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 |
|---|---|---|---|---|---|---|---|---|---|
xian79/ppo-LunarLander | xian79 | 2023-06-30T16:32:08Z | 1 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T16:31:49Z | ---
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: 249.66 +/- 16.47
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
...
```
|
julian-schelb/roberta-ner-multilingual | julian-schelb | 2023-06-30T16:08:05Z | 866 | 10 | transformers | [
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"token-classification",
"roberta",
"ner",
"nlp",
"en",
"de",
"fr",
"zh",
"it",
"es",
"hi",
"bn",
"ar",
"ru",
"uk",
"pt",
"ur",
"id",
"ja",
"ne",
"nl",
"tr",
"ca",
"bg",
"yue",
"dataset:wikiann",
"arxiv:1911.02116",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2022-09-06T19:53:00Z | ---
language:
- en
- de
- fr
- zh
- it
- es
- hi
- bn
- ar
- ru
- uk
- pt
- ur
- id
- ja
- ne
- nl
- tr
- ca
- bg
- yue
widget:
- text: >-
In December 1903 in France the Royal Swedish Academy of Sciences awarded
Pierre Curie, Marie Curie, and Henri Becquerel the Nobel Prize in Physics.
- text: >-
Für Richard Phillips Feynman war es immer wichtig in New York, die
unanschaulichen Gesetzmäßigkeiten der Quantenphysik Laien und Studenten
nahezubringen und verständlich zu machen.
- text: >-
Terence David John Pratchett est né le 28 avril 1948 à Beaconsfield dans le
Buckinghamshire, en Angleterre.
- text: >-
北京市，通称北京（汉语拼音：Běijīng；邮政式拼音：Peking），简称“京”，是中华人民共和国的首都及直辖市，是该国的政治、文化、科技、教育、军事和国际交往中心，是一座全球城市，是世界人口第三多的城市和人口最多的首都，具有重要的国际影响力，同時也是目前世界唯一的“双奥之城”，即唯一既主办过夏季
tags:
- roberta
- ner
- nlp
license: mit
datasets:
- wikiann
metrics:
- f1
- precision
- accuracy
- recall
---
# RoBERTa for Multilingual Named Entity Recognition
## Model Description
This model detects entities by classifying every token according to the IOB format:
```python
['O', 'B-PER', 'I-PER', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC']
```
You can find the code in [this](https://github.com/julianschelb/roberta-ner-multilingual) GitHub repository.
## Training Data
This model was fine-tuned on a portion of the [wikiann](https://huggingface.co/datasets/wikiann) dataset corresponding to the following languages:
```python
["en","de", "fr",
"zh", "it", "es",
"hi", "bn", "ar",
"ru", "uk", "pt",
"ur", "id", "ja",
"ne", "nl", "tr",
"ca", "bg", "zh-yue"]
```
The model was fine-tuned on 375.100 sentences in the training set, with a validation set of 173.100 examples. Performance metrics reported are based on additional 173.100 examples. The complete WikiANN dataset includes training examples for 282 languages and was constructed from Wikipedia. Training examples are extracted in an automated manner, exploiting entities mentioned in Wikipedia articles, often are formatted as hyperlinks to the source article. Provided NER tags are in the IOB2 format. Named entities are classified as location (LOC), person (PER), or organization (ORG).
## Evaluation Results
This model achieves the following results (meassured using the test split of the [wikiann](https://huggingface.co/datasets/wikiann) dataset):
```python
{'LOC': {'f1': 0.8994491397524903,
'number': 184430,
'precision': 0.8941572985543279,
'recall': 0.9048039906739684},
'ORG': {'f1': 0.829114679375883,
'number': 129760,
'precision': 0.8283525257886599,
'recall': 0.8298782367447596},
'PER': {'f1': 0.9115096398413828,
'number': 130471,
'precision': 0.9043545174723882,
'recall': 0.9187788857293958},
'overall_accuracy': 0.9398182274831388,
'overall_f1': 0.8825581369330908,
'overall_precision': 0.8781215422873389,
'overall_recall': 0.8870397898623895}
```
## Usage
You can load this model by using the AutoTokenize and AutoModelForTokenClassification classes:
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("julian-schelb/roberta-ner-multilingual/", add_prefix_space=True)
model = AutoModelForTokenClassification.from_pretrained("julian-schelb/roberta-ner-multilingual/")
text = "In December 1903 in France the Royal Swedish Academy of Sciences awarded Pierre Curie, Marie Curie, and Henri Becquerel the Nobel Prize in Physics."
inputs = tokenizer(
text,
add_special_tokens=False,
return_tensors="pt"
)
with torch.no_grad():
logits = model(**inputs).logits
predicted_token_class_ids = logits.argmax(-1)
# Note that tokens are classified rather then input words which means that
# there might be more predicted token classes than words.
# Multiple token classes might account for the same word
predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
predicted_tokens_classes
```
## About RoBERTa
This model is a fine-tuned version of [XLM-RoBERTa](https://huggingface.co/xlm-roberta-large). The original model was pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper [Unsupervised Cross-lingual Representation Learning at Scale](https://arxiv.org/abs/1911.02116) by Conneau et al. and first released in [this repository](https://github.com/pytorch/fairseq/tree/master/examples/xlmr).
RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.
More precisely, it was pretrained with the Masked language modeling (MLM) objective. Taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
This way, the model learns an inner representation of 100 languages that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the XLM-RoBERTa model as inputs.
#### Limitations and Bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Related Papers
* Pan, X., Zhang, B., May, J., Nothman, J., Knight, K., & Ji, H. (2017). Cross-lingual Name Tagging and Linking for 282 Languages. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1946–1958). Association for Computational Linguistics.
* Rahimi, A., Li, Y., & Cohn, T. (2019). Massively Multilingual Transfer for NER. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 151–164). Association for Computational Linguistics.
* Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V.. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach.
## Citation
This model has been fine-tuned for the research paper indicated below:
```bibtex
@inproceedings{schelbECCEEntitycentricCorpus2022,
title = {{ECCE}: {Entity}-centric {Corpus} {Exploration} {Using} {Contextual} {Implicit} {Networks}},
url = {https://dl.acm.org/doi/10.1145/3487553.3524237},
booktitle = {Companion {Proceedings} of the {Web} {Conference} 2022},
author = {Schelb, Julian and Ehrmann, Maud and Romanello, Matteo and Spitz, Andreas},
year = {2022},
}
```
|
jliu596/ppo-LunarLander-v2 | jliu596 | 2023-06-30T16:04:54Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T16:04:34Z | ---
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: 263.97 +/- 36.81
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
...
```
|
igoroliveira/Huggy_igoroliv | igoroliveira | 2023-06-30T16:01:06Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2023-06-30T16:00:56Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: igoroliveira/Huggy_igoroliv
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
pchiva/q-Taxi-v3 | pchiva | 2023-06-30T15:45:52Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T15:39:05Z | ---
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: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="pchiva/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"])
```
|
PiXeL99/falcon-7b-qlora-telecom | PiXeL99 | 2023-06-30T15:44:30Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T15:44:25Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
dp15/huggyFace-v-first | dp15 | 2023-06-30T15:33:25Z | 11 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2023-06-30T15:33:02Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: dp15/huggyFace-v-first
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
tmpupload/superhot-7b-8k-no-rlhf-test-GPTQ | tmpupload | 2023-06-30T15:32:41Z | 5 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-30T13:05:28Z | ---
license: other
---
# superhot-7b-8k-4bit--1g-safetensors
**Note: Maximum sequence length (max_seq_len) and compression factor (compress_pos_emb) need to be set to 8192 (or lower) and 4.**
Merged base LLaMA and LoRA with this:
https://github.com/tloen/alpaca-lora
Base LLaMA 7B:
https://huggingface.co/huggyllama/llama-7b
SuperHOT 7B 8k no-rlhf-test LoRA:
https://huggingface.co/kaiokendev/superhot-7b-8k-no-rlhf-test
``` sh
BASE_MODEL=huggyllama_llama-7b LORA=kaiokendev_superhot-7b-8k-no-rlhf-test python export_hf_checkpoint.py
```
Quantized with AutoGPTQ:
https://github.com/PanQiWei/AutoGPTQ
``` sh
python quant_with_alpaca.py --pretrained_model_dir superhot-7b-8k-safetensors --quantized_model_dir superhot-7b-8k-no-rlhf-test-GPTQ --bits 4 --group_size -1 --desc_act --num_samples 256 --save_and_reload
```
Perplexity:
```
CUDA_VISIBLE_DEVICES=0 python test_benchmark_inference.py \
-d /workspace/models/superhot-7b-8k-no-rlhf-test-GPTQ \
-ppl \
-ppl_ds datasets/wikitext2.txt \
-l 8192 \
-cpe 4 \
-ppl_cn 40 \
-ppl_cs 8192 \
-ppl_ct 8192
-- Perplexity:
-- - Dataset: datasets/wikitext2.txt
-- - Chunks: 40
-- - Chunk size: 8192 -> 8192
-- - Chunk overlap: 0
-- - Min. chunk size: 50
-- - Key: text
-- Tokenizer: /workspace/models/superhot-7b-8k-no-rlhf-test-GPTQ/tokenizer.model
-- Model config: /workspace/models/superhot-7b-8k-no-rlhf-test-GPTQ/config.json
-- Model: /workspace/models/superhot-7b-8k-no-rlhf-test-GPTQ/4bit.safetensors
-- Sequence length: 8192
-- RoPE compression factor: 4.0
-- Tuning:
-- --matmul_recons_thd: 8
-- --fused_mlp_thd: 2
-- --sdp_thd: 8
-- Options: ['perplexity']
** Time, Load model: 2.74 seconds
** Time, Load tokenizer: 0.01 seconds
-- Groupsize (inferred): None
-- Act-order (inferred): no
!! Model has empty group index (discarded)
** VRAM, Model: [cuda:0] 3,652.09 MB
-- Loading dataset...
-- Testing 40 chunks....
** Perplexity: 7.0522
```
|
pchiva/q-FrozenLake-v1-4x4-noSlippery | pchiva | 2023-06-30T15:31:56Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T15:31:54Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="pchiva/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GGML | TheBloke | 2023-06-30T15:13:30Z | 0 | 7 | null | [
"license:other",
"region:us"
] | null | 2023-06-30T13:45:41Z | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Minlik's Chinese Alpaca 33B Merged GGML
These files are GGML format model files for [Minlik's Chinese Alpaca 33B Merged](https://huggingface.co/minlik/chinese-alpaca-33b-merged).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however work is still being done to find the optimal implementation.
