modelId
string | author
string | last_modified
timestamp[us, tz=UTC] | downloads
int64 | likes
int64 | library_name
string | tags
sequence | pipeline_tag
string | createdAt
timestamp[us, tz=UTC] | card
string |
|---|---|---|---|---|---|---|---|---|---|
DavidAU/TinyDolphin-2.8-1.1b-Q8_0-GGUF | DavidAU | 2024-04-20T08:42:32Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:teknium/openhermes",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T08:42:25Z | ---
language:
- en
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- teknium/openhermes
---
# DavidAU/TinyDolphin-2.8-1.1b-Q8_0-GGUF
This model was converted to GGUF format from [`cognitivecomputations/TinyDolphin-2.8-1.1b`](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyDolphin-2.8-1.1b-Q8_0-GGUF --model tinydolphin-2.8-1.1b.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyDolphin-2.8-1.1b-Q8_0-GGUF --model tinydolphin-2.8-1.1b.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinydolphin-2.8-1.1b.Q8_0.gguf -n 128
```
|
DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k-Q8_0-GGUF | DavidAU | 2024-04-20T08:41:39Z | 2 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"pt",
"en",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-17T03:22:24Z | ---
language:
- pt
- en
license: mit
tags:
- llama-cpp
- gguf-my-repo
pipeline_tag: text-generation
widget:
- text: "Below is an instruction that describes a task, paired with an input that\
\ provides further context. Write a response that appropriately completes the\
\ request.\n\n### Instruction: \nSua instrução aqui\n\n### Response:\n"
---
# DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k-Q8_0-GGUF
This model was converted to GGUF format from [`cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k`](https://huggingface.co/cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k-Q8_0-GGUF --model tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v3-8k.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v3-8k-Q8_0-GGUF --model tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v3-8k.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v3-8k.Q8_0.gguf -n 128
```
|
DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2-Q8_0-GGUF | DavidAU | 2024-04-20T08:41:28Z | 3 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"pt",
"en",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-17T03:22:09Z | ---
language:
- pt
- en
license: mit
tags:
- llama-cpp
- gguf-my-repo
pipeline_tag: text-generation
---
# DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2-Q8_0-GGUF
This model was converted to GGUF format from [`cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2`](https://huggingface.co/cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/cnmoro/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2-Q8_0-GGUF --model tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v2.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-1.1B-intermediate-1.5T-PTBR-Instruct-v2-Q8_0-GGUF --model tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v2.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-1.1b-intermediate-1.5t-ptbr-instruct-v2.Q8_0.gguf -n 128
```
|
DavidAU/TinyLlama-3T-1.1bee-Q8_0-GGUF | DavidAU | 2024-04-20T08:40:53Z | 0 | 0 | null | [
"gguf",
"bees",
"bzz",
"honey",
"oprah winfrey",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"dataset:BEE-spoke-data/bees-internal",
"base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
"base_model:quantized:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T08:40:46Z | ---
language:
- en
license: apache-2.0
tags:
- bees
- bzz
- honey
- oprah winfrey
- llama-cpp
- gguf-my-repo
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
datasets:
- BEE-spoke-data/bees-internal
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
renormalize_logits: true
repetition_penalty: 1.05
no_repeat_ngram_size: 6
temperature: 0.9
top_p: 0.95
epsilon_cutoff: 0.0008
widget:
- text: In beekeeping, the term "queen excluder" refers to
example_title: Queen Excluder
- text: One way to encourage a honey bee colony to produce more honey is by
example_title: Increasing Honey Production
- text: The lifecycle of a worker bee consists of several stages, starting with
example_title: Lifecycle of a Worker Bee
- text: Varroa destructor is a type of mite that
example_title: Varroa Destructor
- text: In the world of beekeeping, the acronym PPE stands for
example_title: Beekeeping PPE
- text: The term "robbing" in beekeeping refers to the act of
example_title: Robbing in Beekeeping
- text: 'Question: What''s the primary function of drone bees in a hive?
Answer:'
example_title: Role of Drone Bees
- text: To harvest honey from a hive, beekeepers often use a device known as a
example_title: Honey Harvesting Device
- text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide
to split the hive into two. Assuming each hive now produces at a 70% rate compared
to before, how much honey will you get from both hives next year?
To calculate'
example_title: Beekeeping Math Problem
- text: In beekeeping, "swarming" is the process where
example_title: Swarming
pipeline_tag: text-generation
model-index:
- name: TinyLlama-3T-1.1bee
results:
- 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
value: 33.79
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
- 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
value: 60.29
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
- 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
value: 25.86
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
- 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: 38.13
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
- 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
value: 60.22
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
- 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
value: 0.45
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
name: Open LLM Leaderboard
---
# DavidAU/TinyLlama-3T-1.1bee-Q8_0-GGUF
This model was converted to GGUF format from [`BEE-spoke-data/TinyLlama-3T-1.1bee`](https://huggingface.co/BEE-spoke-data/TinyLlama-3T-1.1bee) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/BEE-spoke-data/TinyLlama-3T-1.1bee) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-3T-1.1bee-Q8_0-GGUF --model tinyllama-3t-1.1bee.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-3T-1.1bee-Q8_0-GGUF --model tinyllama-3t-1.1bee.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-3t-1.1bee.Q8_0.gguf -n 128
```
|
DavidAU/TinyLlama-1.1bee-Q8_0-GGUF | DavidAU | 2024-04-20T08:40:38Z | 3 | 0 | null | [
"gguf",
"bees",
"beekeeping",
"honey",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"dataset:BEE-spoke-data/bees-internal",
"base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-240k-503b",
"base_model:quantized:TinyLlama/TinyLlama-1.1B-intermediate-step-240k-503b",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T08:40:20Z | ---
language:
- en
license: apache-2.0
tags:
- bees
- beekeeping
- honey
- llama-cpp
- gguf-my-repo
base_model: PY007/TinyLlama-1.1B-intermediate-step-240k-503b
datasets:
- BEE-spoke-data/bees-internal
metrics:
- accuracy
inference:
parameters:
max_new_tokens: 64
do_sample: true
renormalize_logits: true
repetition_penalty: 1.05
no_repeat_ngram_size: 6
temperature: 0.9
top_p: 0.95
epsilon_cutoff: 0.0008
widget:
- text: In beekeeping, the term "queen excluder" refers to
example_title: Queen Excluder
- text: One way to encourage a honey bee colony to produce more honey is by
example_title: Increasing Honey Production
- text: The lifecycle of a worker bee consists of several stages, starting with
example_title: Lifecycle of a Worker Bee
- text: Varroa destructor is a type of mite that
example_title: Varroa Destructor
- text: In the world of beekeeping, the acronym PPE stands for
example_title: Beekeeping PPE
- text: The term "robbing" in beekeeping refers to the act of
example_title: Robbing in Beekeeping
- text: 'Question: What''s the primary function of drone bees in a hive?
Answer:'
example_title: Role of Drone Bees
- text: To harvest honey from a hive, beekeepers often use a device known as a
example_title: Honey Harvesting Device
- text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide
to split the hive into two. Assuming each hive now produces at a 70% rate compared
to before, how much honey will you get from both hives next year?
To calculate'
example_title: Beekeeping Math Problem
- text: In beekeeping, "swarming" is the process where
example_title: Swarming
pipeline_tag: text-generation
---
# DavidAU/TinyLlama-1.1bee-Q8_0-GGUF
This model was converted to GGUF format from [`BEE-spoke-data/TinyLlama-1.1bee`](https://huggingface.co/BEE-spoke-data/TinyLlama-1.1bee) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/BEE-spoke-data/TinyLlama-1.1bee) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-1.1bee-Q8_0-GGUF --model tinyllama-1.1bee.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-1.1bee-Q8_0-GGUF --model tinyllama-1.1bee.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-1.1bee.Q8_0.gguf -n 128
```
|
UnderstandLing/Llama-3-8B-Instruct-ru | UnderstandLing | 2024-04-20T08:38:32Z | 30 | 1 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-04-20T07:22:07Z | ---
library_name: peft
base_model: meta-llama/Meta-Llama-3-8B-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]
## 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: float16
### Framework versions
- PEFT 0.6.2
|
mayankkeshari/distilbert-base-uncased-finetuned-emotions-dataset-wt | mayankkeshari | 2024-04-20T08:37:47Z | 83 | 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 | 2024-04-20T08:00:16Z | ---
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-emotions-dataset-wt
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: 0.8825
- name: F1
type: f1
value: 0.8835873403990151
---
<!-- 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-emotions-dataset-wt
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: 0.4135
- Accuracy: 0.8825
- F1: 0.8836
## 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: 128
- eval_batch_size: 128
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 1.2102 | 1.0 | 125 | 0.6386 | 0.792 | 0.7790 |
| 0.4984 | 2.0 | 250 | 0.4135 | 0.8825 | 0.8836 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
DavidAU/TinyLlama-1.1B-Chat-v1.0-reasoning-v2-Q8_0-GGUF | DavidAU | 2024-04-20T08:31:55Z | 2 | 0 | null | [
"gguf",
"trl",
"sft",
"generated_from_trainer",
"llama-cpp",
"gguf-my-repo",
"dataset:generator",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:quantized:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-04-20T08:31:50Z | ---
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
- llama-cpp
- gguf-my-repo
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
datasets:
- generator
model-index:
- name: TinyLlama-1.1B-Chat-v1.0-reasoning-v2
results: []
---
# DavidAU/TinyLlama-1.1B-Chat-v1.0-reasoning-v2-Q8_0-GGUF
This model was converted to GGUF format from [`alexredna/TinyLlama-1.1B-Chat-v1.0-reasoning-v2`](https://huggingface.co/alexredna/TinyLlama-1.1B-Chat-v1.0-reasoning-v2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/alexredna/TinyLlama-1.1B-Chat-v1.0-reasoning-v2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-1.1B-Chat-v1.0-reasoning-v2-Q8_0-GGUF --model tinyllama-1.1b-chat-v1.0-reasoning-v2.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-1.1B-Chat-v1.0-reasoning-v2-Q8_0-GGUF --model tinyllama-1.1b-chat-v1.0-reasoning-v2.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-1.1b-chat-v1.0-reasoning-v2.Q8_0.gguf -n 128
```
|
DavidAU/Tiny-Llama-2.2B-slerpx2-Q8_0-GGUF | DavidAU | 2024-04-20T08:31:41Z | 5 | 0 | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"Chuanming/Tiny-Llama-2.2B-slerp",
"llama-cpp",
"gguf-my-repo",
"base_model:Chuanming/Tiny-Llama-2.2B-slerp",
"base_model:quantized:Chuanming/Tiny-Llama-2.2B-slerp",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-04-15T01:19:35Z | ---
tags:
- merge
- mergekit
- lazymergekit
- Chuanming/Tiny-Llama-2.2B-slerp
- llama-cpp
- gguf-my-repo
base_model:
- Chuanming/Tiny-Llama-2.2B-slerp
- Chuanming/Tiny-Llama-2.2B-slerp
---
# DavidAU/Tiny-Llama-2.2B-slerpx2-Q8_0-GGUF
This model was converted to GGUF format from [`aipib/Tiny-Llama-2.2B-slerpx2`](https://huggingface.co/aipib/Tiny-Llama-2.2B-slerpx2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/aipib/Tiny-Llama-2.2B-slerpx2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/Tiny-Llama-2.2B-slerpx2-Q8_0-GGUF --model tiny-llama-2.2b-slerpx2.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Tiny-Llama-2.2B-slerpx2-Q8_0-GGUF --model tiny-llama-2.2b-slerpx2.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tiny-llama-2.2b-slerpx2.Q8_0.gguf -n 128
```
|
DavidAU/karasu-1.1B-slerpx2-Q8_0-GGUF | DavidAU | 2024-04-20T08:30:47Z | 4 | 0 | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"lightblue/karasu-1.1B",
"aipib/karasu-1.1B-slerp_reverse",
"llama-cpp",
"gguf-my-repo",
"base_model:aipib/karasu-1.1B-slerp_reverse",
"base_model:merge:aipib/karasu-1.1B-slerp_reverse",
"base_model:lightblue/karasu-1.1B",
"base_model:merge:lightblue/karasu-1.1B",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T08:30:41Z | ---
tags:
- merge
- mergekit
- lazymergekit
- lightblue/karasu-1.1B
- aipib/karasu-1.1B-slerp_reverse
- llama-cpp
- gguf-my-repo
base_model:
- lightblue/karasu-1.1B
- aipib/karasu-1.1B-slerp_reverse
---
# DavidAU/karasu-1.1B-slerpx2-Q8_0-GGUF
This model was converted to GGUF format from [`aipib/karasu-1.1B-slerpx2`](https://huggingface.co/aipib/karasu-1.1B-slerpx2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/aipib/karasu-1.1B-slerpx2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/karasu-1.1B-slerpx2-Q8_0-GGUF --model karasu-1.1b-slerpx2.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/karasu-1.1B-slerpx2-Q8_0-GGUF --model karasu-1.1b-slerpx2.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m karasu-1.1b-slerpx2.Q8_0.gguf -n 128
```
|
DavidAU/karasu-1.1B-slerp_reverse-Q8_0-GGUF | DavidAU | 2024-04-20T08:29:17Z | 3 | 0 | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"lightblue/karasu-1.1B",
"niryuu/Karasu-1.1b-chat-vector",
"llama-cpp",
"gguf-my-repo",
"base_model:lightblue/karasu-1.1B",
"base_model:merge:lightblue/karasu-1.1B",
"base_model:niryuu/Karasu-1.1b-chat-vector",
"base_model:merge:niryuu/Karasu-1.1b-chat-vector",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T08:29:11Z | ---
tags:
- merge
- mergekit
- lazymergekit
- lightblue/karasu-1.1B
- niryuu/Karasu-1.1b-chat-vector
- llama-cpp
- gguf-my-repo
base_model:
- lightblue/karasu-1.1B
- niryuu/Karasu-1.1b-chat-vector
---
# DavidAU/karasu-1.1B-slerp_reverse-Q8_0-GGUF
This model was converted to GGUF format from [`aipib/karasu-1.1B-slerp_reverse`](https://huggingface.co/aipib/karasu-1.1B-slerp_reverse) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/aipib/karasu-1.1B-slerp_reverse) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/karasu-1.1B-slerp_reverse-Q8_0-GGUF --model karasu-1.1b-slerp_reverse.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/karasu-1.1B-slerp_reverse-Q8_0-GGUF --model karasu-1.1b-slerp_reverse.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m karasu-1.1b-slerp_reverse.Q8_0.gguf -n 128
```
|
Azure99/blossom-v5-llama3-8b | Azure99 | 2024-04-20T08:27:23Z | 160 | 4 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"zh",
"en",
"dataset:Azure99/blossom-chat-v3",
"dataset:Azure99/blossom-math-v4",
"dataset:Azure99/blossom-wizard-v3",
"dataset:Azure99/blossom-orca-v3",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T06:28:48Z | ---
license: apache-2.0
datasets:
- Azure99/blossom-chat-v3
- Azure99/blossom-math-v4
- Azure99/blossom-wizard-v3
- Azure99/blossom-orca-v3
language:
- zh
- en
---
# **BLOSSOM-v5-llama3-8b**
[💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)
