
"bus_features": {
"type": "string",
"description": "The features seen on the back of the bus."
},
"bus_location": {
"type": "string",
"description": "The location of the bus (driving or pulled off to the side).",
"enum": ["driving", "pulled off to the side"]
}
}
}
```
Output:
```json
{
"bus_colors": ["red", "white"],
"bus_features": "An advertisement",
"bus_location": "driving"
}
```
## Example
### Chat

### Function Calling
Input image:

Input message:
```json
<fn_call>{
"type": "object",
"properties": {
"food_list": {
"type": "array",
"description": "List of all the food",
"items": {
"type": "string",
}
},
}
}
```
Output:
```json
{
"food_list": [
"Double Burger",
"Cheeseburger",
"French Fries",
"Shakes",
"Coffee"
]
}
``` |
mlx-community/Llama-2-7b-WikiChat-mlx | mlx-community | 2024-01-09T07:49:22Z | 2 | 0 | mlx | [
"mlx",
"llama",
"en",
"license:llama2",
"region:us"
] | null | 2024-01-09T06:55:05Z | ---
language:
- en
license: llama2
tags:
- mlx
---
# Llama-2-7b-WikiChat-mlx
This model was converted to MLX format from [`stanford-oval/Llama-2-7b-WikiChat`]().
Refer to the [original model card](https://huggingface.co/stanford-oval/Llama-2-7b-WikiChat) for more details on the model.
## Use with mlx
```bash
pip install mlx
git clone https://github.com/ml-explore/mlx-examples.git
cd mlx-examples/llms/hf_llm
python generate.py --model mlx-community/Llama-2-7b-WikiChat-mlx --prompt "My name is"
```
|
baichuan-inc/Baichuan-7B | baichuan-inc | 2024-01-09T07:45:22Z | 19,658 | 839 | transformers | [
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"zh",
"en",
"arxiv:1910.07467",
"arxiv:2009.03300",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-13T07:47:16Z | ---
language:
- zh
- en
pipeline_tag: text-generation
inference: false
---
# Baichuan-7B
<!-- Provide a quick summary of what the model is/does. -->
Baichuan-7B是由百川智能开发的一个开源的大规模预训练模型。基于Transformer结构,在大约1.2万亿tokens上训练的70亿参数模型,支持中英双语,上下文窗口长度为4096。在标准的中文和英文权威benchmark(C-EVAL/MMLU)上均取得同尺寸最好的效果。
如果希望使用Baichuan-7B(如进行推理、Finetune等),我们推荐使用配套代码库[Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B)。
Baichuan-7B is an open-source large-scale pre-trained model developed by Baichuan Intelligent Technology. Based on the Transformer architecture, it is a model with 7 billion parameters trained on approximately 1.2 trillion tokens. It supports both Chinese and English, with a context window length of 4096. It achieves the best performance of its size on standard Chinese and English authoritative benchmarks (C-EVAL/MMLU).
If you wish to use Baichuan-7B (for inference, finetuning, etc.), we recommend using the accompanying code library [Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B).
## Why use Baichuan-7B
- 在同尺寸模型中Baichuan-7B达到了目前SOTA的水平,参考下面MMLU指标
- Baichuan-7B使用自有的中英文双语语料进行训练,在中文上进行优化,在C-Eval达到SOTA水平
- 不同于LLaMA完全禁止商业使用,Baichuan-7B使用更宽松的开源协议,允许用于商业目的
- Among models of the same size, Baichuan-7B has achieved the current state-of-the-art (SOTA) level, as evidenced by the following MMLU metrics.
- Baichuan-7B is trained on proprietary bilingual Chinese-English corpora, optimized for Chinese, and achieves SOTA performance on C-Eval.
- Unlike LLaMA, which completely prohibits commercial use, Baichuan-7B employs a more lenient open-source license, allowing for commercial purposes.