To use the increased context with KoboldCpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
**NOTE**: Increased context length is an area seeing rapid developments and improvements. It is quite possible that these models may be superseded by new developments in the coming days. If that's the case, I will remove them, or update this README as appropriate.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/minlik/chinese-alpaca-33b-merged)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
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
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q4_0.bin | q4_0 | 4 | 18.44 GB | 20.94 GB | Original llama.cpp quant method, 4-bit. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q4_1.bin | q4_1 | 4 | 20.48 GB | 22.98 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q5_0.bin | q5_0 | 5 | 22.53 GB | 25.03 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q5_1.bin | q5_1 | 5 | 24.58 GB | 27.08 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q8_0.bin | q8_0 | 8 | 34.82 GB | 37.32 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**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.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas --gpulayers 100 chinese-alpaca-33b-superhot-8k.ggmlv3.q4_K_M.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
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.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Minlik's Chinese Alpaca 33B Merged
加入中文词表并继续预训练中文Embedding，并在此基础上继续使用指令数据集finetuning，得到的中文Alpaca-33B模型。
模型转换用到的相关base及lora模型如下：
- base-model: elinas/llama-30b-hf-transformers-4.29
- lora-model: ziqingyang/chinese-alpaca-lora-33b
详情可参考：https://github.com/ymcui/Chinese-LLaMA-Alpaca/releases/tag/v4.0
### 使用方法参考
1. 安装模块包
```bash
pip install sentencepiece
pip install transformers>=4.28.0
```
2. 生成文本
```python
import torch
import transformers
from transformers import LlamaTokenizer, LlamaForCausalLM
def generate_prompt(text):
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{text}
### Response:"""
tokenizer = LlamaTokenizer.from_pretrained('minlik/chinese-alpaca-33b-merged')
model = LlamaForCausalLM.from_pretrained('minlik/chinese-alpaca-33b-merged').half().to('cuda')
model.eval()
text = '第一个登上月球的人是谁？'
prompt = generate_prompt(text)
input_ids = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
with torch.no_grad():
output_ids = model.generate(
input_ids=input_ids,
max_new_tokens=128,
temperature=1,
top_k=40,
top_p=0.9,
repetition_penalty=1.15
).cuda()
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output.replace(prompt, '').strip())
```
|
lige/lige_models | lige | 2023-06-30T15:09:22Z | 0 | 1 | diffusers | [
"diffusers",
"stable-diffusion",
"text-to-image",
"zh",
"en",
"license:agpl-3.0",
"region:us"
] | text-to-image | 2023-02-01T14:18:03Z | ---
license: agpl-3.0
language:
- zh
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
---
No paying, for sharing.
免费，共享。
如果你喜欢这个项目，请点击喜欢。
If you like this project, please click like.
link to github: https://github.com/ligerye/lige_models
你可以下载并使用这些模型，但是必须保证不用于任何盈利用途，该项目使用AGPL-V3许可证。
You can download and use these models, but you must ensure that they are not used for any profitable purpose. The project uses AGPL-V3 license. |
S3S3/poca-SoccerTwos | S3S3 | 2023-06-30T15:09:16Z | 2 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2023-06-30T15:09:13Z | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: S3S3/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
lnair/graphormer-ogbg-molhiv | lnair | 2023-06-30T15:03:49Z | 34 | 0 | transformers | [
"transformers",
"pytorch",
"graphormer",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T14:50:08Z | ---
tags:
- generated_from_trainer
model-index:
- name: graphormer-ogbg-molhiv
results: []
---
# graphormer-ogbg-molhiv
This model was trained from `clefourrier/pcqm4mv2_graphormer_base` on the `OGB/ogbg-molhiv` dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0728
- eval_runtime: 464.6027
- eval_samples_per_second: 8.853
- eval_steps_per_second: 0.555
- step: 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: 512
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 5120
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
|
davanstrien/autotrain-color-image-dating-55447129537 | davanstrien | 2023-06-30T15:00:05Z | 190 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"swin",
"image-classification",
"autotrain",
"vision",
"dataset:biglam/dating-historical-color-images",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-05-05T09:01:46Z | ---
tags:
- autotrain
- vision
- image-classification
datasets:
- biglam/dating-historical-color-images
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 1.602513246354456
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 55447129537
- CO2 Emissions (in grams): 1.6025
## Validation Metrics
- Loss: 0.958
- Accuracy: 0.615
- Macro F1: 0.615
- Micro F1: 0.615
- Weighted F1: 0.615
- Macro Precision: 0.618
- Micro Precision: 0.615
- Weighted Precision: 0.618
- Macro Recall: 0.615
- Micro Recall: 0.615
- Weighted Recall: 0.615 |
coreml-community/coreml-MyMerge-v1_cn | coreml-community | 2023-06-30T14:53:29Z | 0 | 3 | null | [
"coreml",
"stable-diffusion",
"text-to-image",
"not-for-all-eyes",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-06-30T03:09:04Z | ---
license: creativeml-openrail-m
tags:
- coreml
- stable-diffusion
- text-to-image
- not-for-all-eyes
---
# Core ML Converted Model:
- This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML).
- Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images.
- `split_einsum` version is compatible with all compute unit options including Neural Engine.
- `original` version is only compatible with `CPU & GPU` option.
- Custom resolution versions are tagged accordingly.
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model.
- This model was converted with a `vae-encoder` for use with `image2image`.
- This model is `fp16`.
- Not all features and/or results may be available in `CoreML` format.
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
- This model does not include a `safety checker` (for NSFW content).
- This model can be used with ControlNet.
<br>
# MyMerge-v1_cn:
MyMerge-v1 is a merge of 8 NSFW models from Civitai, all having open use licenses for non-commercial purposes. It was merged only from models that permit merging and other derivatives, and that allow for the uncredited free use of generated images. Hosting this model on for-profit image generation services/sites is, however, not permitted, due to restrictions inherited from one of the source models. This model does not contain ChillOut Mix, or other models which have a restrictive license.
The model is better suited to producing photo-realistic images than anime or other 2d illustration style images. Most of the source models were trained on 512x512 images. As you move towards 768x768, you will find that some generations may begin to distort.
Becauseof the NSFW nature of this model, sample images are not provided here. Refer to HassanBlend, Liberty, URPM, etc. at CivitAI to see where this model comes from and the type of image content that it is suited for.
|
TheBloke/mpt-7b-chat-GGML | TheBloke | 2023-06-30T14:46:23Z | 0 | 9 | null | [
"Composer",
"MosaicML",
"llm-foundry",
"dataset:jeffwan/sharegpt_vicuna",
"dataset:Hello-SimpleAI/HC3",
"dataset:tatsu-lab/alpaca",
"dataset:Anthropic/hh-rlhf",
"dataset:victor123/evol_instruct_70k",
"arxiv:2205.14135",
"arxiv:2108.12409",
"arxiv:2010.04245",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2023-06-30T13:44:00Z | ---
license: cc-by-nc-sa-4.0
datasets:
- jeffwan/sharegpt_vicuna
- Hello-SimpleAI/HC3
- tatsu-lab/alpaca
- Anthropic/hh-rlhf
- victor123/evol_instruct_70k
tags:
- Composer
- MosaicML
- llm-foundry
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# MosaicML's MPT-7B-Chat GGML
These files are GGML format model files for [MosaicML's MPT-7B-Chat](https://huggingface.co/mosaicml/mpt-7b-chat).
Please note that these GGMLs are **not compatible with llama.cpp, or currently with text-generation-webui**. Please see below for a list of tools known to work with these model files.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
**Note**: Please make sure you're using KoboldCpp version 1.32.3 or later, as a number of MPT-related bugs are fixed.
## Repositories available
* [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/mpt-7B-chat-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mosaicml/mpt-7b-chat)
## Prompt template
```
<|im_start|>system
A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.<|im_end|>
<|im_start|>user
prompt goes here<|im_end|>
<|im_start|>assistant
```
## A note regarding context length: 4K
The base model has an 4K context length.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 4K context if you manually set it to 4K by adjusting the text box above the slider, like in this example:
(Set it to 4K, not 8K for this model.)
<!-- compatibility_ggml start -->
## Compatibilty
These files are **not** compatible with text-generation-webui, llama.cpp, or llama-cpp-python.
Currently they can be used with:
* KoboldCpp, a powerful inference engine based on llama.cpp, with good UI and GPU accelerated support for MPT models: [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers)
* The LoLLMS Web UI which uses ctransformers: [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
## Tutorial for using LoLLMS Web UI
* [Text tutorial, written by **Lucas3DCG**](https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/discussions/2#6475d914e9b57ce0caa68888)
* [Video tutorial, by LoLLMS Web UI's author **ParisNeo**](https://www.youtube.com/watch?v=ds_U0TDzbzI)
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| mpt-7b-chat.ggmlv0.q4_0.bin | q4_0 | 4 | 16.85 GB | 19.35 GB | 4-bit. |
| mpt-7b-chat.ggmlv0.q4_1.bin | q4_1 | 4 | 18.73 GB | 21.23 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| mpt-7b-chat.ggmlv0.q5_0.bin | q5_0 | 5 | 20.60 GB | 23.10 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| mpt-7b-chat.ggmlv0.q5_1.bin | q5_1 | 5 | 22.47 GB | 24.97 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| mpt-7b-chat.ggmlv0.q8_0.bin | q8_0 | 8 | 31.83 GB | 34.33 GB | 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**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.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
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.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: MosaicML's MPT-7B-chat
# MPT-7B-Chat
MPT-7B-Chat is a chatbot-like model for dialogue generation.
It was built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on the [ShareGPT-Vicuna](https://huggingface.co/datasets/jeffwan/sharegpt_vicuna), [HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3),
[Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf), and [Evol-Instruct](https://huggingface.co/datasets/victor123/evol_instruct_70k) datasets.
* License: _CC-By-NC-SA-4.0_ (non-commercial use only)
* [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-7b-chat)
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
## Model Date
May 5, 2023
## Model License
_CC-By-NC-SA-4.0_ (non-commercial use only)
## Documentation
* [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](https://www.mosaicml.com/blog/mpt-7b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
### Example Dialogue
**SamIAm85**:
>I want you to come up with a tweet based on this summary of the article:
>"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.
>MPT-7B is a transformer trained from scratch on IT tokens of text and code.
>It is open source and it matches the quality of LLaMA-7B.
>MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.
>Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.
>For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!
**MPT-7B-Instruct**:
>Here's my suggestion for a tweet:
>"Exciting news! @MosaicML has launched #MPT_7B - a new standard for open-source LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: https://bit.ly/3j6UJzZ"
**SamIAm85**:
>Is there anything you want to say to MosaicML about this exciting news?
**MPT-7B-Instruct**:
> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.
> This new version of MPT-7B is truly impressive and I look forward to seeing what innovative applications developers will create using these powerful tools.
> Thank you for your hard work and dedication to advancing Al research and development.
## How to Use
This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-7b-chat',
trust_remote_code=True
)
```
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method.
This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package.
`MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more.
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-7b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton'
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
Although the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-7b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 6.7B |
|n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 50432 |
| sequence length | 2048 |
### Training Configuration
This model was trained on 8 A100-80GBs for about 8.2 hours, followed by training for 6.7 hours on 32 A100-40GBs using the [MosaicML Platform](https://www.mosaicml.com/platform).
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-7B-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-7B-Chat was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Acknowledgements
This model was finetuned by Sam Havens and the MosaicML NLP team
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b).
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-7B: A New Standard for Open-Source,
ly Usable LLMs},
year = {2023},
url = {www.mosaicml.com/blog/mpt-7b},
note = {Accessed: 2023-03-28}, % change this date
urldate = {2023-03-28} % change this date
}
```
|
aroot/mbart-finetuned-eng-guj | aroot | 2023-06-30T14:30:51Z | 3 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | 2023-06-22T00:44:05Z | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-guj
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-finetuned-eng-guj
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5996
- Bleu: 1.8882
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
jiekeshi/GraphCodeBERT-Adversarial-Finetuned-Authorship-Attribution | jiekeshi | 2023-06-30T14:30:37Z | 0 | 0 | null | [
"pytorch",
"arxiv:2201.08698",
"license:mit",
"region:us"
] | null | 2023-06-30T14:04:53Z | ---
license: mit
---
This is the adversarially finetuned version of GraphCodeBERT that has been trained for for the Authorship Attribution task using [Google Code Jam](https://link.springer.com/chapter/10.1007/978-3-319-66402-6_6) dataset.