### What's new?
The Blossom V5 series models is fully trained using high-quality data distilled from gpt-4-0125-preview, resulting in significant improvements.
### Introduction
Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Meta-Llama-3-8B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source.
Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs.
### Inference
Inference is performed in the form of dialogue continuation.
Single-turn dialogue
```
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|:
```
Multi-turn dialogue
```
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|: Hello! How can I assist you today?<|end_of_text|>
|Human|: Generate a random number using python
|Bot|:
```
Note: At the end of the Bot's output in the historical conversation, append a `<|end_of_text|>`. |
maviced/mbart-samsum | maviced | 2024-04-20T08:10:05Z | 4 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"simplification",
"generated_from_trainer",
"base_model:facebook/mbart-large-50",
"base_model:finetune:facebook/mbart-large-50",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-20T06:40:10Z | ---
license: mit
base_model: facebook/mbart-large-50
tags:
- simplification
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-samsum
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. -->
# mbart-samsum
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2023
- Bleu: 8.9056
- Gen Len: 21.9792
## 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: 5.6e-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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log | 1.0 | 188 | 2.6051 | 5.5269 | 22.8339 |
| No log | 2.0 | 376 | 2.2023 | 8.9056 | 21.9792 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
siddharth-magesh/mistral-finetuned-samsum | siddharth-magesh | 2024-04-20T08:07:45Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"base_model:adapter:TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T07:25:56Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
model-index:
- name: mistral-finetuned-samsum
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-finetuned-samsum
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 |
sudhanshusinghaiml/flan-t5-base-airline-sentiment-analysis | sudhanshusinghaiml | 2024-04-20T08:07:09Z | 105 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-base",
"base_model:finetune:google/flan-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-20T07:49:35Z | ---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: flan-t5-base-airline-sentiment-analysis
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. -->
# flan-t5-base-airline-sentiment-analysis
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1600
- F1: 81.2771
- Gen Len: 2.8311
## 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: 0.0003
- 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: 2
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
UnderstandLing/Llama-3-8B-Instruct-pt | UnderstandLing | 2024-04-20T08:04:43Z | 2 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-04-20T07:16:24Z | ---
library_name: peft
base_model: meta-llama/Meta-Llama-3-8B-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]
## 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: float16
### Framework versions
- PEFT 0.6.2
|
blockblockblock/Copus-2x8B-bpw4.6 | blockblockblock | 2024-04-20T08:04:42Z | 3 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"exl2",
"region:us"
] | text-generation | 2024-04-20T08:01:30Z | ---
license: llama2
---
<img src=https://huggingface.co/lodrick-the-lafted/Copus-2x8B/resolve/main/copus.png>
MoE'd up:
- [dreamgen/opus-v1.2-llama-3-8b](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b)
- [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. |
hi000000/insta_chai-llama3_80 | hi000000 | 2024-04-20T08:04:25Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T08:04:23Z | ---
library_name: transformers
tags: []
---
# 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] |
AJosh/G-22-2 | AJosh | 2024-04-20T07:56:34Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T07:55:48Z | ---
library_name: transformers
tags: []
---
# 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] |
ltuzova/pretrain_tapt_unipelt_adpater_fix_train | ltuzova | 2024-04-20T07:54:11Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset",
"region:us"
] | null | 2024-04-20T07:54:05Z | ---
tags:
- roberta
- adapter-transformers
datasets:
- BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset
---
# Adapter `ltuzova/pretrain_tapt_unipelt_adpater_fix_train` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset/) dataset and includes a prediction head for masked lm.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("ltuzova/pretrain_tapt_unipelt_adpater_fix_train", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
jartine/phi-2-llamafile | jartine | 2024-04-20T07:54:08Z | 591 | 18 | transformers | [
"transformers",
"llamafile",
"phi-msft",
"nlp",
"code",
"text-generation",
"en",
"base_model:microsoft/phi-2",
"base_model:finetune:microsoft/phi-2",
"license:mit",
"region:us"
] | text-generation | 2023-12-29T14:41:39Z | ---
base_model: microsoft/phi-2
inference: false
language:
- en
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
model_creator: Microsoft
model_name: Phi 2
model_type: phi-msft
pipeline_tag: text-generation
prompt_template: |
Instruct: {prompt}
Output:
quantized_by: TheBloke
tags:
- nlp
- code
- llamafile
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/FwAVVu7eJ4">Chat & support: jartine's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">jartine's LLM work is generously supported by a grant from <a href="https://mozilla.org">mozilla</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Phi 2 - llamafile
- Model creator: [Microsoft](https://huggingface.co/microsoft)
- Original model: [Phi 2](https://huggingface.co/microsoft/phi-2)
<!-- description start -->
## Description
This repo contains llamafile format model files for [Microsoft's Phi 2](https://huggingface.co/microsoft/phi-2).
WARNING: This README may contain inaccuracies. It was generated automatically by forking <a href=/TheBloke/phi-2-GGUF>TheBloke/phi-2-GGUF</a> and piping the README through sed. Errors should be reported to jartine, and do not reflect TheBloke. You can also support his work on [Patreon](https://www.patreon.com/TheBlokeAI).
<!-- README_llamafile.md-about-llamafile start -->
### About llamafile
llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64.
Here is an incomplete list of clients and libraries that are known to support llamafile:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for llamafile. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_llamafile.md-about-llamafile end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/jartine/phi-2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit llamafile models for CPU+GPU inference](https://huggingface.co/jartine/phi-2-llamafile)
* [Microsoft's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/microsoft/phi-2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Phi
```
Instruct: {prompt}
Output:
```
<!-- prompt-template end -->
<!-- compatibility_llamafile start -->
## Compatibility
These quantised llamafilev2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_llamafile end -->
<!-- README_llamafile.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [phi-2.Q2_K.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q2_K.llamafile) | Q2_K | 2 | 1.17 GB| 3.67 GB | smallest, significant quality loss - not recommended for most purposes |
| [phi-2.Q3_K_S.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q3_K_S.llamafile) | Q3_K_S | 3 | 1.25 GB| 3.75 GB | very small, high quality loss |
| [phi-2.Q3_K_M.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q3_K_M.llamafile) | Q3_K_M | 3 | 1.48 GB| 3.98 GB | very small, high quality loss |
| [phi-2.Q4_0.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q4_0.llamafile) | Q4_0 | 4 | 1.60 GB| 4.10 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [phi-2.Q3_K_L.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q3_K_L.llamafile) | Q3_K_L | 3 | 1.60 GB| 4.10 GB | small, substantial quality loss |
| [phi-2.Q4_K_S.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q4_K_S.llamafile) | Q4_K_S | 4 | 1.62 GB| 4.12 GB | small, greater quality loss |
| [phi-2.Q4_K_M.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q4_K_M.llamafile) | Q4_K_M | 4 | 1.79 GB| 4.29 GB | medium, balanced quality - recommended |
| [phi-2.Q5_0.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q5_0.llamafile) | Q5_0 | 5 | 1.93 GB| 4.43 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [phi-2.Q5_K_S.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q5_K_S.llamafile) | Q5_K_S | 5 | 1.93 GB| 4.43 GB | large, low quality loss - recommended |
| [phi-2.Q5_K_M.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q5_K_M.llamafile) | Q5_K_M | 5 | 2.07 GB| 4.57 GB | large, very low quality loss - recommended |
| [phi-2.Q6_K.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q6_K.llamafile) | Q6_K | 6 | 2.29 GB| 4.79 GB | very large, extremely low quality loss |
| [phi-2.Q8_0.llamafile](https://huggingface.co/jartine/phi-2-llamafile/blob/main/phi-2.Q8_0.llamafile) | Q8_0 | 8 | 2.96 GB| 5.46 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_llamafile.md-provided-files end -->
<!-- README_llamafile.md-how-to-download start -->
## How to download llamafile files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: jartine/phi-2-llamafile and below it, a specific filename to download, such as: phi-2.Q4_K_M.llamafile.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download jartine/phi-2-llamafile phi-2.Q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download jartine/phi-2-llamafile --local-dir . --local-dir-use-symlinks False --include='*Q4_K*llamafile'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download jartine/phi-2-llamafile phi-2.Q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_llamafile.md-how-to-download end -->
<!-- README_llamafile.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m phi-2.Q4_K_M.llamafile --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Instruct: {prompt}\nOutput:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the llamafile file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use llamafile models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./phi-2.Q4_K_M.llamafile", # Download the model file first
n_ctx=2048, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"Instruct: {prompt}\nOutput:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./phi-2.Q4_K_M.llamafile", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_llamafile.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[jartine AI's Discord server](https://discord.gg/FwAVVu7eJ4)
## Thanks, and how to contribute
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
And thank you again to mozilla for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Microsoft's Phi 2
## Model Summary
Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/phi-1.5), augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.
Our model hasn't been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
## Intended Uses
Phi-2 is intended for research purposes only. Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.
### QA Format:
You can provide the prompt as a standalone question as follows:
```markdown
Write a detailed analogy between mathematics and a lighthouse.
```
where the model generates the text after "." .
To encourage the model to write more concise answers, you can also try the following QA format using "Instruct: \<prompt\>\nOutput:"
```markdown
Instruct: Write a detailed analogy between mathematics and a lighthouse.
Output: Mathematics is like a lighthouse. Just as a lighthouse guides ships safely to shore, mathematics provides a guiding light in the world of numbers and logic. It helps us navigate through complex problems and find solutions. Just as a lighthouse emits a steady beam of light, mathematics provides a consistent framework for reasoning and problem-solving. It illuminates the path to understanding and helps us make sense of the world around us.
```
where the model generates the text after "Output:".
### Chat Format:
```markdown
Alice: I don't know why, I'm struggling to maintain focus while studying. Any suggestions?
Bob: Well, have you tried creating a study schedule and sticking to it?
Alice: Yes, I have, but it doesn't seem to help much.
Bob: Hmm, maybe you should try studying in a quiet environment, like the library.
Alice: ...
```
where the model generates the text after the first "Bob:".
### Code Format:
```python
def print_prime(n):
"""
Print all primes between 1 and n
"""
primes = []
for num in range(2, n+1):
is_prime = True
for i in range(2, int(math.sqrt(num))+1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
print(primes)
```
where the model generates the text after the comments.
**Notes:**
* Phi-2 is intended for research purposes. The model-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
* Direct adoption for production tasks is out of the scope of this research project. As a result, the Phi-2 model has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
* If you are using `transformers>=4.36.0`, always load the model with `trust_remote_code=True` to prevent side-effects.