## How to Get Started with the Model
如下是一个使用Baichuan-7B进行1-shot推理的任务,根据作品给出作者名,正确输出为"夜雨寄北->李商隐"
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-7B", device_map="auto", trust_remote_code=True)
inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt')
inputs = inputs.to('cuda:0')
pred = model.generate(**inputs, max_new_tokens=64,repetition_penalty=1.1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```
The following is a task of performing 1-shot inference using Baichuan-7B, where the author's name is given based on the work, with the correct output being "One Hundred Years of Solitude->Gabriel Garcia Marquez"
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-7B", device_map="auto", trust_remote_code=True)
inputs = tokenizer('Hamlet->Shakespeare\nOne Hundred Years of Solitude->', return_tensors='pt')
inputs = inputs.to('cuda:0')
pred = model.generate(**inputs, max_new_tokens=64,repetition_penalty=1.1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** 百川智能(Baichuan Intelligent Technology)
- **Email**: [email protected]
- **Language(s) (NLP):** Chinese/English
- **License:** [Baichuan-7B License](https://huggingface.co/baichuan-inc/Baichuan-7B/blob/main/baichuan-7B%20%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)
### Model Sources
<!-- Provide the basic links for the model. -->
整体模型基于标准的Transformer结构,我们采用了和LLaMA一样的模型设计
- **Position Embedding**:采用rotary-embedding,是现阶段被大多数模型采用的位置编码方案,具有很好的外推性。
- **Feedforward Layer**:采用SwiGLU,Feedforward变化为(8/3)倍的隐含层大小,即11008。
- **Layer Normalization**: 基于[RMSNorm](https://arxiv.org/abs/1910.07467)的Pre-Normalization。
具体参数和见下表
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 7000559616 |
|n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 64000 |
| sequence length | 4096 |
The overall model is based on the standard Transformer structure, and we have adopted the same model design as LLaMA:
- Position Embedding: We use rotary-embedding, which is the position encoding scheme adopted by most models at this stage, and it has excellent extrapolation capabilities.
- Feedforward Layer: We use SwiGLU. The feedforward changes to (8/3) times the size of the hidden layer, that is, 11008.
- Layer Normalization: Pre-Normalization based on [RMSNorm](https://arxiv.org/abs/1910.07467).
The specific parameters are as follows:
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 7000559616 |
|n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 64000 |
| sequence length | 4096 |
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Downstream Use
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
我们同时开源出了和本模型配套的训练代码,允许进行高效的Finetune用于下游任务,具体参见[Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B)。
We have also open-sourced the training code that accompanies this model, allowing for efficient finetuning for downstream tasks. For more details, please refer to [Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B).
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
在没有充分评估风险和采取缓解措施的情况下投入生产使用;任何可能被视为不负责任或有害的使用案例。
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Baichuan-7B可能会产生事实上不正确的输出,不应依赖它产生事实上准确的信息。Baichuan-7B是在各种公共数据集上进行训练的。尽管我们已经做出了巨大的努力来清洗预训练数据,但这个模型可能会生成淫秽、偏见或其他冒犯性的输出。
Baichuan-7B can produce factually incorrect output, and should not be relied on to produce factually accurate information. Baichuan-7B was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Training Details
训练具体设置参见[Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B)。
For specific training settings, please refer to [Baichuan-7B](https://github.com/baichuan-inc/Baichuan-7B).