The adversarial examples used for finetuning are generated from our ICSE 2022 paper titled ["**Natural Attack for Pre-trained Models of Code**"](https://arxiv.org/abs/2201.08698).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/attack-pretrain-models-of-code**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{10.1145/3510003.3510146,
author = {Yang, Zhou and Shi, Jieke and He, Junda and Lo, David},
title = {Natural Attack for Pre-Trained Models of Code},
year = {2022},
isbn = {9781450392211},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3510003.3510146},
doi = {10.1145/3510003.3510146},
abstract = {Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.In this paper, we propose ALERT (Naturalness Aware Attack), a black-box attack that adversarially transforms inputs to make victim models produce wrong outputs. Different from prior works, this paper considers the natural semantic of generated examples at the same time as preserving the operational semantic of original inputs. Our user study demonstrates that human developers consistently consider that adversarial examples generated by ALERT are more natural than those generated by the state-of-the-art work by Zhang et al. that ignores the naturalness requirement. On attacking CodeBERT, our approach can achieve attack success rates of 53.62\%, 27.79\%, and 35.78\% across three downstream tasks: vulnerability prediction, clone detection and code authorship attribution. On GraphCodeBERT, our approach can achieve average success rates of 76.95\%, 7.96\% and 61.47\% on the three tasks. The above outperforms the baseline by 14.07\% and 18.56\% on the two pre-trained models on average. Finally, we investigated the value of the generated adversarial examples to harden victim models through an adversarial fine-tuning procedure and demonstrated the accuracy of CodeBERT and GraphCodeBERT against ALERT-generated adversarial examples increased by 87.59\% and 92.32\%, respectively.},
booktitle = {Proceedings of the 44th International Conference on Software Engineering},
pages = {1482–1493},
numpages = {12},
keywords = {pre-trained models, adversarial attack, genetic algorithm},
location = {Pittsburgh, Pennsylvania},
series = {ICSE '22}
}
``` |
jiekeshi/CodeBERT-Adversarial-Finetuned-Clone-Detection | jiekeshi | 2023-06-30T14:24:23Z | 0 | 0 | null | [
"pytorch",
"arxiv:2201.08698",
"license:mit",
"region:us"
] | null | 2023-06-30T14:09:49Z | ---
license: mit
---
This is the adversarially finetuned version of CodeBERT that has been trained for for the Clone Detection task using [BigCloneBench](https://github.com/clonebench/BigCloneBench.git) dataset.
The adversarial examples used for finetuning are generated from our ICSE 2022 paper titled ["**Natural Attack for Pre-trained Models of Code**"](https://arxiv.org/abs/2201.08698).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/attack-pretrain-models-of-code**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{10.1145/3510003.3510146,
author = {Yang, Zhou and Shi, Jieke and He, Junda and Lo, David},
title = {Natural Attack for Pre-Trained Models of Code},
year = {2022},
isbn = {9781450392211},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3510003.3510146},
doi = {10.1145/3510003.3510146},
abstract = {Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.In this paper, we propose ALERT (Naturalness Aware Attack), a black-box attack that adversarially transforms inputs to make victim models produce wrong outputs. Different from prior works, this paper considers the natural semantic of generated examples at the same time as preserving the operational semantic of original inputs. Our user study demonstrates that human developers consistently consider that adversarial examples generated by ALERT are more natural than those generated by the state-of-the-art work by Zhang et al. that ignores the naturalness requirement. On attacking CodeBERT, our approach can achieve attack success rates of 53.62\%, 27.79\%, and 35.78\% across three downstream tasks: vulnerability prediction, clone detection and code authorship attribution. On GraphCodeBERT, our approach can achieve average success rates of 76.95\%, 7.96\% and 61.47\% on the three tasks. The above outperforms the baseline by 14.07\% and 18.56\% on the two pre-trained models on average. Finally, we investigated the value of the generated adversarial examples to harden victim models through an adversarial fine-tuning procedure and demonstrated the accuracy of CodeBERT and GraphCodeBERT against ALERT-generated adversarial examples increased by 87.59\% and 92.32\%, respectively.},
booktitle = {Proceedings of the 44th International Conference on Software Engineering},
pages = {1482–1493},
numpages = {12},
keywords = {pre-trained models, adversarial attack, genetic algorithm},
location = {Pittsburgh, Pennsylvania},
series = {ICSE '22}
}
``` |
jiekeshi/GraphCodeBERT-Adversarial-Finetuned-Vulnerability-Prediction | jiekeshi | 2023-06-30T14:22:24Z | 0 | 0 | null | [
"pytorch",
"arxiv:2201.08698",
"license:mit",
"region:us"
] | null | 2023-06-30T14:16:04Z | ---
license: mit
---
This is the adversarially finetuned version of GraphCodeBERT that has been trained for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The adversarial examples used for finetuning are generated from our ICSE 2022 paper titled ["**Natural Attack for Pre-trained Models of Code**"](https://arxiv.org/abs/2201.08698).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/attack-pretrain-models-of-code**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{10.1145/3510003.3510146,
author = {Yang, Zhou and Shi, Jieke and He, Junda and Lo, David},
title = {Natural Attack for Pre-Trained Models of Code},
year = {2022},
isbn = {9781450392211},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3510003.3510146},
doi = {10.1145/3510003.3510146},
abstract = {Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.In this paper, we propose ALERT (Naturalness Aware Attack), a black-box attack that adversarially transforms inputs to make victim models produce wrong outputs. Different from prior works, this paper considers the natural semantic of generated examples at the same time as preserving the operational semantic of original inputs. Our user study demonstrates that human developers consistently consider that adversarial examples generated by ALERT are more natural than those generated by the state-of-the-art work by Zhang et al. that ignores the naturalness requirement. On attacking CodeBERT, our approach can achieve attack success rates of 53.62\%, 27.79\%, and 35.78\% across three downstream tasks: vulnerability prediction, clone detection and code authorship attribution. On GraphCodeBERT, our approach can achieve average success rates of 76.95\%, 7.96\% and 61.47\% on the three tasks. The above outperforms the baseline by 14.07\% and 18.56\% on the two pre-trained models on average. Finally, we investigated the value of the generated adversarial examples to harden victim models through an adversarial fine-tuning procedure and demonstrated the accuracy of CodeBERT and GraphCodeBERT against ALERT-generated adversarial examples increased by 87.59\% and 92.32\%, respectively.},
booktitle = {Proceedings of the 44th International Conference on Software Engineering},
pages = {1482–1493},
numpages = {12},
keywords = {pre-trained models, adversarial attack, genetic algorithm},
location = {Pittsburgh, Pennsylvania},
series = {ICSE '22}
}
``` |
ammag/Reinforce-Cart | ammag | 2023-06-30T14:21:50Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T14:21:46Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Cart
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 80.70 +/- 21.97
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
farzadd/falcon-7b-test_finetune_QA_Medical_4pages_more_steps | farzadd | 2023-06-30T14:16:04Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T14:15:58Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
WALIDALI/rahalistaly | WALIDALI | 2023-06-30T14:13:00Z | 31 | 1 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-30T14:09:18Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### rahalistaly Dreambooth model trained by WALIDALI with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
odiaz1066/LunarLander-v2-LunarLander-Show-seed42 | odiaz1066 | 2023-06-30T14:05:23Z | 0 | 0 | cleanrl | [
"cleanrl",
"tensorboard",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T14:05:19Z | ---
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 227.09 +/- 33.24
name: mean_reward
verified: false
---
# (CleanRL) **DQN** Agent Playing **LunarLander-v2**
This is a trained model of a DQN agent playing LunarLander-v2.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/LunarLander-Show.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[LunarLander-Show]"
python -m cleanrl_utils.enjoy --exp-name LunarLander-Show --env-id LunarLander-v2
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/dqn.py
curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/pyproject.toml
curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/poetry.lock
poetry install --all-extras
python dqn.py --track --save-model --capture-video --exp-name LunarLander-Show --seed 42 --env-id LunarLander-v2 --upload-model --hf-entity odiaz1066
```
# Hyperparameters
```python
{'batch_size': 128,
'buffer_size': 10000,
'capture_video': True,
'cuda': True,
'end_e': 0.05,
'env_id': 'LunarLander-v2',
'exp_name': 'LunarLander-Show',
'exploration_fraction': 0.5,
'gamma': 0.99,
'hf_entity': 'odiaz1066',
'learning_rate': 0.00025,
'learning_starts': 10000,
'num_envs': 1,
'save_model': True,
'seed': 42,
'start_e': 1,
'target_network_frequency': 500,
'tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 500000,
'track': True,
'train_frequency': 10,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'lagomorph'}
```
|
lukaszkolodziejczyk/q-FrozenLake-v1-4x4-noSlippery | lukaszkolodziejczyk | 2023-06-30T14:01:39Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T14:01:37Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="lukaszkolodziejczyk/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
MarieAngeA13/Sentiment_Analysis | MarieAngeA13 | 2023-06-30T13:58:25Z | 5 | 0 | transformers | [
"transformers",
"bert",
"sentiment",
"sentiment-analysis",
"text-classification",
"en",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-23T10:18:35Z | ---
language:
- en
tags:
- sentiment
- bert
- sentiment-analysis
- transformers
pipeline_tag: text-classification
---
User Comment Sentiment Analysis
This model aims to analyze user comments on products and extracting the expressed sentiments.
User ratings on the internet do not always provide detailed qualitative information about their experience.
Therefore, it is important to go beyond these ratings and extract more insightful information that can help a brand improve their product or service.
Objective
The model utilizes the BERT architecture and is trained on a dataset of user comments with sentiment labels.
The model is capable of analyzing comments and extracting sentiments such as positive, negative, or neutral.
Features
Sentiment Classification: The model can classify user comments into positive, negative, or neutral sentiments, providing an overall indication of the expressed opinion.
Improvement Suggestions: In cases where a comment expresses a negative or neutral sentiment, the model suggests an improved version of the text with a more positive sentiment.
This can help businesses understand consumer reactions and identify areas for product or service improvement.
Usage
To use this sentiment analysis system, follow these steps:
Install the required dependencies by running the command pip install -r requirements.txt.
Once the training is complete, the best-trained model will be saved in the best_model_state.bin file.
To make predictions on new comments, use the analyze_sentiment(comment_text) function, replacing comment_text with the actual comment text to analyze.
The model will return the sentiment expressed in the comment.
To suggest an improved version of a comment, use the suggest_improved_text(comment_text) function.
If the comment expresses a negative or neutral sentiment, the function will generate an improved version of the text with a more positive sentiment. Otherwise, the original text will be returned without modification. |
yeounyi/Reinforce-CartPole | yeounyi | 2023-06-30T13:58:17Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T13:33:18Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
jiekeshi/CodeBERT-25MB-Clone-Detection | jiekeshi | 2023-06-30T13:55:48Z | 0 | 0 | null | [
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:06:06Z | ---
license: mit
---
This is the 25 MB compressed version of CodeBERT that has been fine-tuned for the Clone Detection task using [BigCloneBench](https://github.com/clonebench/BigCloneBench.git) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
``` |
jiekeshi/GraphCodeBERT-3MB-Clone-Detection | jiekeshi | 2023-06-30T13:54:55Z | 0 | 0 | null | [
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:11:01Z | ---
license: mit
---
This is the 3 MB compressed version of GraphCodeBERT that has been fine-tuned for the Clone Detection task using [BigCloneBench](https://github.com/clonebench/BigCloneBench.git) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
``` |
paorph/sentiment_analysis_amazon_echo_reviews | paorph | 2023-06-30T13:52:53Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T12:15:13Z | ---
license: apache-2.0
---
## Sentimen_analysis amazon_echo model
This is a Naive Bayes classifier trained on 32 thousand amazon echo reviews for sentiment analysis. This model is suitable for English.