## Sample Code
There are four types of execution mode:
1. FP16 / Flash-Attention / CUDA:
```python
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype="auto", flash_attn=True, flash_rotary=True, fused_dense=True, device_map="cuda", trust_remote_code=True)
```
2. FP16 / CUDA:
```python
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype="auto", device_map="cuda", trust_remote_code=True)
```
3. FP32 / CUDA:
```python
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype=torch.float32, device_map="cuda", trust_remote_code=True)
```
4. FP32 / CPU:
```python
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype=torch.float32, device_map="cpu", trust_remote_code=True)
```
To ensure the maximum compatibility, we recommend using the second execution mode (FP16 / CUDA), as follows:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
inputs = tokenizer('''def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
**Remark:** In the generation function, our model currently does not support beam search (`num_beams > 1`).
Furthermore, in the forward pass of the model, we currently do not support outputting hidden states or attention values, or using custom input embeddings.
## Limitations of Phi-2
* Generate Inaccurate Code and Facts: The model may produce incorrect code snippets and statements. Users should treat these outputs as suggestions or starting points, not as definitive or accurate solutions.
* Limited Scope for code: Majority of Phi-2 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.
* Unreliable Responses to Instruction: The model has not undergone instruction fine-tuning. As a result, it may struggle or fail to adhere to intricate or nuanced instructions provided by users.
* Language Limitations: The model is primarily designed to understand standard English. Informal English, slang, or any other languages might pose challenges to its comprehension, leading to potential misinterpretations or errors in response.
* Potential Societal Biases: Phi-2 is not entirely free from societal biases despite efforts in assuring trainig data safety. There's a possibility it may generate content that mirrors these societal biases, particularly if prompted or instructed to do so. We urge users to be aware of this and to exercise caution and critical thinking when interpreting model outputs.
* Toxicity: Despite being trained with carefully selected data, the model can still produce harmful content if explicitly prompted or instructed to do so. We chose to release the model for research purposes only -- We hope to help the open-source community develop the most effective ways to reduce the toxicity of a model directly after pretraining.
* Verbosity: Phi-2 being a base model often produces irrelevant or extra text and responses following its first answer to user prompts within a single turn. This is due to its training dataset being primarily textbooks, which results in textbook-like responses.
## Training
### Model
* Architecture: a Transformer-based model with next-word prediction objective
* Context length: 2048 tokens
* Dataset size: 250B tokens, combination of NLP synthetic data created by AOAI GPT-3.5 and filtered web data from Falcon RefinedWeb and SlimPajama, which was assessed by AOAI GPT-4.
* Training tokens: 1.4T tokens
* GPUs: 96xA100-80G
* Training time: 14 days
### Software
* [PyTorch](https://github.com/pytorch/pytorch)
* [DeepSpeed](https://github.com/microsoft/DeepSpeed)
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
### License
The model is licensed under the [microsoft-research-license](https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE).
## Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
<!-- original-model-card end --> |
PriShenoy/pri | PriShenoy | 2024-04-20T07:52:27Z | 5 | 0 | diffusers | [
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-12-12T14:34:15Z | ---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### Welcome to Pixel AI: A Dreambooth model for text-to-image conversion by Prithvi Shenoy
Project Submission Code: *********
### Stable Diffusion
Stable Diffusion is a state-of-the-art generative AI model that creates detailed images from textual descriptions, revolutionizing the way we generate and interact with digital content.
Sample pictures of this concept:
.jpg)
.jpg)
|
catastropiyush/Alpaca_Mistral_finetune_GGUF | catastropiyush | 2024-04-20T07:49:25Z | 5 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"base_model:quantized:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T07:47:07Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
base_model: unsloth/mistral-7b-bnb-4bit
---
# Uploaded model
- **Developed by:** catastropiyush
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
MaziyarPanahi/Llama-3-11B-Instruct-v0.1-GGUF | MaziyarPanahi | 2024-04-20T07:41:45Z | 596 | 7 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"text-generation",
"mixtral",
"base_model:MaziyarPanahi/Llama-3-11B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/Llama-3-11B-Instruct-v0.1",
"region:us",
"conversational"
] | text-generation | 2024-04-19T10:37:09Z | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- text-generation
- mixtral
- text-generation
model_name: Llama-3-11B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/Llama-3-11B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Llama-3-11B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-11B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/Llama-3-11B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-11B-Instruct-v0.1)
## Description
[MaziyarPanahi/Llama-3-11B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-11B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-11B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-11B-Instruct-v0.1).
## Load GGUF models
You `MUST` follow the prompt template provided by Llama-3:
```sh
./llama.cpp/main -m Llama-3-11B-Instruct.Q2_K.gguf -r '<|eot_id|>' --in-prefix "\n<|start_header_id|>user<|end_header_id|>\n\n" --in-suffix "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" -p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.<|eot_id|>\n<|start_header_id|>user<|end_header_id|>\n\nHi! How are you?<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n\n" -n 1024
```
|
LoneStriker/Llama-3-Smaug-8B-8.0bpw-h8-exl2 | LoneStriker | 2024-04-20T07:41:18Z | 6 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"exl2",
"region:us"
] | text-generation | 2024-04-20T07:37:49Z | ---
library_name: transformers
license: llama2
---
# Llama-3-Smaug-8B
### Built with Meta Llama 3
This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
### Model Description
- **Developed by:** [Abacus.AI](https://abacus.ai)
- **License:** https://llama.meta.com/llama3/license/
- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
## Evaluation
```
########## First turn ##########
score
model turn
llama3-8b-smaug-2-merged-600 1 8.79375
llama3-8b-smaug-2-merged-150 1 8.71250
llama3-8b-smaug-2-merged-300 1 8.66250
base_Meta-Llama-3-8B-Instruct 1 8.53125
llama3-8b-smaug-2-merged-450 1 8.42500
########## Second turn ##########
score
model turn
llama3-8b-smaug-2-merged-450 2 7.8125
llama3-8b-smaug-2-merged-300 2 7.7375
llama3-8b-smaug-2-merged-600 2 7.7250
llama3-8b-smaug-2-merged-150 2 7.7125
base_Meta-Llama-3-8B-Instruct 2 7.5500
########## Average ##########
score
model
llama3-8b-smaug-2-merged-600 8.259375
llama3-8b-smaug-2-merged-150 8.212500
llama3-8b-smaug-2-merged-300 8.200000
llama3-8b-smaug-2-merged-450 8.118750
base_Meta-Llama-3-8B-Instruct 8.040625
```
| Model | First turn | Second Turn | Average |
| :---- | ---------: | ----------: | ------: |
| llama3-8b-smaug-2-merged-600 | **8.79** | 7.73 | **8.26** |
| llama3-8b-smaug-2-merged-450 | 8.43 | **7.81** | 8.12 |
| llama3-8b-smaug-2-merged-300 | 8.66 | 7.74 | 8.20 |
| llama3-8b-smaug-2-merged-150 | 8.71 | 7.71 | 8.21 |
| Meta-Llama-3-8B-Instruct | 8.53 | 7.55 | 8.04 |
|
mesolitica/malaysian-mistral-64M-MLM-512 | mesolitica | 2024-04-20T07:40:53Z | 76 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"feature-extraction",
"custom_code",
"ms",
"text-generation-inference",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-04-17T23:37:12Z | ---
library_name: transformers
language:
- ms
---
# Malaysian Mistral 64M on MLM task using 512 context length
Replicating https://github.com/McGill-NLP/llm2vec using https://huggingface.co/mesolitica/malaysian-mistral-64M-4096, done by https://github.com/aisyahrzk https://twitter.com/aisyahhhrzk
Source code at https://github.com/mesolitica/malaya/tree/master/session/llm2vec
WandB, https://wandb.ai/aisyahrazak/mistral-64M-mlm?nw=nwuseraisyahrazak |
mesolitica/malaysian-mistral-191M-MLM-512 | mesolitica | 2024-04-20T07:40:30Z | 81 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"feature-extraction",
"custom_code",
"ms",
"text-generation-inference",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-04-17T08:35:18Z | ---
library_name: transformers
language:
- ms
---
# Malaysian Mistral 191M on MLM task using 512 context length
Replicating https://github.com/McGill-NLP/llm2vec using https://huggingface.co/mesolitica/malaysian-mistral-191M-4096, done by https://github.com/aisyahrzk https://twitter.com/aisyahhhrzk
Source code at https://github.com/mesolitica/malaya/tree/master/session/llm2vec
WandB, https://wandb.ai/aisyahrazak/mistral-191M-mlm?nw=nwuseraisyahrazak |
yousefg/Academ-0.5 | yousefg | 2024-04-20T07:37:31Z | 112 | 0 | transformers | [
"transformers",
"onnx",
"safetensors",
"bart",
"text2text-generation",
"lecture",
"college",
"university",
"summarization",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | 2024-04-15T09:25:08Z | ---
library_name: transformers
tags:
- lecture
- college
- university
- summarization
license: mit
language:
- en
metrics:
- rouge
pipeline_tag: summarization
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
Academ is a fine-tuned BART model for summarizing academic lectures.
To find out how the model was fine-tuned, you can check the notebook on Kaggle: https://www.kaggle.com/code/yousefr/college-lectures-summarization-bart-unsupervised/
## 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:** Yousef Gamaleldin
- **Model type:** Summarization
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model [optional]:** BART Large CNN
## How to Get Started with the Model
Use the code below to get started with the model.
```
from transformers import BartForConditionalGeneration, AutoTokenizer
model = BartForConditionalGeneration.from_pretrained('yousefg/Academ-0.5')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-cnn')
def get_summary(input_ids, attention_mask, context_length):
summaries = []
for i in range(0, input_ids.shape[1], context_length):
input_slice = input_ids[:, i:i + context_length] if i + context_length <= input_ids.size(1) else input_ids[:, i:]
attention_mask_slice = attention_mask[:, i:i + context_length] if i + context_length <= attention_mask.size(1) else attention_mask[:, i:]
summary = model.generate(input_slice, attention_mask = attention_mask_slice, max_new_tokens = 1654, min_new_tokens = 250, do_sample = True, renormalize_logits = True)
summaries.extend(summary[0].tolist())
summaries = tokenizer.decode(summaries, skip_special_tokens = True)
return summaries
batch = tokenizer(texts, truncation = False) # make sure to get the transcript from the lecture
input_ids = torch.tensor(batch['input_ids']).unsqueeze(0).to(device)
attention_mask = torch.tensor(batch['attention_mask']).unsqueeze(0).to(device)
summary = get_summary(input_ids, attention_mask, 1654)
print(summary)
```
## Training Details
The model's training used a custom loss function for getting the model into an optimal length (35% chosen as the optimal length).
#### Training Hyperparameters
- **Training regime:** bf16 non-mixed precision<!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
- **Learning Rate:** 0.001
- **Weight Decay:** 0.01
- **Epochs:** 4
- **Batch Size:** 16
-
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
The evaluation is based on ROUGE 1 with a change of discounting padding tokens.
#### Testing Data
The model's test dataset had 289 lectures, mainly from MIT OpenCourseWare.
<!-- This should link to a Dataset Card if possible. -->
### Results
The model achieved 96% accuracy for ROUGUE 1 in the test dataset, and 93% in the evaluation dataset.