## Evaluation
### 中文评测
#### C-Eval
[CEval数据集](https://cevalbenchmark.com/index.html)是一个全面的中文基础模型评测数据集,涵盖了52个学科和四个难度的级别。我们使用该数据集的dev集作为few-shot的来源,在test集上进行了5-shot测试。
| Model 5-shot | Average | Avg(Hard) | STEM | Social Sciences | Humanities | Others |
|-----------------------------|---------|-----------|------|-----------------|------------|--------|
| GPT-4 | 68.7 | 54.9 | 67.1 | 77.6 | 64.5 | 67.8 |
| ChatGPT | 54.4 | 41.4 | 52.9 | 61.8 | 50.9 | 53.6 |
| Claude-v1.3 | 54.2 | 39.0 | 51.9 | 61.7 | 52.1 | 53.7 |
| Claude-instant-v1.0 | 45.9 | 35.5 | 43.1 | 53.8 | 44.2 | 45.4 |
| moss-moon-003-base (16B) | 27.4 | 24.5 | 27.0 | 29.1 | 27.2 | 26.9 |
| Ziya-LLaMA-13B-pretrain | 30.2 | 22.7 | 27.7 | 34.4 | 32.0 | 28.9 |
| LLaMA-7B-hf | 27.1 | 25.9 | 27.1 | 26.8 | 27.9 | 26.3 |
| ChatGLM-6B | 34.5 | 23.1 | 30.4 | 39.6 | 37.4 | 34.5 |
| Falcon-7B | 25.8 | 24.3 | 25.8 | 26.0 | 25.8 | 25.6 |
| Open-LLaMA-v2-pretrain (7B) | 24.0 | 22.5 | 23.1 | 25.3 | 25.2 | 23.2 |
| TigerBot-7B-base | 25.7 | 27.0 | 27.3 | 24.7 | 23.4 | 26.1 |
| Aquila-7B<sup>*</sup> | 25.5 | 25.2 | 25.6 | 24.6 | 25.2 | 26.6 |
| BLOOM-7B | 22.8 | 20.2 | 21.8 | 23.3 | 23.9 | 23.3 |
| BLOOMZ-7B | 35.7 | 25.8 | 31.3 | 43.5 | 36.6 | 35.6 |
| **Baichuan-7B** | 42.8 | 31.5 | 38.2 | 52.0 | 46.2 | 39.3 |
#### Gaokao
[Gaokao](https://github.com/ExpressAI/AI-Gaokao) 是一个以中国高考题作为评测大语言模型能力的数据集,用以评估模型的语言能力和逻辑推理能力。
我们只保留了其中的单项选择题,并对所有模型进行统一5-shot测试。
以下是测试的结果。
| Model | Average |
|-------------------------|-----------------|
| Open-LLaMA-v2-pretrain | 21.41 |
| Ziya-LLaMA-13B-pretrain | 23.17 |
| Falcon-7B | 23.98 |
| TigerBot-7B-base | 25.94 |
| LLaMA-7B | 27.81 |
| ChatGLM-6B | 21.41 |
| BLOOM-7B | 26.96 |
| BLOOMZ-7B | 28.72 |
| Aquila-7B<sup>*</sup> | 24.39 |
| **Baichuan-7B** | **36.24** |
#### AGIEval
[AGIEval](https://github.com/microsoft/AGIEval) 旨在评估模型的认知和解决问题相关的任务中的一般能力。
我们只保留了其中的四选一单项选择题,随机划分后对所有模型进行了统一5-shot测试。
| Model | Average |
|-------------------------|-----------------|
| Open-LLaMA-v2-pretrain | 23.49 |
| Ziya-LLaMA-13B-pretrain | 27.64 |
| Falcon-7B | 27.18 |
| TigerBot-7B-base | 25.19 |
| LLaMA-7B | 28.17 |
| ChatGLM-6B | 23.49 |
| BLOOM-7B | 26.55 |
| BLOOMZ-7B | 30.27 |
| Aquila-7B<sup>*</sup> | 25.58 |
| **Baichuan-7B** | **34.44** |
<sup>*</sup>其中Aquila模型来源于[智源官方网站](https://model.baai.ac.cn/model-detail/100098),仅做参考
### English Leaderboard
In addition to Chinese, we also tested the model's performance in English.
#### MMLU
[MMLU](https://arxiv.org/abs/2009.03300) is an English evaluation dataset that includes 57 multiple-choice tasks, covering elementary mathematics, American history, computer science, law, etc. The difficulty ranges from high school level to expert level, making it a mainstream LLM evaluation dataset.