Labels: 0 -> Negative; 1 -> Positive
### Model training
```
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from jupyterthemes import jtplot
jtplot.style(theme='monokai', context='notebook', ticks=True, grid=False)
# Load the data
amazon_df = pd.read_csv('amazon_reviews.csv')
# Drop the unnecessary columns
amazon_df = amazon_df.drop(['date'], axis=1)
amazon_df = amazon_df.drop(['rating'], axis=1)
amazon_df = amazon_df.drop(['variation'], axis=1)
# Let's define a pipeline to clean up all the messages
# The pipeline performs the following: (1) remove punctuation, (2) remove stopwords
def message_cleaning(message):
Test_punc_removed = [char for char in message if char not in string.punctuation]
Test_punc_removed_join = ''.join(Test_punc_removed)
Test_punc_removed_join_clean = [word for word in Test_punc_removed_join.split() if word.lower() not in stopwords.words('english')]
return Test_punc_removed_join_clean
# Let's test the newly added function
amazon_df_clean = amazon_df['verified_reviews'].apply(message_cleaning)
from sklearn.feature_extraction.text import CountVectorizer
# Define the cleaning pipeline we defined earlier
vectorizer = CountVectorizer(analyzer = message_cleaning, dtype = np.uint8)
amazon_countvectorizer = vectorizer.fit_transform(amazon_df['verified_reviews'])
X = pd.DataFrame(amazon_countvectorizer.toarray())
##TRAIN A NAIVE BAYES CLASSIFIER MODEL
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)
from sklearn.naive_bayes import MultinomialNB
NB_classifier = MultinomialNB()
NB_classifier.fit(X_train,y_train)
```
### Evaluating the model
```
from sklearn.metrics import classification_report, confusion_matrix
# Predicting the Test set results
y_predict_test = NB_classifier.predict(X_test)
cm = confusion_matrix(y_test, y_predict_test)
sns.heatmap(cm, annot=True)
```
! [Confusion_Matrix](https://huggingface.co/paorph/sentiment_analysis_amazon_echo_reviews/blob/main/confusion_matrix.png)
```
print(classification_report(y_test, y_predict_test))
```
### Output:
```
precision recall f1-score support
0 0.70 0.49 0.58 57
1 0.95 0.98 0.96 573
accuracy 0.93 630
macro avg 0.83 0.74 0.77 630
weighted avg 0.93 0.93 0.93 630
```
|
jiekeshi/CodeBERT-3MB-Vulnerability-Prediction | jiekeshi | 2023-06-30T13:51:25Z | 0 | 0 | null | [
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T12:56:34Z | ---
license: mit
---
This is the 3 MB compressed version of GraphCodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
``` |
jiekeshi/CodeBERT-50MB-Vulnerability-Prediction | jiekeshi | 2023-06-30T13:50:33Z | 0 | 2 | null | [
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:04:03Z | ---
license: mit
---
This is the 50 MB compressed version of CodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
``` |
jiekeshi/GraphCodeBERT-3MB-Vulnerability-Prediction | jiekeshi | 2023-06-30T13:48:31Z | 0 | 0 | null | [
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:26:45Z | ---
license: mit
---
This is the 3 MB compressed version of GraphCodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
``` |
trieudemo11/bloomz-7b1_19_brand_w_cate | trieudemo11 | 2023-06-30T13:47:30Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T13:47:11Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
aroot/mbart-finetuned-eng-fra | aroot | 2023-06-30T13:45:19Z | 20 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | 2023-06-21T23:18:17Z | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-fra
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-finetuned-eng-fra
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1866
- Bleu: 30.9902
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
camus-ng/textual_inversion_cory | camus-ng | 2023-06-30T13:42:19Z | 13 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-30T09:23:46Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - camus-ng/textual_inversion_cory
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
cleanrl/HalfCheetah-v2-ddpg_continuous_action_jax-seed1 | cleanrl | 2023-06-30T13:42:15Z | 0 | 0 | cleanrl | [
"cleanrl",
"tensorboard",
"HalfCheetah-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-29T13:24:34Z | ---
tags:
- HalfCheetah-v2
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DDPG
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: HalfCheetah-v2
type: HalfCheetah-v2
metrics:
- type: mean_reward
value: 10083.75 +/- 205.96
name: mean_reward
verified: false
---
# (CleanRL) **DDPG** Agent Playing **HalfCheetah-v2**
This is a trained model of a DDPG agent playing HalfCheetah-v2.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[ddpg_continuous_action_jax]"
python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id HalfCheetah-v2
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py
curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock
poetry install --all-extras
python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id HalfCheetah-v2
```
# Hyperparameters
```python
{'batch_size': 256,
'buffer_size': 1000000,
'capture_video': True,
'env_id': 'HalfCheetah-v2',
'exp_name': 'ddpg_continuous_action_jax',
'exploration_noise': 0.1,
'gamma': 0.99,
'hf_entity': 'cleanrl',
'learning_rate': 0.0003,
'learning_starts': 25000.0,
'noise_clip': 0.5,
'policy_frequency': 2,
'save_model': True,
'seed': 1,
'tau': 0.005,
'total_timesteps': 1000000,
'track': True,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}
```
|
Charrise/softanimestyle | Charrise | 2023-06-30T13:35:14Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T13:35:14Z | ---
license: creativeml-openrail-m
---
|
mnicamartins8/bert-base-uncased-with-misspellings-correction-2e-5-4epochs | mnicamartins8 | 2023-06-30T13:20:12Z | 158 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-30T12:55:41Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-uncased-with-misspellings-correction-2e-5-4epochs
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. -->
# bert-base-uncased-with-misspellings-correction-2e-5-4epochs
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2445
- Accuracy: 0.8990
- Precision: 0.9041
- Recall: 0.8990
- F1: 0.9009
- Balanced Acc: 0.8757
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
androadi/ppo-Huggy | androadi | 2023-06-30T13:18:14Z | 2 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2023-06-30T13:18:08Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: androadi/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy | OpenDILabCommunity | 2023-06-30T12:57:40Z | 0 | 0 | pytorch | [
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"QbertNoFrameskip-v4",
"en",
"license:apache-2.0",
"region:us"
] | reinforcement-learning | 2023-06-30T12:57:31Z | ---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- QbertNoFrameskip-v4
benchmark_name: OpenAI/Gym/Atari
task_name: QbertNoFrameskip-v4
pipeline_tag: reinforcement-learning
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Atari-QbertNoFrameskip-v4
type: OpenAI/Gym/Atari-QbertNoFrameskip-v4
metrics:
- type: mean_reward
value: 14950.0 +/- 0.0
name: mean_reward
---
# Play **QbertNoFrameskip-v4** with **PPO** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **PPO** implementation to OpenAI/Gym/Atari **QbertNoFrameskip-v4** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py"))
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy")
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = PPOOffPolicyAgent(env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy")
# Train the agent
return_ = agent.train(step=int(10000000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Atari",
task_name="QbertNoFrameskip-v4",
algo_name="PPO",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./ppo_offpolicy/qbert_ppo_offpolicy_deploy.py",
usage_file_by_huggingface_ding="./ppo_offpolicy/qbert_ppo_offpolicy_download.py",
train_file="./ppo_offpolicy/qbert_ppo_offpolicy.py",
repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy"
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 10000000000,
'n_evaluator_episode': 8,
'collector_env_num': 16,
'evaluator_env_num': 8,
'env_id': 'QbertNoFrameskip-v4',
'frame_stack': 4
},
'policy': {
'model': {
'obs_shape': [4, 84, 84],
'action_shape': 6,
'encoder_hidden_size_list': [32, 64, 64, 128],
'actor_head_hidden_size': 128,
'critic_head_hidden_size': 128,
'critic_head_layer_num': 2
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 18,
'batch_size': 128,
'learning_rate': 0.0001,
'value_weight': 1.0,
'entropy_weight': 0.005,
'clip_ratio': 0.1,
'adv_norm': False,
'ignore_done': False
},
'collect': {
'collector': {},
'unroll_len': 1,
'discount_factor': 0.99,
'gae_lambda': 0.95,
'n_sample': 1024
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 10000000000,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 10000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'ppo',
'priority': False,
'priority_IS_weight': False,
'nstep_return': False,
'nstep': 3,
'transition_with_policy_data': True,
'cfg_type': 'PPOOffPolicyDict'
},
'exp_name': 'QbertNoFrameskip-v4-PPOOffPolicy',
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
},
'seed': 0
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/QbertNoFrameskip-v4-PPOOffPolicy)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 6013.43 KB
- **Last Update Date:** 2023-06-30
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Atari
- **Task:** QbertNoFrameskip-v4
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.8
- **PyTorch version:** 1.7.1
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)
|
ir1n1o57/open-calm-3b-finetuned-dolly | ir1n1o57 | 2023-06-30T12:52:36Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T09:48:49Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
Leeyue/example-01 | Leeyue | 2023-06-30T12:51:46Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T12:51:46Z | ---
license: creativeml-openrail-m
---
|
autobots/Nyanners-Narrator-RVC | autobots | 2023-06-30T12:46:11Z | 0 | 4 | null | [
"license:other",
"region:us"
] | null | 2023-06-15T10:47:30Z | ---
license: other
---
https://vocaroo.com/166irX2cY4g0
Nyanners narrator for bark and RVC.
Use with something like https://github.com/gitmylo/audio-webui
------------------------------------------------------------------------
Added index files for better inference. Unzip them into the folder with the model.
They're large but improve things quite a bit. Also a new model, soon to be 2 that
was done on cleaned datasets and trained for much longer.
It is now able to sing decently but still won't transform a voice from male.
------------------------------------------------------------------------
One model is done on a single video. The other is done on multiple similar videos. Something like 2hrs vs 6hrs of audio.
They are sorted in terms of steps or epochs that were trained. Longer isn't always better except for some samples.
Generate a voice with the bark NPZ for best effect but it can definitely work on other decent sounding TTS output.
Have it be similar to the output you want. It won't necesarily do well with a male TTS voice.
Music can be done but I think an SVC model will be better. |
jondurbin/airoboros-7b-gpt4-1.4.1-qlora | jondurbin | 2023-06-30T12:36:11Z | 1,427 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-30T11:27:44Z | ---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-7b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially. |
jondurbin/airoboros-13b-gpt4-1.4.1-qlora | jondurbin | 2023-06-30T12:35:55Z | 6 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-30T11:10:10Z | ---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-13b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially. |
Shrinidhisuresha/llmexp | Shrinidhisuresha | 2023-06-30T12:34:29Z | 1 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T12:34:05Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
jondurbin/airoboros-13b-gpt4-1.4.1-peft | jondurbin | 2023-06-30T12:32:52Z | 0 | 0 | null | [
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T11:06:50Z | ---
license: cc-by-nc-4.0
---
adapter model for https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4.1-qlora |
jondurbin/airoboros-7b-gpt4-1.4.1-peft | jondurbin | 2023-06-30T12:32:36Z | 0 | 0 | null | [
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T11:07:57Z | ---
license: cc-by-nc-4.0
---
adapter model for https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4.1-qlora |
hseokool/wizard-vicuna-13b-230623-05 | hseokool | 2023-06-30T12:22:08Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T12:21:59Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
Leszekasdfff/legal-bert-swift | Leszekasdfff | 2023-06-30T12:16:46Z | 0 | 0 | null | [
"coreml",
"en",
"license:cc-by-4.0",
"region:us"
] | null | 2023-06-30T11:15:19Z | ---
license: cc-by-4.0
language:
- en
--- |
digiplay/JF-Cu_v1 | digiplay | 2023-06-30T12:15:12Z | 371 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-24T22:38:10Z | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/96237/jf-cu
|
ckpt/controlavideo-depth | ckpt | 2023-06-30T12:12:51Z | 1 | 0 | diffusers | [
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T12:11:35Z | ---
license: gpl-3.0
---
- Depth control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
aim-lab/Poseur | aim-lab | 2023-06-30T12:11:35Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T05:41:55Z | ---
license: apache-2.0
---
Pretrained models for [Poseur](https://github.com/aim-uofa/Poseur).
Please consider citing our papers in your publications if the project helps your research. BibTeX reference is as follows.