#### Summary
Academ is a summarization model trained on 2307 lectures, mainly from MIT OpenCourseWare. The model has a max sequence length of 1654, increasing 630 tokens from the original model. |
LoneStriker/Llama-3-Smaug-8B-5.0bpw-h6-exl2 | LoneStriker | 2024-04-20T07:34:53Z | 3 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"5-bit",
"exl2",
"region:us"
] | text-generation | 2024-04-20T07:32:29Z | ---
library_name: transformers
license: llama2
---
# Llama-3-Smaug-8B
### Built with Meta Llama 3
This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
### Model Description
- **Developed by:** [Abacus.AI](https://abacus.ai)
- **License:** https://llama.meta.com/llama3/license/
- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
## Evaluation
```
########## First turn ##########
score
model turn
llama3-8b-smaug-2-merged-600 1 8.79375
llama3-8b-smaug-2-merged-150 1 8.71250
llama3-8b-smaug-2-merged-300 1 8.66250
base_Meta-Llama-3-8B-Instruct 1 8.53125
llama3-8b-smaug-2-merged-450 1 8.42500
########## Second turn ##########
score
model turn
llama3-8b-smaug-2-merged-450 2 7.8125
llama3-8b-smaug-2-merged-300 2 7.7375
llama3-8b-smaug-2-merged-600 2 7.7250
llama3-8b-smaug-2-merged-150 2 7.7125
base_Meta-Llama-3-8B-Instruct 2 7.5500
########## Average ##########
score
model
llama3-8b-smaug-2-merged-600 8.259375
llama3-8b-smaug-2-merged-150 8.212500
llama3-8b-smaug-2-merged-300 8.200000
llama3-8b-smaug-2-merged-450 8.118750
base_Meta-Llama-3-8B-Instruct 8.040625
```
| Model | First turn | Second Turn | Average |
| :---- | ---------: | ----------: | ------: |
| llama3-8b-smaug-2-merged-600 | **8.79** | 7.73 | **8.26** |
| llama3-8b-smaug-2-merged-450 | 8.43 | **7.81** | 8.12 |
| llama3-8b-smaug-2-merged-300 | 8.66 | 7.74 | 8.20 |
| llama3-8b-smaug-2-merged-150 | 8.71 | 7.71 | 8.21 |
| Meta-Llama-3-8B-Instruct | 8.53 | 7.55 | 8.04 |
|
FredDYyy/distilhubert-finetuned-gtzan-finetuned-gtzan | FredDYyy | 2024-04-20T07:31:51Z | 163 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:yuval6967/distilhubert-finetuned-gtzan",
"base_model:finetune:yuval6967/distilhubert-finetuned-gtzan",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | audio-classification | 2024-04-20T04:58:28Z | ---
license: apache-2.0
base_model: yuval6967/distilhubert-finetuned-gtzan
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-music-genre-classification
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.935
---
<!-- 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. -->
# distilhubert-finetuned-gtzan-music-genre-classification
This model is a fine-tuned version of [yuval6967/distilhubert-finetuned-gtzan](https://huggingface.co/yuval6967/distilhubert-finetuned-gtzan) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4478
- Accuracy: 0.935
## 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
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 100 | 0.3000 | 0.935 |
| No log | 2.0 | 200 | 0.4770 | 0.905 |
| No log | 3.0 | 300 | 0.5666 | 0.93 |
| No log | 4.0 | 400 | 0.4572 | 0.92 |
| 0.0298 | 5.0 | 500 | 0.6038 | 0.9 |
| 0.0298 | 6.0 | 600 | 0.4111 | 0.925 |
| 0.0298 | 7.0 | 700 | 0.4528 | 0.93 |
| 0.0298 | 8.0 | 800 | 0.4400 | 0.94 |
| 0.0298 | 9.0 | 900 | 0.4638 | 0.935 |
| 0.0081 | 10.0 | 1000 | 0.4478 | 0.935 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
LoneStriker/Llama-3-Smaug-8B-3.0bpw-h6-exl2 | LoneStriker | 2024-04-20T07:30:13Z | 3 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"3-bit",
"exl2",
"region:us"
] | text-generation | 2024-04-20T07:28:27Z | ---
library_name: transformers
license: llama2
---
# Llama-3-Smaug-8B
### Built with Meta Llama 3
This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
### Model Description
- **Developed by:** [Abacus.AI](https://abacus.ai)
- **License:** https://llama.meta.com/llama3/license/
- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
## Evaluation
```
########## First turn ##########
score
model turn
llama3-8b-smaug-2-merged-600 1 8.79375
llama3-8b-smaug-2-merged-150 1 8.71250
llama3-8b-smaug-2-merged-300 1 8.66250
base_Meta-Llama-3-8B-Instruct 1 8.53125
llama3-8b-smaug-2-merged-450 1 8.42500
########## Second turn ##########
score
model turn
llama3-8b-smaug-2-merged-450 2 7.8125
llama3-8b-smaug-2-merged-300 2 7.7375
llama3-8b-smaug-2-merged-600 2 7.7250
llama3-8b-smaug-2-merged-150 2 7.7125
base_Meta-Llama-3-8B-Instruct 2 7.5500
########## Average ##########
score
model
llama3-8b-smaug-2-merged-600 8.259375
llama3-8b-smaug-2-merged-150 8.212500
llama3-8b-smaug-2-merged-300 8.200000
llama3-8b-smaug-2-merged-450 8.118750
base_Meta-Llama-3-8B-Instruct 8.040625
```
| Model | First turn | Second Turn | Average |
| :---- | ---------: | ----------: | ------: |
| llama3-8b-smaug-2-merged-600 | **8.79** | 7.73 | **8.26** |
| llama3-8b-smaug-2-merged-450 | 8.43 | **7.81** | 8.12 |
| llama3-8b-smaug-2-merged-300 | 8.66 | 7.74 | 8.20 |
| llama3-8b-smaug-2-merged-150 | 8.71 | 7.71 | 8.21 |
| Meta-Llama-3-8B-Instruct | 8.53 | 7.55 | 8.04 |
|
sidnarsipur/controlnet_height | sidnarsipur | 2024-04-20T07:25:16Z | 2 | 0 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"controlnet",
"diffusers-training",
"base_model:stabilityai/stable-diffusion-2-1-base",
"base_model:adapter:stabilityai/stable-diffusion-2-1-base",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2024-04-16T04:15:54Z | ---
license: creativeml-openrail-m
library_name: diffusers
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
- diffusers-training
base_model: stabilityai/stable-diffusion-2-1-base
inference: true
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# controlnet-sidnarsipur/controlnet_models
These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning.
You can find some example images below.
prompt: Height Map
prompt: Height Map
prompt: Height Map
prompt: Height Map
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
LoneStriker/Llama-3-Smaug-8B-GGUF | LoneStriker | 2024-04-20T07:21:11Z | 0 | 3 | transformers | [
"transformers",
"gguf",
"license:llama2",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-04-20T07:09:10Z | ---
library_name: transformers
license: llama2
---
# Llama-3-Smaug-8B
### Built with Meta Llama 3
This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
### Model Description
- **Developed by:** [Abacus.AI](https://abacus.ai)
- **License:** https://llama.meta.com/llama3/license/
- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
## Evaluation
```
########## First turn ##########
score
model turn
llama3-8b-smaug-2-merged-600 1 8.79375
llama3-8b-smaug-2-merged-150 1 8.71250
llama3-8b-smaug-2-merged-300 1 8.66250
base_Meta-Llama-3-8B-Instruct 1 8.53125
llama3-8b-smaug-2-merged-450 1 8.42500
########## Second turn ##########
score
model turn
llama3-8b-smaug-2-merged-450 2 7.8125
llama3-8b-smaug-2-merged-300 2 7.7375
llama3-8b-smaug-2-merged-600 2 7.7250
llama3-8b-smaug-2-merged-150 2 7.7125
base_Meta-Llama-3-8B-Instruct 2 7.5500
########## Average ##########
score
model
llama3-8b-smaug-2-merged-600 8.259375
llama3-8b-smaug-2-merged-150 8.212500
llama3-8b-smaug-2-merged-300 8.200000
llama3-8b-smaug-2-merged-450 8.118750
base_Meta-Llama-3-8B-Instruct 8.040625
```
| Model | First turn | Second Turn | Average |
| :---- | ---------: | ----------: | ------: |
| llama3-8b-smaug-2-merged-600 | **8.79** | 7.73 | **8.26** |
| llama3-8b-smaug-2-merged-450 | 8.43 | **7.81** | 8.12 |
| llama3-8b-smaug-2-merged-300 | 8.66 | 7.74 | 8.20 |
| llama3-8b-smaug-2-merged-150 | 8.71 | 7.71 | 8.21 |
| Meta-Llama-3-8B-Instruct | 8.53 | 7.55 | 8.04 |
|
thisurawz1/llama3_unsloth_10ep | thisurawz1 | 2024-04-20T07:15:40Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T07:11:54Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** thisurawz1
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
jenjenot/whisper_medium_tw_minnan | jenjenot | 2024-04-20T07:15:32Z | 13 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"zh",
"dataset:thomas0104/nan_tw_soap_opera",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-04-16T07:00:04Z | ---
language:
- zh
tags:
- hf-asr-leaderboard
- generated_from_trainer
base_model: openai/whisper_medium
datasets:
- thomas0104/nan_tw_soap_opera
model-index:
- name: jenjenot/whisper_medium_tw_minnan
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. -->
# jenjenot/whisper_medium_tw_minnan
This model is a fine-tuned version of [openai/whisper_medium](https://huggingface.co/openai/whisper_medium) on the nan_tw_soap_opera 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: 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: 8000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
johannhartmann/mistral22b_orpo_de | johannhartmann | 2024-04-20T07:13:39Z | 8 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"de",
"en",
"dataset:johannhartmann/steroids",
"dataset:johannhartmann/oh25_mistral_dpo_de",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-19T18:18:15Z | ---
license: apache-2.0
datasets:
- johannhartmann/steroids
- johannhartmann/oh25_mistral_dpo_de
language:
- de
- en
---
This is a simple experiment using geman ORPO training for one epoch using qlora and unsloth on [Vezora/Mistral-22B-v0.2](https://huggingface.coVezora/Mistral-22B-v0.2) |
TinyPixel/llama-3-adapter | TinyPixel | 2024-04-20T07:04:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T07:04:01Z | ---
library_name: transformers
tags: []
---
# 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] |
michaelw37/sc46 | michaelw37 | 2024-04-20T07:02:42Z | 89 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T07:01:14Z | ---
library_name: transformers
tags: []
---
# 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] |
f77777/wav2vec2-large-xls-r-300m-firdous-nep-colab | f77777 | 2024-04-20T06:58:15Z | 105 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_13_0",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-04-20T03:43:05Z | ---
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
- common_voice_13_0
model-index:
- name: wav2vec2-large-xls-r-300m-firdous-nep-colab
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. -->
# wav2vec2-large-xls-r-300m-firdous-nep-colab
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
LeoNight/custom-resnet50d-v2 | LeoNight | 2024-04-20T06:57:57Z | 106 | 0 | transformers | [
"transformers",
"safetensors",
"resnet-t",
"image-classification",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | image-classification | 2024-04-20T06:55:06Z | ---
library_name: transformers
tags: []
---
# 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]
|
gotchu/llama3-4 | gotchu | 2024-04-20T06:57:03Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T06:40:53Z | ---
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
library_name: transformers
tags:
- mergekit
- merge
---
# merged
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 passthrough merge method.