We adopted the [open-source]((https://github.com/hendrycks/test)) evaluation scheme, and the final 5-shot results are as follows:
| Model | Humanities | Social Sciences | STEM | Other | Average |
|----------------------------------------|-----------:|:---------------:|:----:|:-----:|:-------:|
| LLaMA-7B<sup>2</sup> | 34.0 | 38.3 | 30.5 | 38.1 | 35.1 |
| Falcon-7B<sup>1</sup> | - | - | - | - | 35.0 |
| mpt-7B<sup>1</sup> | - | - | - | - | 35.6 |
| ChatGLM-6B<sup>0</sup> | 35.4 | 41.0 | 31.3 | 40.5 | 36.9 |
| BLOOM 7B<sup>0</sup> | 25.0 | 24.4 | 26.5 | 26.4 | 25.5 |
| BLOOMZ 7B<sup>0</sup> | 31.3 | 42.1 | 34.4 | 39.0 | 36.1 |
| moss-moon-003-base (16B)<sup>0</sup> | 24.2 | 22.8 | 22.4 | 24.4 | 23.6 |
| moss-moon-003-sft (16B)<sup>0</sup> | 30.5 | 33.8 | 29.3 | 34.4 | 31.9 |
| **Baichuan-7B<sup>0</sup>** | 38.4 | 48.9 | 35.6 | 48.1 | 42.3 |
The superscript in the Model column indicates the source of the results.
```
0:reimplemented
1:https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
2:https://paperswithcode.com/sota/multi-task-language-understanding-on-mmlu
```
## Our Group

|
kwaikeg/kagentlms_qwen_7b_mat | kwaikeg | 2024-01-09T07:45:10Z | 42 | 15 | transformers | [
"transformers",
"pytorch",
"qwen",
"feature-extraction",
"text-generation",
"custom_code",
"en",
"zh",
"dataset:kwaikeg/KAgentInstruct",
"dataset:kwaikeg/KAgentBench",
"license:cc-by-nc-nd-4.0",
"region:us"
] | text-generation | 2023-11-17T06:24:12Z | ---
license: cc-by-nc-nd-4.0
datasets:
- kwaikeg/KAgentInstruct
- kwaikeg/KAgentBench
language:
- en
- zh
pipeline_tag: text-generation
---
KwaiAgents ([Github](https://github.com/KwaiKEG/KwaiAgents)) is a series of Agent-related works open-sourced by the [KwaiKEG](https://github.com/KwaiKEG) from [Kuaishou Technology](https://www.kuaishou.com/en). The open-sourced content includes:
1. **KAgentSys-Lite**: An experimental Agent Loop implemented based on open-source search engines, browsers, time, calendar, weather, and other tools, which is only missing the memory mechanism and some search capabilities compared to the system in the paper.
2. **KAgentLMs**: A series of large language models with Agent capabilities such as planning, reflection, and tool-use, acquired through the Meta-agent tuning proposed in the paper.
3. **KAgentInstruct**: Fine-tuned data of instructions generated by the Meta-agent in the paper.
4. **KAgentBench**: Over 3,000 human-edited, automated evaluation data for testing Agent capabilities, with evaluation dimensions including planning, tool-use, reflection, concluding, and profiling.
## User Guide
### Direct usage
Tutorial can refer to [QwenLM/Qwen](https://github.com/QwenLM/Qwen)
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("kwaikeg/kagentlms_qwen_7b_mat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
"kwaikeg/kagentlms_qwen_7b_mat",
device_map="auto",
trust_remote_code=True
).eval()
response, history = model.chat(tokenizer, "你好", history=None)
print(response)
```
### AgentLMs as service
#### Serving by [vLLM](https://github.com/vllm-project/vllm) (GPU)
We recommend using [vLLM](https://github.com/vllm-project/vllm) and [FastChat](https://github.com/lm-sys/FastChat) to deploy the model inference service. First, you need to install the corresponding packages (for detailed usage, please refer to the documentation of the two projects):
```bash
pip install vllm
pip install "fschat[model_worker,webui]"
```
To deploy KAgentLMs, you first need to start the controller in one terminal.
```bash
python -m fastchat.serve.controller
```
Secondly, you should use the following command in another terminal for single-gpu inference service deployment:
```bash
python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code
```
Where `$model_path` is the local path of the model downloaded. If the GPU does not support Bfloat16, you can add `--dtype half` to the command line.