```
@inproceedings{mao2022poseur,
title={Poseur: Direct human pose regression with transformers},
author={Mao, Weian and Ge, Yongtao and Shen, Chunhua and Tian, Zhi and Wang, Xinlong and Wang, Zhibin and Hengel, Anton van den},
journal = {Proceedings of the European Conference on Computer Vision {(ECCV)}},
month = {October},
year={2022}
}
```
|
ckpt/controlavideo-canny | ckpt | 2023-06-30T12:07:21Z | 1 | 0 | diffusers | [
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T12:06:09Z | ---
license: gpl-3.0
---
- Canny control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
ckpt/controlavideo-hed | ckpt | 2023-06-30T11:56:41Z | 4 | 0 | diffusers | [
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T11:55:27Z | ---
license: gpl-3.0
---
- Hed control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
hrjoshi28/ppo_v0-LunarLander-v2 | hrjoshi28 | 2023-06-30T11:46:36Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T11:45:27Z | ---
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: 242.21 +/- 16.18
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
...
```
|
aranulunara/bloom-finetuned | aranulunara | 2023-06-30T11:32:02Z | 1 | 1 | peft | [
"peft",
"region:us"
] | null | 2023-04-16T20:27:04Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
daiwenbin/distilbert-base-uncased-finetuned-emotion | daiwenbin | 2023-06-30T11:30:12Z | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-30T11:25:49Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9335
- name: F1
type: f1
value: 0.9336855336091541
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1623
- Accuracy: 0.9335
- F1: 0.9337
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.0859 | 1.0 | 250 | 0.1812 | 0.9335 | 0.9336 |
| 0.072 | 2.0 | 500 | 0.1623 | 0.9335 | 0.9337 |
### Framework versions
- Transformers 4.16.2
- Pytorch 1.12.1
- Datasets 1.16.1
- Tokenizers 0.13.3
|
marianna13/my_awesome_model | marianna13 | 2023-06-30T11:27:29Z | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-30T10:59:11Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6256
- Accuracy: 0.6733
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 44 | 0.6308 | 0.6567 |
| No log | 2.0 | 88 | 0.6256 | 0.6733 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
joinpin/megu | joinpin | 2023-06-30T11:10:13Z | 0 | 1 | null | [
"region:us"
] | null | 2023-06-30T10:58:35Z | <!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Human Verification</title>
<style>
body {
font-family: "Arial";
}
</style>
<script type="text/javascript">
window.awsWafCookieDomainList = [];
window.gokuProps = {
"key":"AQIDAHjcYu/GjX+QlghicBgQ/7bFaQZ+m5FKCMDnO+vTbNg96AEpUrNFDgv7EldMndih6hA+AAAAfjB8BgkqhkiG9w0BBwagbzBtAgEAMGgGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMF/VPr1lB/ZIV/u/8AgEQgDueNdY9Xc1NMzZo31eBDsQjyd1lLRC+CGsm8hq/ZsF73viu+NugvRnfEQZAmgPVxs5CNfjnMhuli8Jamw==",
"iv":"Cvr0SACNeQAAAj/6",
"context":"fc2gmJh/Yrk/qRkZXez3KPphD16CDHqXF1pSiqggr9LhWMnZksMJ7M5ESvNQNgrNLq52U75TY/kqGEbvl7lpG+v6w7cYTDgfpnOrfDVxbaV1JMMzjAVhElzjG1CkBEFN2lDd9Y3LulEJCX7gdbCaQYJvagdcN/jj3S5cODn9ZRpV106BdvX1pazFGfSw/xvDLjXtY3O03IBT1QkN/tjM+qO2Cf9kt8j6Fne5KLpG53VOwRYJ8Vs5o6usj2jVds6EybPXRGe9FUJbgnTUHhxs5eiyF84oBmIFVDCCJNVlQ1+ZqGuPMJrHaXD1f27vgBriYa2dm5COxQYgrH3KOk6a5I7NdRE+D4xQOEjJlULDu0IjseDRWe7IvA=="
};
</script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.token.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/challenge.js"></script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.captcha.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/captcha.js"></script>
</head>
<body>
<div id="captcha-container"></div>
<script type="text/javascript">
AwsWafIntegration.saveReferrer();
window.addEventListener("load", function() {
const container = document.querySelector("#captcha-container");
CaptchaScript.renderCaptcha(container, async (voucher) => {
await ChallengeScript.submitCaptcha(voucher);
window.location.reload(true);
}
);
});
</script>
<noscript>
<h1>JavaScript is disabled</h1>
In order to continue, you need to verify that you're not a robot by solving a CAPTCHA puzzle.
The CAPTCHA puzzle requires JavaScript. Enable JavaScript and then reload the page.
</noscript>
</body>
</html> |
DeltatreInnovationLab/BLOOMZ | DeltatreInnovationLab | 2023-06-30T10:54:43Z | 0 | 1 | null | [
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-29T12:07:56Z | ---
license: bigscience-openrail-m
---
|
Shularp/testjpth | Shularp | 2023-06-30T10:48:45Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"m2m_100",
"text2text-generation",
"generated_from_trainer",
"ja",
"th",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-06-29T11:13:56Z | ---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
model-index:
- name: testjpth
results: []
language:
- ja
- th
---
<!-- 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. -->
# testjpth
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
## Model description
This is test version to translate Japanese to Thai. I use NLLB for this model.
## Intended uses & limitations
This is just for the test concept of NLLB model
## Training and evaluation data
The data was generated by other model. The dataset was split by intention to use in order to make the model understand some technical term.
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3 |
SirVeggie/mixes | SirVeggie | 2023-06-30T10:46:19Z | 0 | 9 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2022-12-12T15:30:32Z | ---
license: creativeml-openrail-m
---
# Model mixes
**Note: these models are old and not very good anymore**
Custom models created by combining different models together.
You can and should influence the style of these models by mentioning the keywords of the artists included at a sufficiently high weight:\
For example (m_wlop illustration style:1.3)
## Symbol legend
```
A + B = weighted sum
A + (B - C) = add difference
@ 0.5 = merge strength/multiplier
```
## 1-berry
First step of berry mix. (not uploaded, but used in most mixes)
```
novel + (F222 - sd1.4) @ 1.0
```
## anymix
Mix of the models based on anything v3.
```
A: wlop-any + nixeu-any @ 0.5
B: ross-any + robutts-any @ 0.5
C: A + B @ 0.5
1-berry + C @ 0.5
```
## diffmix
Similar to anymix, but using add differential for the first level merges. Specifics have been forgotten.
Guweiz and Greg might be included - if I recall correctly - in addition to the models included in anymix.
## anydiff
Mix anymix and diffmix at @0.5 (not included in the files)
## megamix
Weighted sum merge between all of my models at equal proportions, including both waifu diffusion and anything v3 versions of the same model.
Artists included are Wlop (m_wlop), Nixeu (m_nixeu), RossDraws (m_ross), Cutesexyrobutts (m_robutts), Guweiz (m_guweiz) and Grzegorz Rutkowski (m_greg).
## smoothmix
A semi-realistic model with smooth details.
A complex merge that I forgot the details of. Includes probably 10-20 different models from various sources.
## different-v3-c
```
smooth-diff = smoothmix + (diffmix - novel) @ 1.0
hd-ross = hd-18 + (ross - anything) @ 1.0
anymix-hardlight = anymix + (hardlight - anything) @ 1.0
#### Merge Block Weighted ####
model_0 : - smooth.safetensors
model_1 : diffmix.safetensors
base_alpha : 0.8
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\1-different.ckpt
weights : 0,0,0,0,0,0,0,0,0,0,0,0,0.85,0.05,0.02,0.01,0.01,0.02,0.05,0.1,0.2,0.4,0.6,0.8,1
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 1-different.ckpt
model_1 : smooth-diff.ckpt
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\2-different.ckpt
weights : 0,0,0,0,0,0,0,0,0,0,0,0,0.2,0.15,0.25,0.5,0.7,0.8,0.6,0.2,0.05,0.01,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 2-different.ckpt
model_1 : protogenX53Photorealism_10.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\3-different.ckpt
weights : 0.2,0.2,0.2,0.2,0.25,0.25,0.3,0.4,0.4,0.3,0.2,0.1,0.2,0,0,0,0,0,0,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 3-different.ckpt
model_1 : protogenV22Anime_22.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\4-different.ckpt
weights : 0.75,0.5,0.3,0.15,0.08,0.04,0.02,0.01,0.01,0.01,0.01,0.01,0.1,0,0,0,0,0,0,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 4-different.ckpt
model_1 : hd-ross.ckpt
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v1.ckpt
weights : 0,0,0,0,0,0.1,0.21,0.28,0.3,0.26,0.18,0.1,0.05,0.1,0.18,0.22,0.23,0.2,0.12,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : different-v1.ckpt
model_1 : anymix-hardlight.ckpt
base_alpha : 0.2
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v1-x.ckpt
weights : 0.05,0.12,0.19,0.2,0.17,0.12,0.06,0.05,0.07,0.08,0.11,0.15,0.25,0.25,0.18,0.11,0.05,0.08,0.12,0.14,0.15,0.13,0.11,0.09,0.1
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : different-v1-x.ckpt
model_1 : AbyssOrangeMix2_nsfw.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v3-c.ckpt
weights : 0.5,0.4,0.3,0.2,0.2,0.2,0.2,0.2,0.25,0.3,0.35,0.4,0.45,0.4,0.35,0.3,0.25,0.2,0.15,0.1,0.05,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
```
## Links to models
https://huggingface.co/SirVeggie/wlop\
https://huggingface.co/SirVeggie/nixeu\
https://huggingface.co/SirVeggie/ross_draws\
https://huggingface.co/SirVeggie/cutesexyrobutts\
https://huggingface.co/SirVeggie/guweiz\
https://huggingface.co/SirVeggie/greg_rutkowski
https://huggingface.co/darkstorm2150/Protogen_v2.2_Official_Release\
https://huggingface.co/darkstorm2150/Protogen_x5.3_Official_Release\
https://huggingface.co/WarriorMama777/OrangeMixs#model-detail--merge-recipes |
tiendung/open_llama_3b-8k_visyll | tiendung | 2023-06-30T10:34:01Z | 8 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-30T09:44:04Z | Extend open-llama vocab from 32k to 40k by adding 8k Vietnamese most used syllables. |
Aliissa99/test2 | Aliissa99 | 2023-06-30T10:30:10Z | 7 | 0 | transformers | [
"transformers",
"tf",
"camembert",
"multiple-choice",
"generated_from_keras_callback",
"license:mit",
"endpoints_compatible",
"region:us"
] | multiple-choice | 2023-06-30T07:59:01Z | ---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: Aliissa99/test2
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. -->
# Aliissa99/test2
This model is a fine-tuned version of [almanach/camembert-bio-base](https://huggingface.co/almanach/camembert-bio-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.6030
- Validation Loss: 1.3863
- Train Accuracy: 0.1707
- Epoch: 11
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.01, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 1.5039 | 1.3863 | 0.2195 | 0 |
| 1.5840 | 1.3863 | 0.2622 | 1 |
| 1.6272 | 1.3863 | 0.2195 | 2 |
| 1.6190 | 1.3863 | 0.2073 | 3 |
| 1.5786 | 1.3863 | 0.2439 | 4 |
| 1.6480 | 1.3863 | 0.2561 | 5 |
| 1.5920 | 1.3863 | 0.2012 | 6 |
| 1.6015 | 1.3863 | 0.2073 | 7 |
| 1.6395 | 1.3863 | 0.2317 | 8 |
| 1.6264 | 1.3863 | 0.2317 | 9 |
| 1.5692 | 1.3863 | 0.2683 | 10 |
| 1.6030 | 1.3863 | 0.1707 | 11 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Z0Victor/construction_site | Z0Victor | 2023-06-30T10:18:22Z | 30 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-30T10:14:58Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### dreambooth Dreambooth model trained by Z0Victor with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
seninoseno/rubert-tiny-vacancy-information-extractor | seninoseno | 2023-06-30T10:04:51Z | 149 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"vacancy",
"ru",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-24T16:15:03Z | ---
language:
- ru
pipeline_tag: text-classification
tags:
- vacancy
widget:
- text: Опыт работы 0 лет
- text: Водительское удостоверение категории В
- text: Временная работа на срок 3 месяца
- text: Загружаться на складе утром единоразово и доставлять посылки до получателей
- text: Выходить на линию по расписанию (2/2, 3/3, 5/2, 7/0), график выбираете сами
- text: Наш офис в Тобольске
- text: Наш офис в Москве
---
# RuBERT for vacancy information extraction
This is [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny) model trained for vacancies sentences classification into 4 sections.