### Models Merged
The following models were included in the merge:
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
dtype: float16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 32]
model:
model:
path: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
- layer_range: [0, 32]
model:
model:
path: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
- layer_range: [0, 32]
model:
model:
path: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
- layer_range: [0, 32]
model:
model:
path: meta-llama/Meta-Llama-3-8B-Instruct
```
|
sebajoe/batchPrompting_7b_25 | sebajoe | 2024-04-20T06:49:30Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T06:49:20Z | ---
library_name: transformers
tags: []
---
# 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] |
DandinPower/deberta-v3-large-otat-recommened-hp | DandinPower | 2024-04-20T06:40:31Z | 104 | 0 | transformers | [
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"nycu-112-2-datamining-hw2",
"generated_from_trainer",
"en",
"dataset:DandinPower/review_onlytitleandtext",
"base_model:microsoft/deberta-v3-large",
"base_model:finetune:microsoft/deberta-v3-large",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-04-20T05:37:34Z | ---
language:
- en
license: mit
base_model: microsoft/deberta-v3-large
tags:
- nycu-112-2-datamining-hw2
- generated_from_trainer
datasets:
- DandinPower/review_onlytitleandtext
metrics:
- accuracy
model-index:
- name: deberta-v3-large-otat-recommened-hp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: DandinPower/review_onlytitleandtext
type: DandinPower/review_onlytitleandtext
metrics:
- name: Accuracy
type: accuracy
value: 0.6685714285714286
---
<!-- 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. -->
# deberta-v3-large-otat-recommened-hp
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the DandinPower/review_onlytitleandtext dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8169
- Accuracy: 0.6686
- Macro F1: 0.6662
## 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: 6e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.7726 | 1.14 | 500 | 0.8107 | 0.6613 | 0.6602 |
| 0.6983 | 2.29 | 1000 | 0.7739 | 0.669 | 0.6662 |
| 0.6504 | 3.43 | 1500 | 0.7891 | 0.6726 | 0.6725 |
| 0.6067 | 4.57 | 2000 | 0.8169 | 0.6686 | 0.6662 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
LeoNight/custom-resnet50d | LeoNight | 2024-04-20T06:39:55Z | 106 | 0 | transformers | [
"transformers",
"safetensors",
"myResnet",
"image-classification",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | image-classification | 2024-04-20T06:37:03Z | ---
library_name: transformers
tags: []
---
# 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]
|
IntervitensInc/intv_l3_mk5 | IntervitensInc | 2024-04-20T06:32:31Z | 3 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T06:27:22Z | ---
library_name: transformers
tags: []
---
# 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] |
gK29382231121/idefics2-8b-docvqa-finetuned-tutorial | gK29382231121 | 2024-04-20T06:28:37Z | 0 | 0 | null | [
"safetensors",
"generated_from_trainer",
"base_model:HuggingFaceM4/idefics2-8b",
"base_model:finetune:HuggingFaceM4/idefics2-8b",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T06:28:30Z | ---
license: apache-2.0
base_model: HuggingFaceM4/idefics2-8b
tags:
- generated_from_trainer
model-index:
- name: idefics2-8b-docvqa-finetuned-tutorial
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. -->
# idefics2-8b-docvqa-finetuned-tutorial
This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) 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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 50
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
yunkimmy/taxi | yunkimmy | 2024-04-20T06:24:51Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-04-20T06:24:35Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi
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="yunkimmy/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"])
```
|
lucataco/Meta-Llama-3-70B-Instruct-4bit | lucataco | 2024-04-20T06:24:41Z | 4 | 0 | mlx | [
"mlx",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"text-generation",
"conversational",
"en",
"license:other",
"region:us"
] | text-generation | 2024-04-20T06:17:42Z | ---
language:
- en
license: other
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- mlx
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
# lucataco/Meta-Llama-3-70B-Instruct-4bit
This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("lucataco/Meta-Llama-3-70B-Instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
Rupesh2/Llama3Hindi | Rupesh2 | 2024-04-20T06:23:13Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T05:52:26Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** Rupesh2
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
jamesphe/smile-model-gguf | jamesphe | 2024-04-20T06:20:44Z | 6 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-2-7b-bnb-4bit",
"base_model:quantized:unsloth/llama-2-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-22T12:41:39Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-2-7b-bnb-4bit
---
# Uploaded model
- **Developed by:** jamesphe
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-2-7b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
ntvcie/Gemma2bVinhntV6_16bit | ntvcie | 2024-04-20T06:18:25Z | 0 | 0 | transformers | [
"transformers",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-2b-bnb-4bit",
"base_model:finetune:unsloth/gemma-2b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T06:18:18Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
- trl
base_model: unsloth/gemma-2b-bnb-4bit
---
# Uploaded model
- **Developed by:** ntvcie
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
JJJCHHH/my_awesome_opus_books_model | JJJCHHH | 2024-04-20T06:15:50Z | 61 | 0 | transformers | [
"transformers",
"tf",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-19T07:55:36Z | ---
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_keras_callback
model-index:
- name: JJJCHHH/my_awesome_opus_books_model
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. -->
# JJJCHHH/my_awesome_opus_books_model
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.6435
- Validation Loss: 0.5323
- Epoch: 2
## 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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.7171 | 0.5727 | 0 |
| 0.6735 | 0.5501 | 1 |
| 0.6435 | 0.5323 | 2 |
### Framework versions
- Transformers 4.40.0
- TensorFlow 2.16.1
- Datasets 2.14.5
- Tokenizers 0.19.1
|
jieunhan/solar-merge-v1.0 | jieunhan | 2024-04-20T06:10:42Z | 62 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"upstage/SOLAR-10.7B-Instruct-v1.0",
"heavytail/kullm-solar",
"base_model:heavytail/kullm-solar",
"base_model:merge:heavytail/kullm-solar",
"base_model:upstage/SOLAR-10.7B-Instruct-v1.0",
"base_model:merge:upstage/SOLAR-10.7B-Instruct-v1.0",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T02:43:48Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- upstage/SOLAR-10.7B-Instruct-v1.0
- heavytail/kullm-solar
base_model:
- upstage/SOLAR-10.7B-Instruct-v1.0
- heavytail/kullm-solar
---
# solar-merge-v1.0
solar-merge-v1.0 is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
* [heavytail/kullm-solar](https://huggingface.co/heavytail/kullm-solar)
## 🧩 Configuration
```yaml
base_model: upstage/SOLAR-10.7B-v1.0
dtype: float16
experts:
- source_model: upstage/SOLAR-10.7B-Instruct-v1.0
positive_prompts: ["당신은 친절한 보편적인 어시스턴트이다."]
- source_model: heavytail/kullm-solar
positive_prompts: ["당신은 친절한 어시스턴트이다."]
gate_mode: cheap_embed
tokenizer_source: base
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jieunhan/solar-merge-v1.0"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
``` |
sahaj96/Alpaca-Llama3-8B-Instruct-v1.0 | sahaj96 | 2024-04-20T06:08:59Z | 0 | 0 | diffusers | [
"diffusers",
"art",
"code",
"text-to-image",
"en",
"dataset:HuggingFaceTB/compendia",
"doi:10.57967/hf/2088",
"license:apache-2.0",
"region:us"
] | text-to-image | 2024-04-20T04:29:52Z | ---
license: apache-2.0
language:
- en
metrics:
- accuracy
library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
- code
datasets:
- HuggingFaceTB/compendia
---
## Model Card for Model ID
Alpaca based on Llama 3 8B
Instruct
8k context length.
### Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import torchvision
tokenizer = AutoTokenizer.from_pretrained("sahaj96/Alpaca-Llama3-8B-Instruct-v1.0")
model = AutoModelForCausalLM.from_pretrained("sahaj96/Alpaca-Llama3-8B-Instruct-v1.0")
prompt = "A serene landscape with mountains and a lake"
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print("Generated Text:", generated_text)
output_image_path = "generated_image.png"
torchvision.utils.save_image(torch.zeros((3, 256, 256)), output_image_path)
print(f"Image generated and saved at {output_image_path}")
### Model Description
fine-tuned from the original Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo.
Alpaca is a general model and can itself be finetuned to be specialized for specific use cases.
|
allknowingroger/Llam3merge4 | allknowingroger | 2024-04-20T06:03:57Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2306.01708",
"base_model:cloudyu/Meta-Llama-3-8B-Instruct-DPO",
"base_model:finetune:cloudyu/Meta-Llama-3-8B-Instruct-DPO",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T05:59:37Z | ---
base_model:
- cloudyu/Meta-Llama-3-8B-Instruct-DPO
- Grayx/sad_llama_6
library_name: transformers
tags:
- mergekit
- merge
---
# merge
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Grayx/sad_llama_6](https://huggingface.co/Grayx/sad_llama_6) as a base.
### Models Merged
The following models were included in the merge:
* [cloudyu/Meta-Llama-3-8B-Instruct-DPO](https://huggingface.co/cloudyu/Meta-Llama-3-8B-Instruct-DPO)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
parameters:
density: 0.5
weight: 0.5
- model: Grayx/sad_llama_6
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: Grayx/sad_llama_6
parameters:
normalize: false
int8_mask: true
dtype: float16
```
|
b2bp8ip/llama_mbpp_syn | b2bp8ip | 2024-04-20T05:56:15Z | 76 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-04-20T05:04:34Z | ---
library_name: transformers
tags:
- trl
- sft
---
# 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] |
b2bp8ip/llama_mbpp_ft | b2bp8ip | 2024-04-20T05:54:14Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-04-20T04:05:15Z | ---
library_name: transformers
tags:
- trl
- sft
---
# 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] |
RunDiffusion/Juggernaut-X-v10 | RunDiffusion | 2024-04-20T05:50:38Z | 4,213 | 147 | diffusers | [
"diffusers",
"art",
"people",
"diffusion",
"Cinematic",
"Photography",
"Landscape",
"Interior",
"Food",
"Car",
"Wildlife",
"Architecture",
"text-to-image",
"en",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | 2024-04-19T21:30:46Z | ---
language:
- en
license: creativeml-openrail-m
library_name: diffusers
tags:
- art
- people
- diffusion
- Cinematic
- Photography
- Landscape
- Interior
- Food
- Car
- Wildlife
- Architecture
thumbnail: >-
https://storage.googleapis.com/run-diffusion-public-assets/juggernaut-x/juggernaut-collage-256.webp
base_model: stabilityai/stable-diffusion-xl-base-1.0
pipeline_tag: text-to-image
---
# Juggernaut X v10 + RunDiffusion Official (Community Version)
This model is not permitted to be used behind API services. Please contact [[email protected]](mailto:[email protected]) for business inquires, commercial licensing, custom models, and consultation.
Juggernaut X (SAFE) is available exclusivly on [RunDiffusion.com](http://rundiffusion.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=juggernautv10)
🎉 Juggernaut X World Wide Release! 🌍
After almost two months, we are thrilled to announce the next version of Juggernaut is ready to launch! Introducing Juggernaut 10, aka Juggernaut X. 🚀 If you would have been following us on Twitter (X) you would have been seeing the test images. If you aren't following us, do it now! https://x.com/RunDiffusion & Kandoo's new account needs some new followers. Help him out. https://x.com/Juggernaut_AI
- TWO Versions of Juggernaut X! SFW 🌟 and NSFW 🔥
- Fully trained from the ground up using the GPT4 Vision Captioning tool by LEOSAM 🛠️
- Much improved prompt adherence ✅
- Expanded and cleaner dataset with higher quality images 🖼️
- Improved classifications of shots (Full Body, Midshots, Portraits, etc) 📸
- Enhanced text generation capability 📝
- Two different prompting techniques, Natural and Tagging style 🏷️
- Enhanced by RunDiffusion Photo for refinement of details 🧐
Read more about this version here https://rundiffusion.com/juggernaut-xl
Dual Version Release 🔄
A Safe for Work (SFW) and a Not Safe for Work (NSFW) version of Juggernaut X will be available. This dual release strategy is designed to cater to diverse preferences and ensure inclusivity, offering the perfect solution for every user.
Our newest Safe for Work edition is available right now exclusively through Fooocus on RunDiffusion.com.
Launch Fooocus on RunDiffusion
Find Juggernaut X_ RunDiffusion_SAFE.safetensors and start generating!
It allows users to generate high-quality, suitable images while adhering to safe content guidelines. This version is particularly user-friendly, requiring only simple, straightforward prompts. It's ideal for the workplace, students, educators, and families.
SAFE stands for Suitable Ai For Everyone. 🌈
Conversely, the Not Safe for Work version offers unrestricted creative freedom across all categories and spectrums. This model is perfect for those seeking less constrained artistic expression and is available for free on Civitai.com, though a license is required for commercial use. 🎨
Both models of Juggernaut X (v10) represent our commitment to fostering a creative community that respects diverse needs and preferences. 🤝
Prompting Guide 📘
Because everything has been trained from the ground up, prompting is a bit different. (Simpler, don't worry) @Kandoo has created a guide to help you seamlessly integrate this powerful model into your workflow, enabling you to leverage its advanced capabilities without feeling overwhelmed. Download it here: https://rundiffusion.com/juggernaut-xl#nav
As always, we love our community and feel so lucky to be in this position to bring these awesome tools and models to you amazing diffusers. Thanks for supporting us since our first day back in 2022. Going on TWO YEARS since we first started using generative Ai. Time flies when you're having fun. wow!
Don't forget to follow us on Twitter where we have way more updates on big things we're working on. The future is bright
https://x.com/RunDiffusion
-RunDiffusion Team
 |
OwOOwO/dumbo-stable3 | OwOOwO | 2024-04-20T05:49:00Z | 91 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T05:47:25Z | ---
library_name: transformers
tags: []
---
# 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] |
lucataco/Meta-Llama-3-8B-4bit | lucataco | 2024-04-20T05:46:34Z | 6 | 0 | mlx | [
"mlx",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"text-generation",
"en",
"license:other",
"region:us"
] | text-generation | 2024-04-20T05:43:31Z | ---
language:
- en
license: other
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- mlx
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
# lucataco/Meta-Llama-3-8B-4bit
This model was converted to MLX format from [`meta-llama/Meta-Llama-3-8B`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("lucataco/Meta-Llama-3-8B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx | mlx-community | 2024-04-20T05:43:51Z | 5 | 1 | mlx | [
"mlx",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"text-generation",
"conversational",
"en",
"license:other",
"region:us"
] | text-generation | 2024-04-20T01:57:25Z | ---
language:
- en
license: other
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- mlx
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
# mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx
This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
toshi456/llava-jp-1.3b-v1.1-pretrain | toshi456 | 2024-04-20T05:41:07Z | 2 | 2 | transformers | [
"transformers",
"llava-jp",
"text-generation",
"ja",
"dataset:turing-motors/LLaVA-Pretrain-JA",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-17T13:39:10Z | ---
license: apache-2.0
datasets:
- turing-motors/LLaVA-Pretrain-JA
language:
- ja
---
# LLaVA-JP Model Card
This is a pretrained checkpoint, you can use it to instruct tune your multimodal models.
Check out the instructions [here](https://github.com/tosiyuki/LLaVA-JP)
## Model details
**Model type:**
LLaVA-JP is a vision-language model that can converse about input images.<br>
This model is an LVLM model trained using [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) as the image encoder and [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0) as the text decoder. supports the input of 768 x 768 high resolution images by scaling_on_scales method.