Thirdly, start the REST API server in the third terminal.
```bash
python -m fastchat.serve.openai_api_server --host localhost --port 8888
```
Finally, you can use the curl command to invoke the model same as the OpenAI calling format. Here's an example:
```bash
curl http://localhost:8888/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "kagentlms_qwen_7b_mat", "messages": [{"role": "user", "content": "Who is Andy Lau"}]}'
```
#### Serving by [Lamma.cpp](https://github.com/ggerganov/llama.cpp) (CPU)
llama-cpp-python offers a web server which aims to act as a drop-in replacement for the OpenAI API. This allows you to use llama.cpp compatible models with any OpenAI compatible client (language libraries, services, etc). The converted model can be found in [kwaikeg/kagentlms_qwen_7b_mat_gguf](https://huggingface.co/kwaikeg/kagentlms_qwen_7b_mat_gguf).
To install the server package and get started:
```bash
pip install "llama-cpp-python[server]"
python3 -m llama_cpp.server --model kagentlms_qwen_7b_mat_gguf/ggml-model-q4_0.gguf --chat_format chatml --port 8888
```
### Citation
```
@article{pan2023kwaiagents,
author = {Haojie Pan and
Zepeng Zhai and
Hao Yuan and
Yaojia Lv and
Ruiji Fu and
Ming Liu and
Zhongyuan Wang and
Bing Qin
},
title = {KwaiAgents: Generalized Information-seeking Agent System with Large Language Models},
journal = {CoRR},
volume = {abs/2312.04889},
year = {2023}
}
``` |
LI-ST/Mistral-7B-ko-v0.005 | LI-ST | 2024-01-09T07:36:16Z | 39 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"ko",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-01-08T10:22:04Z | ---
license: cc-by-nc-nd-4.0
language:
- en
- ko
library_name: transformers
pipeline_tag: text-generation
---
<p><h1>Mistral-7B-ko</h1></p>
basemodel: Open-Orca/Mistral-7B-OpenOrca
=================================================
<BR>
This model is a temporary model for testing.
<BR>
We will be deleting it soon.
<BR>
================================================= |
zxhezexin/openlrm-large-obj-1.0 | zxhezexin | 2024-01-09T07:32:56Z | 7 | 5 | transformers | [
"transformers",
"image-to-3d",
"dataset:allenai/objaverse",
"arxiv:2311.04400",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | image-to-3d | 2024-01-09T05:59:51Z | ---
license: cc-by-nc-4.0
datasets:
- allenai/objaverse
pipeline_tag: image-to-3d
---
# Model Card for OpenLRM
## Overview
This model card is for the [OpenLRM](https://github.com/3DTopia/OpenLRM) project, which is an open-source implementation of the paper [LRM](https://arxiv.org/abs/2311.04400).
## Model Details
| Model | Training Data | Layers | Feat. Dim | Trip. Dim. | Render Res. | Link |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| openlrm-small-obj-1.0 | Objaverse | 12 | 768 | 32 | 192 | [HF](https://huggingface.co/zxhezexin/openlrm-small-obj-1.0) |
| openlrm-base-obj-1.0 | Objaverse | 12 | 1024 | 40 | 192 | [HF](https://huggingface.co/zxhezexin/openlrm-base-obj-1.0) |
| openlrm-large-obj-1.0 | Objaverse | 16 | 1024 | 80 | 384 | [HF](https://huggingface.co/zxhezexin/openlrm-large-obj-1.0) |
| openlrm-small | Objaverse + MVImgNet | 12 | 768 | 32 | 192 | To be released |
| openlrm-base | Objaverse + MVImgNet | 12 | 1024 | 40 | 192 | To be released |
| openlrm-large | Objaverse + MVImgNet | 16 | 1024 | 80 | 384 | To be released |
## Differences from the Original Paper
- We do not use the deferred back-propagation technique in the original paper.
- The triplane decoder contains 4 layers in our implementation.
## License
- The model weights are released under the [Creative Commons Attribution-NonCommercial 4.0 International License](LICENSE_WEIGHT).