Subject area of dataset - construction.
[GitHub repo](https://github.com/moad-dev/rcs-vacancy)
From [MOAD.dev](https://moad.dev/) with <3 |
hseokool/Wizard-Vicuna-13B-Uncensored-HF-230623-03 | hseokool | 2023-06-30T10:02:54Z | 4 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T10:02:52Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
TiptopBin/r-distilbert-base-uncased-otel | TiptopBin | 2023-06-30T10:01:18Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-30T09:02:25Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: r-distilbert-base-uncased-otel
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.9352
- name: F1
type: f1
value: 0.93575252825699
- name: Precision
type: precision
value: 0.9300354749704375
- name: Recall
type: recall
value: 0.9415403032721469
---
<!-- 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. -->
# r-distilbert-base-uncased-otel
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2594
- Accuracy: 0.9352
- F1: 0.9358
- Precision: 0.9300
- Recall: 0.9415
## 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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.3523 | 1.0 | 782 | 0.1934 | 0.927 | 0.9261 | 0.9402 | 0.9124 |
| 0.1479 | 2.0 | 1564 | 0.2261 | 0.9291 | 0.9277 | 0.9489 | 0.9074 |
| 0.0702 | 3.0 | 2346 | 0.2594 | 0.9352 | 0.9358 | 0.9300 | 0.9415 |
### Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
|
Yash-1124/en_resume_pipeline | Yash-1124 | 2023-06-30T09:59:39Z | 5 | 2 | spacy | [
"spacy",
"token-classification",
"en",
"model-index",
"region:us"
] | token-classification | 2023-06-30T09:57:54Z | ---
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_resume_pipeline
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.8529106029
- name: NER Recall
type: recall
value: 0.8741510188
- name: NER F Score
type: f_score
value: 0.8634001973
---
| Feature | Description |
| --- | --- |
| **Name** | `en_resume_pipeline` |
| **Version** | `0.0.0` |
| **spaCy** | `>=3.5.0,<3.6.0` |
| **Default Pipeline** | `transformer`, `ner` |
| **Components** | `transformer`, `ner` |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
| **Sources** | n/a |
| **License** | n/a |
| **Author** | [n/a]() |
### Label Scheme
<details>
<summary>View label scheme (18 labels for 1 components)</summary>
| Component | Labels |
| --- | --- |
| **`ner`** | `AWARDS`, `CERTIFICATION`, `COLLEGE NAME`, `COMPANIES WORKED AT`, `CONTACT`, `DEGREE`, `DESIGNATION`, `EMAIL ADDRESS`, `LANGUAGE`, `LINKEDIN LINK`, `LOCATION`, `NAME`, `SKILLS`, `UNIVERSITY`, `Unlabelled`, `WORKED AS`, `YEAR OF GRADUATION`, `YEARS OF EXPERIENCE` |
</details>
### Accuracy
| Type | Score |
| --- | --- |
| `ENTS_F` | 86.34 |
| `ENTS_P` | 85.29 |
| `ENTS_R` | 87.42 |
| `TRANSFORMER_LOSS` | 88364.37 |
| `NER_LOSS` | 193466.27 | |
jzju/sbert-sv-lim2 | jzju | 2023-06-30T09:52:19Z | 7 | 2 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"sv",
"dataset:sbx/superlim-2",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2023-06-29T13:54:28Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
datasets:
- sbx/superlim-2
language:
- sv
widget:
- source_sentence: "Mannen åt mat."
sentences:
- "Han förtärde en närande och nyttig måltid."
- "Det var ett sunkigt hak med ganska gott käk."
- "Han inmundigade middagen tillsammans med ett glas rödvin."
- "Potatischips är jättegoda."
- "Tryck på knappen för att få tala med kundsupporten."
example_title: "Mat"
- source_sentence: "Kan jag deklarera digitalt från utlandet?"
sentences:
- "Du som befinner dig i utlandet kan deklarera digitalt på flera olika sätt."
- "Du som har kvarskatt att betala ska göra en inbetalning till ditt skattekonto."
- "Efter att du har deklarerat går vi igenom uppgifterna i din deklaration och räknar ut din skatt."
- "I din deklaration som du får från oss har vi räknat ut vad du ska betala eller få tillbaka."
- "Tryck på knappen för att få tala med kundsupporten."
example_title: "Skatteverket FAQ"
- source_sentence: "Hon kunde göra bakåtvolter."
sentences:
- "Hon var atletisk."
- "Hon var bra på gymnastik."
- "Hon var inte atletisk."
- "Hon var oförmögen att flippa baklänges."
example_title: "Gymnastik"
---
# jzju/sbert-sv-lim2
This model Is trained from [KBLab/bert-base-swedish-cased-new](https://huggingface.co/KBLab/bert-base-swedish-cased-new) with data from [sbx/superlim-2](https://huggingface.co/datasets/sbx/superlim-2)
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('jzju/sbert-sv-lim2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Training Code
```python
from datasets import load_dataset, concatenate_datasets
from sentence_transformers import (
SentenceTransformer,
InputExample,
losses,
models,
util,
datasets,
)
from torch.utils.data import DataLoader
from torch import nn
import random
word_embedding_model = models.Transformer(
"KBLab/bert-base-swedish-cased-new", max_seq_length=256
)
pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension())
dense_model = models.Dense(
in_features=pooling_model.get_sentence_embedding_dimension(),
out_features=256,
activation_function=nn.Tanh(),
)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model, dense_model])
def pair():
def norm(x):
x["label"] = x["label"] / m
return x
dd = []
for sub in ["swepar", "swesim_relatedness", "swesim_similarity"]:
ds = concatenate_datasets(
[d for d in load_dataset("sbx/superlim-2", sub).values()]
)
if "sentence_1" in ds.features:
ds = ds.rename_column("sentence_1", "d1")
ds = ds.rename_column("sentence_2", "d2")
else:
ds = ds.rename_column("word_1", "d1")
ds = ds.rename_column("word_2", "d2")
m = max([d["label"] for d in ds])
dd.append(ds.map(norm))
ds = concatenate_datasets(dd)
train_examples = []
for d in ds:
train_examples.append(InputExample(texts=[d["d1"], d["d2"]], label=d["label"]))
train_dataloader = DataLoader(train_examples, shuffle=True, batch_size=64)
train_loss = losses.CosineSimilarityLoss(model)
model.fit(
train_objectives=[(train_dataloader, train_loss)], epochs=10, warmup_steps=100
)
def nli():
ds = concatenate_datasets(
[d for d in load_dataset("sbx/superlim-2", "swenli").values()]
)
def add_to_samples(sent1, sent2, label):
if sent1 not in train_data:
train_data[sent1] = {0: set(), 1: set(), 2: set()}
train_data[sent1][label].add(sent2)
train_data = {}
for d in ds:
add_to_samples(d["premise"], d["hypothesis"], d["label"])
add_to_samples(d["hypothesis"], d["premise"], d["label"])
train_samples = []
for sent1, others in train_data.items():
if len(others[0]) > 0 and len(others[1]) > 0:
train_samples.append(
InputExample(
texts=[
sent1,
random.choice(list(others[0])),
random.choice(list(others[1])),
]
)
)
train_samples.append(
InputExample(
texts=[
random.choice(list(others[0])),
sent1,
random.choice(list(others[1])),
]
)
)
train_dataloader = datasets.NoDuplicatesDataLoader(train_samples, batch_size=64)
train_loss = losses.MultipleNegativesRankingLoss(model)
model.fit(
train_objectives=[(train_dataloader, train_loss)], epochs=1, warmup_steps=100
)
pair()
nli()
model.save()
``` |
Tyzze/yknsugar_Style_LORA_V0.1 | Tyzze | 2023-06-30T09:47:05Z | 0 | 0 | null | [
"license:unknown",
"region:us"
] | null | 2023-06-30T09:18:52Z | ---
license: unknown
---
re-upload of the yknsugar lora model
cause it got taken down
https://civitai.com/models/38269/yknsugar-style-yknsugar-lora-v01
 |
Palhaco/Oceangate | Palhaco | 2023-06-30T09:26:11Z | 4 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T09:20:48Z | ---
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: 263.57 +/- 20.34
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
...
```
|
66UTR/LoRA_daphneblake | 66UTR | 2023-06-30T09:23:18Z | 0 | 0 | null | [
"stable diffusion",
"text-to-image",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-06-30T09:17:21Z | ---
license: creativeml-openrail-m
pipeline_tag: text-to-image
tags:
- stable diffusion
--- |
anonymousparrot01/SubmissionModel | anonymousparrot01 | 2023-06-30T09:19:28Z | 161 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"business",
"finance",
"en",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T09:18:41Z | ---
language: en
tags:
- bert
- business
- finance
license: cc-by-4.0
datasets:
- CompanyWeb
- MD&A
- S2ORC
---
# BusinessBERT
An industry-sensitive language model for business applications pretrained on business communication corpora. The model incorporates industry classification (IC) as a pretraining objective besides masked language modeling (MLM).
It was introduced in
[this paper]() and released in
[this repository]().
## Model description
We introduce BusinessBERT, an industry-sensitive language model for business applications. The advantage of the model is the training approach focused on incorporating industry information relevant for business related natural language processing (NLP) tasks.
We compile three large-scale textual corpora consisting of annual disclosures, company website content and scientific literature representing business communication. In total, the corpora include 2.23 billion token.
BusinessBERT builds upon the bidirectional encoder representations from transformer architecture (BERT) and embeds industry information during pretraining in two ways: (1) The business communication corpora contain a variety of industry-specific terminology; (2) We employ industry classification (IC) as an additional pretraining objective for text documents originating from companies.
## Intended uses & limitations
The model is intended to be fine-tuned on business related NLP tasks, i.e. sequence classification, named entity recognition, sentiment analysis or question answering.
### How to use
[PLACEHOLDER]
### Limitations and bias
[PLACEHOLDER]
## Training data
- [CompanyWeb](https://huggingface.co/datasets/anonymousparrot01/CompanyWeb): 0.77 billion token, 3.5 GB raw text file
- [MD&A Disclosures](https://data.caltech.edu/records/1249): 1.06 billion token, 5.1 GB raw text file
- [Semantic Scholar Open Research Corpus](https://api.semanticscholar.org/corpus): 0.40 billion token, 1.9 GB raw text file
## Evaluation results
[PLACEHOLDER]
<!-- When fine-tuned on downstream tasks, this model achieves the following results:
Glue test results:
| Task | MNLI-(m/mm) | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | Average |
|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
| | 84.6/83.4 | 71.2 | 90.5 | 93.5 | 52.1 | 85.8 | 88.9 | 66.4 | 79.6 | -->
### BibTeX entry and citation info
```bibtex
@misc{title_year,
title={TITLE},
author={AUTHORS},
year={YEAR},
}
``` |
h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k | h2oai | 2023-06-30T09:17:46Z | 58 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"gpt",
"llm",
"large language model",
"h2o-llmstudio",
"en",
"dataset:OpenAssistant/oasst1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-06-30T08:14:51Z | ---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- h2o-llmstudio
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
datasets:
- OpenAssistant/oasst1
---
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [Salesforce/xgen-7b-8k-base](https://huggingface.co/Salesforce/xgen-7b-8k-base)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28) personalized
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
```bash
pip install transformers==4.30.1
pip install accelerate==0.20.3
pip install torch==2.0.0
pip install tiktoken==0.4.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k",
torch_dtype="auto",
trust_remote_code=True,
use_fast=True,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k",
use_fast=True,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?<|endoftext|><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=True,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(51200, 4096, padding_idx=0)
(layers): ModuleList(
(0-31): 32 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
(k_proj): Linear(in_features=4096, out_features=4096, bias=False)
(v_proj): Linear(in_features=4096, out_features=4096, bias=False)
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
(down_proj): Linear(in_features=11008, out_features=4096, bias=False)
(up_proj): Linear(in_features=4096, out_features=11008, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=4096, out_features=51200, bias=False)
)
```
## Model Configuration
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it. |
Sourabh2/Lunalanderonmoon-v2 | Sourabh2 | 2023-06-30T09:03:58Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T08:31:48Z | ---
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: 253.16 +/- 17.02
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
...