## Training dataset
- [LLaVA-Pretrain-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Pretrain-JA)
## Acknowledgement
- [LLaVA](https://llava-vl.github.io/)
- [LLM-jp](https://llm-jp.nii.ac.jp/)
- [scaling_on_scales](https://github.com/bfshi/scaling_on_scales/tree/master)
## License
Apache-2.0 |
blockblockblock/Copus-2x8B-bpw3 | blockblockblock | 2024-04-20T05:38:11Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"3-bit",
"exl2",
"region:us"
] | text-generation | 2024-04-20T05:35:54Z | ---
license: llama2
---
<img src=https://huggingface.co/lodrick-the-lafted/Copus-2x8B/resolve/main/copus.png>
MoE'd up:
- [dreamgen/opus-v1.2-llama-3-8b](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b)
- [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. |
sephichapdson/SugarDefender | sephichapdson | 2024-04-20T05:27:37Z | 0 | 0 | sentence-transformers | [
"sentence-transformers",
"Sugar Defender",
"en",
"license:bigscience-openrail-m",
"region:us"
] | null | 2024-04-20T05:26:14Z | ---
license: bigscience-openrail-m
language:
- en
library_name: sentence-transformers
tags:
- Sugar Defender
---
[Sugar Defender](https://icsfs.microsoftcrmportals.com/forums/general-discussion/752befe8-1dfe-ee11-a81c-000d3a289315) It's a vital wellspring of energy for your phones and organs, especially for the mind. Glucose levels in the blood should be painstakingly managed as too high or too low levels can cause medical problems.High blood sugar, known as hyperglycemia, can be connected to conditions like diabetes. Side effects might incorporate unreasonable thirst, successive pee, exhaustion, and obscured vision. Then again, low blood sugar, or hypoglycemia, can cause side effects like flimsiness, perspiring, disarray, and, in serious cases, loss of cognizance.
VISIT HERE FOR OFFICIAL WEBSITE:-https://icsfs.microsoftcrmportals.com/forums/general-discussion/752befe8-1dfe-ee11-a81c-000d3a289315
|
jamesphe/smile_lora_model | jamesphe | 2024-04-20T05:27:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-2-7b-bnb-4bit",
"base_model:finetune:unsloth/llama-2-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-23T02:11:12Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-2-7b-bnb-4bit
---
# Uploaded model
- **Developed by:** jamesphe
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-2-7b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
ikimhope/whisper-large-v2-commonko-100steps | ikimhope | 2024-04-20T05:26:13Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T15:24:17Z | ---
library_name: transformers
tags: []
---
# 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] |
automerger/Experiment27pasticheMergerix-7B | automerger | 2024-04-20T05:22:29Z | 0 | 0 | null | [
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:MiniMoog/Mergerix-7b-v0.3",
"base_model:finetune:MiniMoog/Mergerix-7b-v0.3",
"license:apache-2.0",
"region:us"
] | null | 2024-04-18T05:05:43Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- automerger
base_model:
- MiniMoog/Mergerix-7b-v0.3
---
# Experiment27pasticheMergerix-7B
Experiment27pasticheMergerix-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
* [MiniMoog/Mergerix-7b-v0.3](https://huggingface.co/MiniMoog/Mergerix-7b-v0.3)
## 🧩 Configuration
```yaml
models:
- model: automerger/Experiment27Pastiche-7B
# No parameters necessary for base model
- model: MiniMoog/Mergerix-7b-v0.3
parameters:
density: 0.53
weight: 0.6
merge_method: dare_ties
base_model: automerger/Experiment27Pastiche-7B
parameters:
int8_mask: true
dtype: bfloat16
random_seed: 0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Experiment27pasticheMergerix-7B"
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"])
``` |
emma7897/bert_two | emma7897 | 2024-04-20T05:12:37Z | 106 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2024-04-20T05:12:05Z | ---
library_name: transformers
tags: []
---
# 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] |
DavidAU/French-Alpaca-Croissant-1.3B-Instruct-Q8_0-GGUF | DavidAU | 2024-04-20T05:10:53Z | 7 | 2 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"sft",
"llama-cpp",
"gguf-my-repo",
"en",
"fr",
"dataset:jpacifico/French-Alpaca-dataset-Instruct-110K",
"base_model:croissantllm/CroissantLLMBase",
"base_model:quantized:croissantllm/CroissantLLMBase",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-04-17T03:15:27Z | ---
language:
- en
- fr
license: mit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
- llama-cpp
- gguf-my-repo
base_model: croissantllm/CroissantLLMBase
datasets:
- jpacifico/French-Alpaca-dataset-Instruct-110K
---
# DavidAU/French-Alpaca-Croissant-1.3B-Instruct-Q8_0-GGUF
This model was converted to GGUF format from [`AdrienB134/French-Alpaca-Croissant-1.3B-Instruct`](https://huggingface.co/AdrienB134/French-Alpaca-Croissant-1.3B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/AdrienB134/French-Alpaca-Croissant-1.3B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/French-Alpaca-Croissant-1.3B-Instruct-Q8_0-GGUF --model french-alpaca-croissant-1.3b-instruct.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/French-Alpaca-Croissant-1.3B-Instruct-Q8_0-GGUF --model french-alpaca-croissant-1.3b-instruct.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m french-alpaca-croissant-1.3b-instruct.Q8_0.gguf -n 128
```
|
kuotient/Meta-Llama-3-8B-Instruct | kuotient | 2024-04-20T05:10:28Z | 104 | 5 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-18T16:43:54Z | ---
language:
- en
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: other
license_name: llama3
license_link: LICENSE
extra_gated_prompt: >-
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
Meta Llama 3 Version Release Date: April 18, 2024
"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the
Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation accompanying Meta Llama 3
distributed by Meta at https://llama.meta.com/get-started/.
"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into
this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
regulations to provide legal consent and that has legal authority to bind your employer or such other
person or entity if you are entering in this Agreement on their behalf.
"Meta Llama 3" means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://llama.meta.com/llama-downloads.
"Llama Materials" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any
portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
outside of the EEA or Switzerland).
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works
thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta
Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you
use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is
distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model
name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following
attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is
licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
reference into this Agreement.
v. You will not use the Llama Materials or any output or results of the Llama Materials to
improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
million monthly active users in the preceding calendar month, you must request a license from Meta,
which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama
Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
or any of its affiliates, except as required for reasonable and customary use in describing and
redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
comply with Meta’s brand guidelines (currently accessible at
https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
of the Mark will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
respect to any derivative works and modifications of the Llama Materials that are made by you, as
between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or
results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
rights owned or licensable by you, then any licenses granted to you under this Agreement shall
terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
harmless Meta from and against any claim by any third party arising out of or related to your use or
distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
the State of California without regard to choice of law principles, and the UN Convention on Contracts
for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
exclusive jurisdiction of any dispute arising out of this Agreement.
### Meta Llama 3 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you
access or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of
this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)
#### Prohibited Uses
We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow
others to use, Meta Llama 3 to:
1. Violate the law or others’ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
2. Guns and illegal weapons (including weapon development)
3. Illegal drugs and regulated/controlled substances
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
3. Generating, promoting, or further distributing spam
4. Impersonating another individual without consent, authorization, or legal right
5. Representing that the use of Meta Llama 3 or outputs are human-generated
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation
of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)
* Reporting risky content generated by the model:
developers.facebook.com/llama_output_feedback
* Reporting bugs and security concerns: facebook.com/whitehat/info
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
|
binganao/ppo-LunarLander-v2 | binganao | 2024-04-20T05:07:12Z | 2 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-04-20T05:06:52Z | ---
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: 252.43 +/- 16.80
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
...
```
|
AlexWang99/byt5_add | AlexWang99 | 2024-04-20T04:58:26Z | 105 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/byt5-small",
"base_model:finetune:google/byt5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-20T03:34:27Z | ---
license: apache-2.0
base_model: google/byt5-small
tags:
- generated_from_trainer
model-index:
- name: byt5_add
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. -->
# byt5_add
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0003
- eval_runtime: 10.8156
- eval_samples_per_second: 924.594
- eval_steps_per_second: 1.202
- epoch: 51.0
- step: 1275
## 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: 800
- eval_batch_size: 800
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
Supersaiyan1729/financeLM_outputpath | Supersaiyan1729 | 2024-04-20T04:56:13Z | 125 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-19T13:42:26Z | ---
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: financeLM_outputpath
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. -->
# financeLM_outputpath
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3037
## 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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.0803 | 1.0 | 7031 | 1.0331 |
| 0.8 | 2.0 | 14062 | 1.1243 |
| 0.6646 | 3.0 | 21093 | 1.1960 |
| 0.5747 | 4.0 | 28125 | 1.2458 |
| 0.5094 | 5.0 | 35155 | 1.3037 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Swarnava/T5_base_NASA_ADS_title_v5 | Swarnava | 2024-04-20T04:48:59Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-base",
"base_model:finetune:google-t5/t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-19T18:34:42Z | ---
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: T5_base_NASA_ADS_title_v5
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. -->
# T5_base_NASA_ADS_title_v5
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7910
- Rouge1: 0.4285
- Rouge2: 0.2147
- Rougel: 0.3712
- Rougelsum: 0.3711
- Gen Len: 16.3966
## 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: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.1209 | 1.0 | 2535 | 1.9129 | 0.4133 | 0.2034 | 0.3581 | 0.3581 | 16.0037 |
| 1.9984 | 2.0 | 5070 | 1.8568 | 0.4138 | 0.2051 | 0.3608 | 0.3608 | 15.9065 |
| 1.9004 | 3.0 | 7605 | 1.8307 | 0.4222 | 0.2109 | 0.3675 | 0.3674 | 15.9252 |
| 1.8491 | 4.0 | 10140 | 1.8110 | 0.4199 | 0.209 | 0.3638 | 0.3638 | 16.1813 |
| 1.7823 | 5.0 | 12675 | 1.7972 | 0.4231 | 0.2107 | 0.3665 | 0.3664 | 16.2793 |