- They are provided for research purposes only, and CANNOT be used commercially.
## Disclaimer
This model is an open-source implementation and is NOT the official release of the original research paper. While it aims to reproduce the original results as faithfully as possible, there may be variations due to model implementation, training data, and other factors.
### Ethical Considerations
- This model should be used responsibly and ethically, and should not be used for malicious purposes.
- Users should be aware of potential biases in the training data.
- The model should not be used under the circumstances that could lead to harm or unfair treatment of individuals or groups.
### Usage Considerations
- The model is provided "as is" without warranty of any kind.
- Users are responsible for ensuring that their use complies with all relevant laws and regulations.
- The developers and contributors of this model are not liable for any damages or losses arising from the use of this model.
---
*This model card is subject to updates and modifications. Users are advised to check for the latest version regularly.*
|
zxhezexin/openlrm-small-obj-1.0 | zxhezexin | 2024-01-09T07:32:35Z | 41 | 6 | transformers | [
"transformers",
"image-to-3d",
"dataset:allenai/objaverse",
"arxiv:2311.04400",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | image-to-3d | 2024-01-09T05:56:48Z | ---
license: cc-by-nc-4.0
datasets:
- allenai/objaverse
pipeline_tag: image-to-3d
---
# Model Card for OpenLRM
## Overview
This model card is for the [OpenLRM](https://github.com/3DTopia/OpenLRM) project, which is an open-source implementation of the paper [LRM](https://arxiv.org/abs/2311.04400).
## Model Details
| Model | Training Data | Layers | Feat. Dim | Trip. Dim. | Render Res. | Link |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| openlrm-small-obj-1.0 | Objaverse | 12 | 768 | 32 | 192 | [HF](https://huggingface.co/zxhezexin/openlrm-small-obj-1.0) |
| openlrm-base-obj-1.0 | Objaverse | 12 | 1024 | 40 | 192 | [HF](https://huggingface.co/zxhezexin/openlrm-base-obj-1.0) |
| openlrm-large-obj-1.0 | Objaverse | 16 | 1024 | 80 | 384 | [HF](https://huggingface.co/zxhezexin/openlrm-large-obj-1.0) |
| openlrm-small | Objaverse + MVImgNet | 12 | 768 | 32 | 192 | To be released |
| openlrm-base | Objaverse + MVImgNet | 12 | 1024 | 40 | 192 | To be released |
| openlrm-large | Objaverse + MVImgNet | 16 | 1024 | 80 | 384 | To be released |
## Differences from the Original Paper
- We do not use the deferred back-propagation technique in the original paper.
- The triplane decoder contains 4 layers in our implementation.
## License
- The model weights are released under the [Creative Commons Attribution-NonCommercial 4.0 International License](LICENSE_WEIGHT).
- They are provided for research purposes only, and CANNOT be used commercially.
## Disclaimer
This model is an open-source implementation and is NOT the official release of the original research paper. While it aims to reproduce the original results as faithfully as possible, there may be variations due to model implementation, training data, and other factors.
### Ethical Considerations
- This model should be used responsibly and ethically, and should not be used for malicious purposes.
- Users should be aware of potential biases in the training data.
- The model should not be used under the circumstances that could lead to harm or unfair treatment of individuals or groups.
### Usage Considerations
- The model is provided "as is" without warranty of any kind.
- Users are responsible for ensuring that their use complies with all relevant laws and regulations.
- The developers and contributors of this model are not liable for any damages or losses arising from the use of this model.
---
*This model card is subject to updates and modifications. Users are advised to check for the latest version regularly.*
|
ProjectsbyGaurav/donut-base-gaurav-receipt-epoch-5 | ProjectsbyGaurav | 2024-01-09T07:28:52Z | 36 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:podbilabs/wildreceipt-donut",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-01-09T05:50:46Z | ---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- podbilabs/wildreceipt-donut
model-index:
- name: donut-base-gaurav-receipt-epoch-5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-gaurav-receipt-epoch-5
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Subsets and Splits