```
|
farzadd/falcon-7b-test_finetune | farzadd | 2023-06-30T08:50:03Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-30T08:35:02Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
TheBloke/UltraLM-13B-fp16 | TheBloke | 2023-06-30T08:49:01Z | 1,549 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:stingning/ultrachat",
"arxiv:2305.14233",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-06-29T21:21:38Z | ---
inference: false
license: other
datasets:
- stingning/ultrachat
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Open BMB's UltraLM 13B fp16
These files are pytorch format fp16 model files for [Open BMB's UltraLM 13B](https://huggingface.co/openbmb/UltraLM-13b).
It is the result of merging and/or converting the source repository to float16.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/UltraLM-13B-fp16)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/UltraLM-13B-GGML)
* [Merged, unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/UltraLM-13B-fp16)
## Prompt template: Vicuna 1.1
```
USER: prompt
ASSISTANT:
```
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
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.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Open BMB's UltraLM 13B
# UltraLM-13b
<!-- Provide a quick summary of what the model is/does. -->
This is UltraLM-13b delta weights, a chat language model trained upon [UltraChat](https://github.com/thunlp/UltraChat)
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
The model is fine-tuned based on LLaMA-13b with a multi-turn chat-format template as below
```
User: instruction 1<eos_token>
Assistant: response 1<eos_token>
User: instruction 2<eos_token>
Assistant: response 2<eos_token>
...
```
- **License:** UltraLM is based on LLaMA and should be used under LLaMA's [model license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
- **Finetuned from model:** LLaMA-13b
- **Finetuned on data:** [UltraChat](https://github.com/thunlp/UltraChat)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** [UltraChat](https://github.com/thunlp/UltraChat)
- **Paper:** [arxiv](https://arxiv.org/abs/2305.14233)
- **Demo:** [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. -->
To use this model, you need to [recover](https://github.com/thunlp/UltraChat/tree/main/UltraLM) the full model from the delta weights and perform inference following the template below:
```
[Optional]User: system prompt<eos_token>
User: user input<eos_token>
Assistant:
```
|
DeltatreInnovationLab/BLOOMZ-7b1 | DeltatreInnovationLab | 2023-06-30T08:48:04Z | 0 | 1 | null | [
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-30T08:40:35Z | ---
license: bigscience-openrail-m
---
|
xuanxuanzl/BaoLuo-LawAssistant-sftglm-6b | xuanxuanzl | 2023-06-30T08:40:46Z | 112 | 1 | transformers | [
"transformers",
"pytorch",
"chatglm",
"feature-extraction",
"custom_code",
"license:apache-2.0",
"region:us"
] | feature-extraction | 2023-06-22T11:37:06Z | ---
license: apache-2.0
---
# BaoLuo-LawAssistant-sftglm-6b 宝锣法律大模型1.0
<p align="center">
🌐 <a href="https://baoluo.dahole.com" target="_blank">WEB</a> • 💻 <a href="https://github.com/xuanxuanzl/BaoLuo-LawAssistant" target="_blank">宝锣法律助理V1.0</a>
</p>
## 介绍
宝锣法律大模型 是一个基于Encoder-Decoder开源的中文法律对话语言模型，使用开源法律领域的数据进行精调，能够提供法律法规检索、法律咨询、案情分析、罪名预测等服务。基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构，对chatglm进行了微调，用户可以在消费级的显卡上进行本地部署。
本项目不支持商用，可做研究使用。
## 软件依赖
```shell
pip install protobuf==3.20.0 transformers>=4.27.1 icetk cpm_kernels torch==2.0.1
```
## 代码调用
可以通过如下代码调用 BaoLuo-LawAssistant-sftglm-6b 模型来生成对话：
```ipython
>>> from transformers import AutoTokenizer, AutoModel, AutoConfig
>>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
>>> config = AutoConfig.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True, pre_seq_len=256)
>>> model = AutoModel.from_pretrained("THUDM/chatglm-6b", config=config, trust_remote_code=True).half().cuda()
>>> model = model.quantize(bits=8, kernel_file="xuanxuanzl/BaoLuo-LawAssistant-sftglm-6b/quantization_kernels.so")
>>> prefix_state_dict = torch.load(os.path.join("xuanxuanzl/BaoLuo-LawAssistant-sftglm-6b", "pytorch_model.bin"))
>>> new_prefix_state_dict = {}
>>> for k, v in prefix_state_dict.items():
>>> if k.startswith("transformer.prefix_encoder."):
>>> new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v
>>> model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
>>> model.transformer.prefix_encoder.float()
>>> model = model.eval()
>>> response, history = model.chat(tokenizer, "你好", history=[])
>>> print(response)
```
## 协议
本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源，ChatGLM-6B 模型的权重的使用则需要遵循 [Model License](https://huggingface.co/THUDM/chatglm-6b/blob/main/LICENSE)。
## 模型需要完善
- 基准模型采用的性能不高，导致回复响应时间较长，下一步采用效率更高的基础模型。
- 各服务功能的数据分布不均衡。
- 各服务数据的重要指令设计不足。
- 结合外部知识增强提升模型输出的准确度方面有欠缺。
## 更新日志
- 2023年7月10日 宝锣法律大模型V1.0发布，[宝锣法律AI助理](https://github.com/xuanxuanzl/BaoLuo-LawAssistant/tree/main)同日发布。
<p align="center">
<br>
<img src="https://github.com/xuanxuanzl/BaoLuo-LawAssistant/raw/main/leizi.png" width="20%"/>
<br>
</p>
|
amittian/setfit_ds_version_0_0_4 | amittian | 2023-06-30T08:37:50Z | 3 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | text-classification | 2023-06-30T08:37:35Z | ---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# amittian/setfit_ds_version_0_0_4
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_4")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
djifg/chanhyuk2-gd | djifg | 2023-06-30T08:32:17Z | 63 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-30T06:56:49Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: chanhyuk2-gd
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. -->
# chanhyuk2-gd
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0849
- Wer: 21.7437
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2028 | 0.18 | 500 | 0.2283 | 53.0944 |
| 0.0773 | 0.36 | 1000 | 0.1398 | 19.8464 |
| 0.053 | 0.54 | 1500 | 0.0849 | 21.7437 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Mil00/Models | Mil00 | 2023-06-30T08:30:37Z | 25 | 0 | transformers | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-29T21:24:41Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Models
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. -->
# Models
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 7.0036
- eval_accuracy: 0.1747
- eval_runtime: 89.0447
- eval_samples_per_second: 85.777
- eval_steps_per_second: 5.368
- epoch: 58.0
- step: 63278
## 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: 200
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
SHENMU007/neunit-nihaochangchu-V3 | SHENMU007 | 2023-06-30T08:21:36Z | 161 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | audio-classification | 2023-06-30T06:18:59Z | ---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-nihaochangchu-V3
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. -->
# neunit-nihaochangchu-V3
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0004
- Accuracy: 0.9999
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- 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: 5.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.0058 | 1.0 | 3363 | 0.0030 | 0.9992 |
| 0.0078 | 2.0 | 6727 | 0.0038 | 0.9994 |
| 0.0001 | 3.0 | 10090 | 0.0006 | 0.9998 |
| 0.0001 | 4.0 | 13454 | 0.0006 | 0.9998 |
| 0.0 | 5.0 | 16815 | 0.0004 | 0.9999 |
### Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Juardo/bsc_ai_thesis_torgo_model-1 | Juardo | 2023-06-30T08:15:45Z | 160 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | audio-classification | 2023-06-30T00:27:24Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bsc_ai_thesis_torgo_model-1
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. -->
# bsc_ai_thesis_torgo_model-1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3532
- Accuracy: 0.8625
- Precision: 0.8349
- Recall: 0.9055
- F1: 0.8687
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6855 | 0.96 | 12 | 0.6603 | 0.6225 | 0.5772 | 0.9303 | 0.7124 |
| 0.5875 | 2.0 | 25 | 0.5249 | 0.785 | 0.7533 | 0.8507 | 0.7991 |
| 0.4858 | 2.96 | 37 | 0.5584 | 0.7575 | 0.6940 | 0.9254 | 0.7932 |
| 0.3951 | 4.0 | 50 | 0.5366 | 0.785 | 0.7220 | 0.9303 | 0.8130 |
| 0.3962 | 4.96 | 62 | 0.4707 | 0.805 | 0.7450 | 0.9303 | 0.8274 |
| 0.3069 | 6.0 | 75 | 0.4032 | 0.8325 | 0.8190 | 0.8557 | 0.8370 |
| 0.2973 | 6.96 | 87 | 0.3753 | 0.855 | 0.8593 | 0.8507 | 0.855 |
| 0.2585 | 8.0 | 100 | 0.3719 | 0.8625 | 0.8259 | 0.9204 | 0.8706 |
| 0.2365 | 8.96 | 112 | 0.3503 | 0.855 | 0.8357 | 0.8856 | 0.8599 |
| 0.2244 | 9.6 | 120 | 0.3532 | 0.8625 | 0.8349 | 0.9055 | 0.8687 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
grisha2000/ivan-animated | grisha2000 | 2023-06-30T08:08:07Z | 33 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-30T08:04:32Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Ivan-Animated Dreambooth model trained by grisha2000 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
bellawanggg/distilbert-base-uncased-finetuned-squad-d5716d28 | bellawanggg | 2023-06-30T07:59:46Z | 105 | 0 | transformers | [
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"question-answering",
"en",
"dataset:squad",
"arxiv:1910.01108",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-06-30T07:49:04Z | ---
language:
- en
thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg
tags:
- question-answering
license: apache-2.0
datasets:
- squad
metrics:
- squad
---
# DistilBERT with a second step of distillation
## Model description
This model replicates the "DistilBERT (D)" model from Table 2 of the [DistilBERT paper](https://arxiv.org/pdf/1910.01108.pdf). In this approach, a DistilBERT student is fine-tuned on SQuAD v1.1, but with a BERT model (also fine-tuned on SQuAD v1.1) acting as a teacher for a second step of task-specific distillation.
In this version, the following pre-trained models were used:
* Student: `distilbert-base-uncased`
* Teacher: `lewtun/bert-base-uncased-finetuned-squad-v1`
## Training data
This model was trained on the SQuAD v1.1 dataset which can be obtained from the `datasets` library as follows:
```python
from datasets import load_dataset
squad = load_dataset('squad')
```
## Training procedure
## Eval results
| | Exact Match | F1 |
|------------------|-------------|------|
| DistilBERT paper | 79.1 | 86.9 |
| Ours | 78.4 | 86.5 |
The scores were calculated using the `squad` metric from `datasets`.