| 1.7302 | 6.0 | 15210 | 1.7924 | 0.427 | 0.2145 | 0.3704 | 0.3705 | 16.3819 |
| 1.6996 | 7.0 | 17745 | 1.7918 | 0.4284 | 0.2157 | 0.3712 | 0.3713 | 16.0767 |
| 1.6705 | 8.0 | 20280 | 1.7851 | 0.4252 | 0.2134 | 0.3682 | 0.3682 | 16.3485 |
| 1.6338 | 9.0 | 22815 | 1.7853 | 0.4291 | 0.2146 | 0.3721 | 0.372 | 16.398 |
| 1.6193 | 10.0 | 25350 | 1.7850 | 0.4297 | 0.2158 | 0.3726 | 0.3725 | 16.3821 |
| 1.5808 | 11.0 | 27885 | 1.7837 | 0.4274 | 0.2144 | 0.3708 | 0.3706 | 16.303 |
| 1.574 | 12.0 | 30420 | 1.7895 | 0.428 | 0.2151 | 0.3708 | 0.3709 | 16.3568 |
| 1.5544 | 13.0 | 32955 | 1.7898 | 0.4282 | 0.2152 | 0.3711 | 0.3711 | 16.412 |
| 1.5377 | 14.0 | 35490 | 1.7902 | 0.4287 | 0.2147 | 0.3709 | 0.3709 | 16.3917 |
| 1.5304 | 15.0 | 38025 | 1.7910 | 0.4285 | 0.2147 | 0.3712 | 0.3711 | 16.3966 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.19.1
|
reeddg/04-20-04-33-22 | reeddg | 2024-04-20T04:46:47Z | 0 | 0 | null | [
"tensorboard",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T04:36:21Z | ---
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 04-20-04-33-22
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. -->
# 04-20-04-33-22
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0014
- Accuracy: 1.0
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
## 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: 0.0002
- 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.7284 | 0.21 | 10 | 0.6353 | 0.5976 | 0.0 | 0.0 | 0.0 |
| 0.7191 | 0.42 | 20 | 0.5723 | 0.6098 | 1.0 | 0.0303 | 0.0588 |
| 0.6009 | 0.62 | 30 | 0.4573 | 0.7561 | 1.0 | 0.3939 | 0.5652 |
| 0.4025 | 0.83 | 40 | 0.2610 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1859 | 1.04 | 50 | 0.0880 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0584 | 1.25 | 60 | 0.0175 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0526 | 1.46 | 70 | 0.0054 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0127 | 1.67 | 80 | 0.0040 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0104 | 1.88 | 90 | 0.0026 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0036 | 2.08 | 100 | 0.0017 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0309 | 2.29 | 110 | 0.0015 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0023 | 2.5 | 120 | 0.0015 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0049 | 2.71 | 130 | 0.0014 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0017 | 2.92 | 140 | 0.0014 | 1.0 | 1.0 | 1.0 | 1.0 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
|
IntervitensInc/intv_l3_mk4 | IntervitensInc | 2024-04-20T04:44:25Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T04:39:08Z | ---
library_name: transformers
tags: []
---
# 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] |
DavidAU/TinyLlama-1.1B-chat-dare-v1-Q8_0-GGUF | DavidAU | 2024-04-20T04:41:31Z | 2 | 0 | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"l3utterfly/tinyllama-1.1b-layla-v1",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T04:41:21Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
- l3utterfly/tinyllama-1.1b-layla-v1
- llama-cpp
- gguf-my-repo
---
# DavidAU/TinyLlama-1.1B-chat-dare-v1-Q8_0-GGUF
This model was converted to GGUF format from [`abuelnasr/TinyLlama-1.1B-chat-dare-v1`](https://huggingface.co/abuelnasr/TinyLlama-1.1B-chat-dare-v1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/abuelnasr/TinyLlama-1.1B-chat-dare-v1) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/TinyLlama-1.1B-chat-dare-v1-Q8_0-GGUF --model tinyllama-1.1b-chat-dare-v1.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/TinyLlama-1.1B-chat-dare-v1-Q8_0-GGUF --model tinyllama-1.1b-chat-dare-v1.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m tinyllama-1.1b-chat-dare-v1.Q8_0.gguf -n 128
```
|
sparsh35/gemman1.12bnormalawq | sparsh35 | 2024-04-20T04:41:14Z | 76 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
] | text-generation | 2024-04-20T04:40:00Z | ---
library_name: transformers
tags: []
---
# 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] |
DavidAU/Heimer-dpo-TinyLlama-1.1B-Q8_0-GGUF | DavidAU | 2024-04-20T04:41:13Z | 3 | 0 | transformers | [
"transformers",
"gguf",
"TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
"abideen/Heimer-ipo-TinyLlama-1.1B",
"abideen/Heimer-kto-TinyLlama-1.1B",
"Intel/orca_dpo_pairs",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:Intel/orca_dpo_pairs",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T04:41:07Z | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
- abideen/Heimer-ipo-TinyLlama-1.1B
- abideen/Heimer-kto-TinyLlama-1.1B
- Intel/orca_dpo_pairs
- llama-cpp
- gguf-my-repo
datasets:
- Intel/orca_dpo_pairs
---
# DavidAU/Heimer-dpo-TinyLlama-1.1B-Q8_0-GGUF
This model was converted to GGUF format from [`abideen/Heimer-dpo-TinyLlama-1.1B`](https://huggingface.co/abideen/Heimer-dpo-TinyLlama-1.1B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/abideen/Heimer-dpo-TinyLlama-1.1B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/Heimer-dpo-TinyLlama-1.1B-Q8_0-GGUF --model heimer-dpo-tinyllama-1.1b.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Heimer-dpo-TinyLlama-1.1B-Q8_0-GGUF --model heimer-dpo-tinyllama-1.1b.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m heimer-dpo-tinyllama-1.1b.Q8_0.gguf -n 128
```
|
BuroIdentidadDigital/formaMigratoria_Frontal_v1 | BuroIdentidadDigital | 2024-04-20T04:17:20Z | 48 | 0 | transformers | [
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-04-20T04:11:19Z | ---
library_name: transformers
tags: []
---
# 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] |
jgrc3/pfeiffer_adapter_classification_trained_lr0_0001 | jgrc3 | 2024-04-20T04:07:03Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness",
"region:us"
] | null | 2024-04-20T04:07:00Z | ---
tags:
- roberta
- adapter-transformers
datasets:
- BigTMiami/amazon_helpfulness
---
# Adapter `jgrc3/pfeiffer_adapter_classification_trained_lr0_0001` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("jgrc3/pfeiffer_adapter_classification_trained_lr0_0001", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
AsemBadr/whisper-small-final-v2 | AsemBadr | 2024-04-20T04:03:42Z | 9 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ara",
"dataset:AsemBadr/GP",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-03-24T13:44:48Z | ---
language:
- ara
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- AsemBadr/GP
model-index:
- name: Whisper Small for Quran Recognition
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 for Quran Recognition
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Quran_Reciters 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: 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: 12000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.19.1
|
adrirw/trained_sentiment_model | adrirw | 2024-04-20T04:03:36Z | 119 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:twitter-sentiment-analysis",
"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 | 2024-04-18T18:53:31Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- twitter-sentiment-analysis
metrics:
- accuracy
model-index:
- name: trained_sentiment_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: twitter-sentiment-analysis
type: twitter-sentiment-analysis
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8366169950328366
---
<!-- 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. -->
# trained_sentiment_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the twitter-sentiment-analysis dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5841
- Accuracy: 0.8366
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.2239 | 1.0 | 7500 | 0.5493 | 0.8240 |
| 0.1769 | 2.0 | 15000 | 0.5841 | 0.8366 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_3_adapter | BigTMiami | 2024-04-20T04:00:24Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_10k_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T04:00:19Z | ---
tags:
- roberta
- adapter-transformers
datasets:
- BigTMiami/amazon_10k_helpfulness_dataset
---
# Adapter `BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_3_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_10k_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_10k_helpfulness_dataset/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_3_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
dallonf/Q-Taxi-v3 | dallonf | 2024-04-20T03:58:57Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-04-20T03:58:55Z | ---
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: 7.52 +/- 2.73
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="dallonf/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"])
```
|
BuroIdentidadDigital/formaMigratoria_Frontal_v0 | BuroIdentidadDigital | 2024-04-20T03:56:11Z | 48 | 0 | transformers | [
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-04-20T03:43:53Z | ---
library_name: transformers
tags: []
---
# 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] |
soareslance/mistral-7b-sft-lora-tom | soareslance | 2024-04-20T03:54:14Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.1",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T01:01:13Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
datasets:
- generator
model-index:
- name: mistral-7b-sft-lora-tom
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/soareslance/huggingface/runs/vv73wird)
# mistral-7b-sft-lora-tom
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.8562 | 2 | 1.9027 |
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1 |
michaelw37/sc45 | michaelw37 | 2024-04-20T03:53:25Z | 92 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T01:16:05Z | ---
library_name: transformers
tags: []
---
# 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] |
Sahil998/codegen-350M-mono-finetuned-python-18k-alpaca_50_percent_30pochs | Sahil998 | 2024-04-20T03:50:18Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T03:50:18Z | ---
library_name: transformers
tags: []
---
# 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] |
almak75/swin-tiny-patch4-window7-224-finetuned-eurosat | almak75 | 2024-04-20T03:50:08Z | 5 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-12-18T15:01:06Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8583333333333333
---
<!-- 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. -->
# swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3937
- Accuracy: 0.8583
## 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: 32
- eval_batch_size: 32
- 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6866 | 0.99 | 37 | 0.6202 | 0.6742 |
| 0.5892 | 2.0 | 75 | 0.5467 | 0.72 |
| 0.5195 | 2.99 | 112 | 0.4933 | 0.7483 |
| 0.4322 | 4.0 | 150 | 0.4787 | 0.765 |
| 0.3712 | 4.99 | 187 | 0.3829 | 0.8208 |
| 0.3162 | 6.0 | 225 | 0.3960 | 0.8133 |
| 0.3082 | 6.99 | 262 | 0.3591 | 0.8392 |
| 0.3038 | 8.0 | 300 | 0.3274 | 0.8467 |
| 0.2794 | 8.99 | 337 | 0.3533 | 0.8433 |
| 0.2596 | 10.0 | 375 | 0.3766 | 0.8258 |
| 0.2369 | 10.99 | 412 | 0.3392 | 0.8575 |
| 0.2503 | 12.0 | 450 | 0.3198 | 0.8625 |
| 0.2009 | 12.99 | 487 | 0.3438 | 0.8625 |
| 0.2195 | 14.0 | 525 | 0.3234 | 0.8617 |
| 0.2025 | 14.99 | 562 | 0.3758 | 0.855 |
| 0.1879 | 16.0 | 600 | 0.3909 | 0.8408 |
| 0.18 | 16.99 | 637 | 0.3642 | 0.8617 |
| 0.1545 | 18.0 | 675 | 0.3948 | 0.8567 |
| 0.171 | 18.99 | 712 | 0.3889 | 0.8525 |
| 0.1667 | 20.0 | 750 | 0.3883 | 0.8625 |
| 0.163 | 20.99 | 787 | 0.3743 | 0.8575 |
| 0.1682 | 22.0 | 825 | 0.3739 | 0.8592 |
| 0.1611 | 22.99 | 862 | 0.3623 | 0.8742 |
| 0.1348 | 24.0 | 900 | 0.3806 | 0.8592 |
| 0.1366 | 24.99 | 937 | 0.3849 | 0.865 |
| 0.1418 | 26.0 | 975 | 0.4049 | 0.8558 |
| 0.1096 | 26.99 | 1012 | 0.3849 | 0.8608 |
| 0.1347 | 28.0 | 1050 | 0.3926 | 0.8592 |
| 0.137 | 28.99 | 1087 | 0.3938 | 0.8592 |
| 0.1312 | 29.6 | 1110 | 0.3937 | 0.8583 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3
|
OzzyGT/RealVisXL_V4.0_inpainting | OzzyGT | 2024-04-20T03:43:06Z | 5,827 | 13 | diffusers | [
"diffusers",
"license:openrail++",
"diffusers:StableDiffusionXLInpaintPipeline",
"region:us"
] | image-to-image | 2024-04-20T03:37:36Z | ---
license: openrail++
---
This is the inpainting version of RealVisXL_V4 in diffusers "fp16" format.
Original model: https://huggingface.co/SG161222/RealVisXL_V4.0
|
AlignmentResearch/robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-25 | AlignmentResearch | 2024-04-20T03:39:29Z | 104 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-160m",
"base_model:finetune:EleutherAI/pythia-160m",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-04-20T03:39:13Z | ---
license: apache-2.0
tags:
- generated_from_trainer
base_model: EleutherAI/pythia-160m
model-index:
- name: robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-25
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. -->
# robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-25
This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
|
Warddamn2/Meta-Llama-2-13b-chat-hf | Warddamn2 | 2024-04-20T03:38:42Z | 5 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T02:23:50Z | ---
license: llama2
---
---
Full backup from [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
---
|
BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_2_adapter | BigTMiami | 2024-04-20T03:29:18Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_10k_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T03:29:07Z | ---
tags:
- roberta
- adapter-transformers
datasets:
- BigTMiami/amazon_10k_helpfulness_dataset
---
# Adapter `BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_2_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_10k_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_10k_helpfulness_dataset/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_2_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
baek26/cnn_dailymail_3864_bart-base | baek26 | 2024-04-20T03:26:44Z | 103 | 0 | transformers | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-base",
"base_model:finetune:facebook/bart-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-04-17T19:14:38Z | ---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: cnn_dailymail_3864_bart-base
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. -->
# cnn_dailymail_3864_bart-base
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9201
- Rouge1: 0.2472
- Rouge2: 0.1256
- Rougel: 0.2063
- Rougelsum: 0.2331
- Gen Len: 20.0
## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 1.2077 | 0.11 | 500 | 1.0668 | 0.2378 | 0.1128 | 0.1955 | 0.2228 | 20.0 |
| 1.1503 | 0.22 | 1000 | 1.0418 | 0.2376 | 0.1145 | 0.1964 | 0.223 | 20.0 |
| 1.1191 | 0.33 | 1500 | 1.0109 | 0.2409 | 0.1187 | 0.1995 | 0.2268 | 20.0 |
| 1.0828 | 0.45 | 2000 | 1.0048 | 0.2408 | 0.1192 | 0.2004 | 0.227 | 20.0 |
| 1.0546 | 0.56 | 2500 | 0.9911 | 0.2417 | 0.1206 | 0.2008 | 0.2278 | 20.0 |
| 1.0537 | 0.67 | 3000 | 0.9891 | 0.2418 | 0.1201 | 0.2014 | 0.2277 | 20.0 |
| 1.0643 | 0.78 | 3500 | 0.9895 | 0.2396 | 0.1194 | 0.1997 | 0.2259 | 20.0 |
| 1.0375 | 0.89 | 4000 | 0.9775 | 0.2434 | 0.122 | 0.2025 | 0.2293 | 20.0 |
| 1.013 | 1.0 | 4500 | 0.9728 | 0.244 | 0.1218 | 0.2029 | 0.2298 | 20.0 |
| 1.0247 | 1.11 | 5000 | 0.9705 | 0.243 | 0.1206 | 0.2019 | 0.2287 | 20.0 |
| 1.0374 | 1.23 | 5500 | 0.9642 | 0.2432 | 0.1217 | 0.2022 | 0.2292 | 20.0 |
| 1.0084 | 1.34 | 6000 | 0.9609 | 0.2437 | 0.1235 | 0.204 | 0.2299 | 20.0 |
| 1.0195 | 1.45 | 6500 | 0.9603 | 0.243 | 0.1221 | 0.2029 | 0.2291 | 20.0 |
| 0.9642 | 1.56 | 7000 | 0.9559 | 0.2438 | 0.1228 | 0.2035 | 0.2301 | 20.0 |
| 0.9903 | 1.67 | 7500 | 0.9540 | 0.243 | 0.1225 | 0.2029 | 0.2293 | 20.0 |
| 0.976 | 1.78 | 8000 | 0.9518 | 0.2434 | 0.1224 | 0.2025 | 0.2297 | 19.9997 |
| 1.0101 | 1.89 | 8500 | 0.9460 | 0.2452 | 0.1235 | 0.2042 | 0.231 | 20.0 |
| 0.9711 | 2.01 | 9000 | 0.9446 | 0.2431 | 0.1226 | 0.2032 | 0.2295 | 19.9995 |
| 0.9137 | 2.12 | 9500 | 0.9463 | 0.2459 | 0.1239 | 0.205 | 0.2318 | 20.0 |
| 0.9631 | 2.23 | 10000 | 0.9410 | 0.2451 | 0.1234 | 0.2043 | 0.2309 | 19.9999 |
| 0.9309 | 2.34 | 10500 | 0.9399 | 0.2446 | 0.1236 | 0.2042 | 0.2308 | 19.9991 |
| 0.9653 | 2.45 | 11000 | 0.9363 | 0.2444 | 0.1233 | 0.2039 | 0.2308 | 19.9999 |
| 0.9338 | 2.56 | 11500 | 0.9413 | 0.2439 | 0.1224 | 0.2028 | 0.2294 | 20.0 |
| 0.9373 | 2.67 | 12000 | 0.9334 | 0.245 | 0.1241 | 0.2047 | 0.2312 | 19.9996 |
| 0.9661 | 2.79 | 12500 | 0.9334 | 0.2456 | 0.1241 | 0.2051 | 0.2318 | 19.9999 |
| 0.9446 | 2.9 | 13000 | 0.9340 | 0.2447 | 0.1239 | 0.2045 | 0.2309 | 19.9999 |
| 0.9109 | 3.01 | 13500 | 0.9340 | 0.2445 | 0.1234 | 0.2041 | 0.2308 | 19.9999 |
| 0.8955 | 3.12 | 14000 | 0.9357 | 0.2459 | 0.1249 | 0.2055 | 0.2318 | 20.0 |
| 0.9163 | 3.23 | 14500 | 0.9319 | 0.2461 | 0.1239 | 0.205 | 0.2319 | 20.0 |
| 0.9059 | 3.34 | 15000 | 0.9320 | 0.2446 | 0.124 | 0.2044 | 0.2309 | 19.9997 |
| 0.8893 | 3.46 | 15500 | 0.9288 | 0.2462 | 0.1247 | 0.2053 | 0.2322 | 19.9999 |
| 0.8963 | 3.57 | 16000 | 0.9301 | 0.2441 | 0.124 | 0.2043 | 0.2306 | 20.0 |
| 0.8924 | 3.68 | 16500 | 0.9295 | 0.2431 | 0.1236 | 0.2038 | 0.2296 | 19.9997 |
| 0.8832 | 3.79 | 17000 | 0.9267 | 0.2457 | 0.1237 | 0.2049 | 0.2316 | 19.9999 |
| 0.8874 | 3.9 | 17500 | 0.9263 | 0.2458 | 0.125 | 0.2054 | 0.232 | 20.0 |
| 0.8464 | 4.01 | 18000 | 0.9272 | 0.2446 | 0.1234 | 0.2039 | 0.2305 | 20.0 |
| 0.8391 | 4.12 | 18500 | 0.9253 | 0.2453 | 0.1245 | 0.205 | 0.2313 | 20.0 |
| 0.8602 | 4.24 | 19000 | 0.9273 | 0.2464 | 0.1248 | 0.2055 | 0.2322 | 19.9997 |
| 0.8674 | 4.35 | 19500 | 0.9260 | 0.2449 | 0.1242 | 0.2047 | 0.2309 | 20.0 |
| 0.8634 | 4.46 | 20000 | 0.9261 | 0.2462 | 0.1248 | 0.2053 | 0.2322 | 20.0 |
| 0.8522 | 4.57 | 20500 | 0.9259 | 0.2456 | 0.1242 | 0.2052 | 0.2316 | 20.0 |
| 0.8532 | 4.68 | 21000 | 0.9256 | 0.2452 | 0.1242 | 0.2049 | 0.2315 | 20.0 |
| 0.8608 | 4.79 | 21500 | 0.9218 | 0.2446 | 0.1242 | 0.2049 | 0.2309 | 19.9997 |
| 0.8649 | 4.9 | 22000 | 0.9239 | 0.2461 | 0.1243 | 0.2047 | 0.2317 | 19.9997 |
| 0.8329 | 5.02 | 22500 | 0.9260 | 0.2456 | 0.1248 | 0.2052 | 0.2315 | 19.9999 |
| 0.8475 | 5.13 | 23000 | 0.9247 | 0.2449 | 0.1241 | 0.2045 | 0.2309 | 20.0 |
| 0.8595 | 5.24 | 23500 | 0.9246 | 0.2443 | 0.1239 | 0.2044 | 0.2306 | 20.0 |
| 0.8707 | 5.35 | 24000 | 0.9228 | 0.2458 | 0.1246 | 0.2054 | 0.2318 | 19.9997 |
| 0.8565 | 5.46 | 24500 | 0.9243 | 0.245 | 0.1241 | 0.2047 | 0.231 | 20.0 |
| 0.848 | 5.57 | 25000 | 0.9232 | 0.2464 | 0.1256 | 0.206 | 0.2324 | 20.0 |
| 0.8251 | 5.68 | 25500 | 0.9212 | 0.2465 | 0.1253 | 0.2057 | 0.2327 | 20.0 |
| 0.8352 | 5.8 | 26000 | 0.9203 | 0.245 | 0.1242 | 0.2043 | 0.2309 | 19.9996 |
| 0.837 | 5.91 | 26500 | 0.9178 | 0.2464 | 0.1247 | 0.2055 | 0.2321 | 19.9999 |
| 0.8233 | 6.02 | 27000 | 0.9204 | 0.2456 | 0.1247 | 0.2052 | 0.2318 | 20.0 |
| 0.8169 | 6.13 | 27500 | 0.9246 | 0.2454 | 0.1242 | 0.205 | 0.2314 | 20.0 |
| 0.8351 | 6.24 | 28000 | 0.9194 | 0.2453 | 0.1248 | 0.2052 | 0.2312 | 20.0 |
| 0.8275 | 6.35 | 28500 | 0.9221 | 0.2468 | 0.1255 | 0.2062 | 0.2329 | 19.9999 |
| 0.818 | 6.46 | 29000 | 0.9244 | 0.2456 | 0.1243 | 0.205 | 0.2316 | 20.0 |
| 0.8262 | 6.58 | 29500 | 0.9194 | 0.2471 | 0.1256 | 0.2064 | 0.233 | 20.0 |
| 0.8138 | 6.69 | 30000 | 0.9225 | 0.2469 | 0.1257 | 0.2062 | 0.233 | 20.0 |
| 0.8476 | 6.8 | 30500 | 0.9188 | 0.2467 | 0.1254 | 0.2059 | 0.2328 | 20.0 |
| 0.8376 | 6.91 | 31000 | 0.9216 | 0.2473 | 0.1255 | 0.2064 | 0.2331 | 20.0 |
| 0.7947 | 7.02 | 31500 | 0.9218 | 0.2471 | 0.1256 | 0.2061 | 0.2329 | 19.9999 |
| 0.7937 | 7.13 | 32000 | 0.9241 | 0.2465 | 0.1249 | 0.2057 | 0.2324 | 19.9996 |
| 0.8194 | 7.24 | 32500 | 0.9230 | 0.2471 | 0.1259 | 0.2063 | 0.2329 | 20.0 |
| 0.8122 | 7.36 | 33000 | 0.9204 | 0.2458 | 0.125 | 0.2055 | 0.232 | 19.9996 |
| 0.7676 | 7.47 | 33500 | 0.9232 | 0.2468 | 0.1253 | 0.206 | 0.2327 | 20.0 |
| 0.7772 | 7.58 | 34000 | 0.9226 | 0.2463 | 0.1251 | 0.2057 | 0.2323 | 20.0 |
| 0.809 | 7.69 | 34500 | 0.9197 | 0.2469 | 0.1255 | 0.2061 | 0.2329 | 19.9997 |
| 0.7839 | 7.8 | 35000 | 0.9205 | 0.2475 | 0.1261 | 0.2067 | 0.2334 | 19.9997 |
| 0.7936 | 7.91 | 35500 | 0.9186 | 0.2469 | 0.1254 | 0.2061 | 0.2327 | 19.9997 |
| 0.8108 | 8.02 | 36000 | 0.9215 | 0.2472 | 0.1253 | 0.206 | 0.2329 | 20.0 |
| 0.7987 | 8.14 | 36500 | 0.9219 | 0.2473 | 0.1254 | 0.2062 | 0.2331 | 19.9999 |
| 0.7881 | 8.25 | 37000 | 0.9213 | 0.2474 | 0.1253 | 0.206 | 0.233 | 20.0 |
| 0.8007 | 8.36 | 37500 | 0.9215 | 0.2474 | 0.1258 | 0.2064 | 0.2332 | 20.0 |
| 0.7789 | 8.47 | 38000 | 0.9226 | 0.2462 | 0.1252 | 0.2054 | 0.2321 | 20.0 |
| 0.8155 | 8.58 | 38500 | 0.9182 | 0.2465 | 0.1254 | 0.206 | 0.2325 | 19.9999 |
| 0.7863 | 8.69 | 39000 | 0.9187 | 0.2465 | 0.1252 | 0.2059 | 0.2323 | 19.9999 |
| 0.796 | 8.8 | 39500 | 0.9201 | 0.2469 | 0.1254 | 0.206 | 0.2327 | 19.9999 |
| 0.8003 | 8.92 | 40000 | 0.9197 | 0.2463 | 0.1252 | 0.2057 | 0.2323 | 20.0 |
| 0.803 | 9.03 | 40500 | 0.9206 | 0.2465 | 0.1253 | 0.2058 | 0.2323 | 19.9997 |
| 0.79 | 9.14 | 41000 | 0.9221 | 0.2467 | 0.1251 | 0.206 | 0.2326 | 19.9997 |
| 0.7605 | 9.25 | 41500 | 0.9211 | 0.247 | 0.1254 | 0.2059 | 0.2329 | 20.0 |
| 0.7543 | 9.36 | 42000 | 0.9214 | 0.2473 | 0.1258 | 0.2065 | 0.2333 | 19.9999 |
| 0.7959 | 9.47 | 42500 | 0.9203 | 0.2471 | 0.1255 | 0.2061 | 0.2332 | 19.9999 |
| 0.7826 | 9.58 | 43000 | 0.9205 | 0.2469 | 0.1256 | 0.206 | 0.2329 | 20.0 |
| 0.7835 | 9.7 | 43500 | 0.9198 | 0.2466 | 0.1252 | 0.2057 | 0.2326 | 20.0 |
| 0.7809 | 9.81 | 44000 | 0.9205 | 0.2469 | 0.1253 | 0.206 | 0.2328 | 20.0 |
| 0.7899 | 9.92 | 44500 | 0.9201 | 0.2472 | 0.1256 | 0.2063 | 0.2331 | 20.0 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
|
lodrick-the-lafted/Copus-2x8B | lodrick-the-lafted | 2024-04-20T03:21:42Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T00:04:35Z | ---
license: llama2
---
<img src=https://huggingface.co/lodrick-the-lafted/Copus-2x8B/resolve/main/copus.png>
MoE'd up:
- [dreamgen/opus-v1.2-llama-3-8b](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b)
- [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. |
NLPark/Test0_SLIDE | NLPark | 2024-04-20T03:15:42Z | 181 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T01:45:16Z | ---
language:
- en
pipeline_tag: text-generation
inference: true
library_name: transformers
license: cc-by-nc-sa-4.0
---
# Shi-Ci Language Identify & Decode Expositor
**8B**, Ruozhiba...
* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
**Chinese**
Released as an early preview of our v3 LLMs.
The v3 series covers the "Shi-Ci", "AnFeng" and "Cecilia" LLM products.
The sizes are labelled from small to large "Nano" "Leap" "Pattern" "Avocet "Robin" "Kestrel" |
foolunderscore/GlennAI-04.19.2024 | foolunderscore | 2024-04-20T03:13:44Z | 116 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T03:13:18Z | ---
library_name: transformers
tags: []
---
# 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]
|
BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_1_adapter | BigTMiami | 2024-04-20T03:07:58Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_10k_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T03:07:53Z | ---
tags:
- roberta
- adapter-transformers
datasets:
- BigTMiami/amazon_10k_helpfulness_dataset
---
# Adapter `BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_1_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_10k_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_10k_helpfulness_dataset/) dataset and includes a prediction head for classification.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/seq_bn_amz_10k_help_class_no_pretrain_1_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
denru/Meta-Llama-3-70B-Instruct-x2 | denru | 2024-04-20T03:05:22Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-70B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-20T02:33:10Z | ---
base_model:
- meta-llama/Meta-Llama-3-70B-Instruct
library_name: transformers
tags:
- mergekit
- merge
---
# merged_model
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 passthrough merge method.
### Models Merged
The following models were included in the merge:
* [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [0, 16]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [8, 24]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [16, 32]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [24, 40]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [32, 48]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [40, 56]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [48, 64]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [56, 72]
- sources:
- model: meta-llama/Meta-Llama-3-70B-Instruct
layer_range: [64, 80]
merge_method: passthrough
dtype: float16
```
|
Subsets and Splits