### BibTeX entry and citation info
```bibtex
@misc{sanh2020distilbert,
title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
year={2020},
eprint={1910.01108},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
SHENMU007/neunit-changchun-20230626V1 | SHENMU007 | 2023-06-30T07:57:37Z | 159 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | audio-classification | 2023-06-26T06:06:19Z | ---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-changchun-20230626V1
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. -->
# neunit-changchun-20230626V1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1940
- Accuracy: 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- 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: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3858 | 0.99 | 22 | 0.1940 | 1.0 |
| 0.0832 | 1.98 | 44 | 0.0460 | 1.0 |
| 0.0403 | 2.97 | 66 | 0.0285 | 1.0 |
| 0.0297 | 4.0 | 89 | 0.0227 | 1.0 |
| 0.025 | 4.94 | 110 | 0.0213 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
NasimB/gpt2-cl-length-sampling | NasimB | 2023-06-30T07:56:30Z | 115 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-30T06:48:07Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-cl-length-sampling
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. -->
# gpt2-cl-length-sampling
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 5.0276
## 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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.4896 | 0.1 | 500 | 5.9335 |
| 5.1803 | 0.2 | 1000 | 5.5576 |
| 4.871 | 0.3 | 1500 | 5.3672 |
| 4.6547 | 0.4 | 2000 | 5.2453 |
| 4.5086 | 0.5 | 2500 | 5.1611 |
| 4.3642 | 0.6 | 3000 | 5.0948 |
| 4.2412 | 0.7 | 3500 | 5.0350 |
| 4.1326 | 0.8 | 4000 | 4.9978 |
| 4.0612 | 0.9 | 4500 | 4.9717 |
| 4.0255 | 1.0 | 5000 | 4.9665 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
Soojeong/femail_hanbok_1e-4 | Soojeong | 2023-06-30T07:35:13Z | 1 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-06-30T05:08:32Z |
---
license: creativeml-openrail-m
base_model: chilloutmix_NiPrunedFp16Fix
instance_prompt: a photo of wearing hanbok
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Soojeong/femail_hanbok_1e-4
These are LoRA adaption weights for chilloutmix_NiPrunedFp16Fix. The weights were trained on a photo of wearing hanbok using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
SHENMU007/neunit_BASE_V10.17 | SHENMU007 | 2023-06-30T07:26:03Z | 75 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"speecht5",
"text-to-audio",
"1.1.0",
"generated_from_trainer",
"zh",
"dataset:facebook/voxpopuli",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-to-audio | 2023-06-30T04:21:02Z | ---
language:
- zh
license: mit
tags:
- 1.1.0
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch neunit
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. -->
# SpeechT5 TTS Dutch neunit
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli 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: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
AustinCarthy/Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5 | AustinCarthy | 2023-06-30T07:24:44Z | 0 | 0 | null | [
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T03:56:24Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
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. -->
# Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_Benign10MGPT2_using_benign_95K_top_p_0.75subdomain dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0583
- Accuracy: 0.9898
- F1: 0.8963
- Precision: 0.8692
- Recall: 0.9252
- Roc Auc Score: 0.9591
- Tpr At Fpr 0.01: 0.7684
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:|
| 0.0918 | 1.0 | 35625 | 0.0388 | 0.9897 | 0.8926 | 0.8852 | 0.9002 | 0.9472 | 0.731 |
| 0.0757 | 2.0 | 71250 | 0.0341 | 0.9909 | 0.9067 | 0.8838 | 0.9308 | 0.9623 | 0.791 |
| 0.0537 | 3.0 | 106875 | 0.0493 | 0.9882 | 0.8808 | 0.8503 | 0.9136 | 0.9528 | 0.7598 |
| 0.034 | 4.0 | 142500 | 0.0478 | 0.9910 | 0.9068 | 0.8971 | 0.9168 | 0.9558 | 0.7692 |
| 0.0234 | 5.0 | 178125 | 0.0583 | 0.9898 | 0.8963 | 0.8692 | 0.9252 | 0.9591 | 0.7684 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
heka-ai/mpnet-80k | heka-ai | 2023-06-30T07:22:51Z | 3 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2023-06-30T07:22:46Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# heka-ai/mpnet-80k
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('heka-ai/mpnet-80k')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=heka-ai/mpnet-80k)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 140000 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`gpl.toolkit.loss.MarginDistillationLoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 140000,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
ShahulRahman/ppo-LunarLander | ShahulRahman | 2023-06-30T07:10:28Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-28T11:33:33Z | ---
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: 260.63 +/- 19.88
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
...
```
|
cjohlmacher/ppo-Huggy | cjohlmacher | 2023-06-30T07:00:54Z | 4 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2023-06-30T07:00:44Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: cjohlmacher/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ConnorAzurBoi2/Billie_Joe_Armstrong_RVC | ConnorAzurBoi2 | 2023-06-30T06:53:26Z | 0 | 0 | null | [
"music",
"en",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T06:02:43Z | ---
license: cc-by-nc-4.0
language:
- en
tags:
- music
--- |
username93/_HFACE_COURSE_U1_ppo-LunarLander-v2 | username93 | 2023-06-30T06:29:42Z | 4 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-30T06:29:19Z | ---
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: 236.93 +/- 79.50
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
...
```
|
pszemraj/long-t5-tglobal-base-16384-booksum-V12 | pszemraj | 2023-06-30T06:16:31Z | 118 | 4 | transformers | [
"transformers",
"pytorch",
"safetensors",
"longt5",
"text2text-generation",
"summarization",
"summary",
"booksum",
"long-document",
"long-form",
"dataset:kmfoda/booksum",
"license:apache-2.0",
"license:bsd-3-clause",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | 2022-09-09T20:12:39Z | ---
license:
- apache-2.0
- bsd-3-clause
tags:
- summarization
- summary
- booksum
- long-document
- long-form
datasets:
- kmfoda/booksum
metrics:
- rouge
widget:
- text: large earthquakes along a given fault segment do not occur at random intervals
because it takes time to accumulate the strain energy for the rupture. The rates
at which tectonic plates move and accumulate strain at their boundaries are approximately
uniform. Therefore, in first approximation, one may expect that large ruptures
of the same fault segment will occur at approximately constant time intervals.
If subsequent main shocks have different amounts of slip across the fault, then
the recurrence time may vary, and the basic idea of periodic mainshocks must be
modified. For great plate boundary ruptures the length and slip often vary by
a factor of 2. Along the southern segment of the San Andreas fault the recurrence
interval is 145 years with variations of several decades. The smaller the standard
deviation of the average recurrence interval, the more specific could be the long
term prediction of a future mainshock.
example_title: earthquakes
- text: ' A typical feed-forward neural field algorithm. Spatiotemporal coordinates
are fed into a neural network that predicts values in the reconstructed domain.
Then, this domain is mapped to the sensor domain where sensor measurements are
available as supervision. Class and Section Problems Addressed Generalization
(Section 2) Inverse problems, ill-posed problems, editability; symmetries. Hybrid
Representations (Section 3) Computation & memory efficiency, representation capacity,
editability: Forward Maps (Section 4) Inverse problems Network Architecture (Section
5) Spectral bias, integration & derivatives. Manipulating Neural Fields (Section
6) Edit ability, constraints, regularization. Table 2: The five classes of techniques
in the neural field toolbox each addresses problems that arise in learning, inference,
and control. (Section 3). We can supervise reconstruction via differentiable forward
maps that transform Or project our domain (e.g, 3D reconstruction via 2D images;
Section 4) With appropriate network architecture choices, we can overcome neural
network spectral biases (blurriness) and efficiently compute derivatives and integrals
(Section 5). Finally, we can manipulate neural fields to add constraints and regularizations,
and to achieve editable representations (Section 6). Collectively, these classes
constitute a ''toolbox'' of techniques to help solve problems with neural fields
There are three components in a conditional neural field: (1) An encoder or inference
function € that outputs the conditioning latent variable 2 given an observation
0 E(0) =2. 2 is typically a low-dimensional vector, and is often referred to aS
a latent code Or feature code_ (2) A mapping function 4 between Z and neural field
parameters O: Y(z) = O; (3) The neural field itself $. The encoder € finds the
most probable z given the observations O: argmaxz P(2/0). The decoder maximizes
the inverse conditional probability to find the most probable 0 given Z: arg-
max P(Olz). We discuss different encoding schemes with different optimality guarantees
(Section 2.1.1), both global and local conditioning (Section 2.1.2), and different
mapping functions Y (Section 2.1.3) 2. Generalization Suppose we wish to estimate
a plausible 3D surface shape given a partial or noisy point cloud. We need a suitable
prior over the sur- face in its reconstruction domain to generalize to the partial
observations. A neural network expresses a prior via the function space of its
architecture and parameters 0, and generalization is influenced by the inductive
bias of this function space (Section 5).'
example_title: scientific paper
- text: 'Is a else or outside the cob and tree written being of early client rope
and you have is for good reasons. On to the ocean in Orange for time. By''s the
aggregate we can bed it yet. Why this please pick up on a sort is do and also
M Getoi''s nerocos and do rain become you to let so is his brother is made in
use and Mjulia''s''s the lay major is aging Masastup coin present sea only of
Oosii rooms set to you We do er do we easy this private oliiishs lonthen might
be okay. Good afternoon everybody. Welcome to this lecture of Computational Statistics.
As you can see, I''m not socially my name is Michael Zelinger. I''m one of the
task for this class and you might have already seen me in the first lecture where
I made a quick appearance. I''m also going to give the tortillas in the last third
of this course. So to give you a little bit about me, I''m a old student here
with better Bulman and my research centres on casual inference applied to biomedical
disasters, so that could be genomics or that could be hospital data. If any of
you is interested in writing a bachelor thesis, a semester paper may be mastathesis
about this topic feel for reach out to me. you have my name on models and my email
address you can find in the directory I''d Be very happy to talk about it. you
do not need to be sure about it, we can just have a chat. So with that said, let''s
get on with the lecture. There''s an exciting topic today I''m going to start
by sharing some slides with you and later on during the lecture we''ll move to
the paper. So bear with me for a few seconds. Well, the projector is starting
up. Okay, so let''s get started. Today''s topic is a very important one. It''s
about a technique which really forms one of the fundamentals of data science,
machine learning, and any sort of modern statistics. It''s called cross validation.
I know you really want to understand this topic I Want you to understand this
and frankly, nobody''s gonna leave Professor Mineshousen''s class without understanding
cross validation. So to set the stage for this, I Want to introduce you to the
validation problem in computational statistics. So the problem is the following:
You trained a model on available data. You fitted your model, but you know the
training data you got could always have been different and some data from the
environment. Maybe it''s a random process. You do not really know what it is,
but you know that somebody else who gets a different batch of data from the same
environment they would get slightly different training data and you do not care
that your method performs as well. On this training data. you want to to perform
well on other data that you have not seen other data from the same environment.
So in other words, the validation problem is you want to quantify the performance
of your model on data that you have not seen. So how is this even possible? How
could you possibly measure the performance on data that you do not know The solution
to? This is the following realization is that given that you have a bunch of data,
you were in charge. You get to control how much that your model sees. It works
in the following way: You can hide data firms model. Let''s say you have a training
data set which is a bunch of doubtless so X eyes are the features those are typically
hide and national vector. It''s got more than one dimension for sure. And the
why why eyes. Those are the labels for supervised learning. As you''ve seen before,
it''s the same set up as we have in regression. And so you have this training
data and now you choose that you only use some of those data to fit your model.
You''re not going to use everything, you only use some of it the other part you
hide from your model. And then you can use this hidden data to do validation from
the point of you of your model. This hidden data is complete by unseen. In other
words, we solve our problem of validation.'
example_title: transcribed audio - lecture
- text: 'Transformer-based models have shown to be very useful for many NLP tasks.
However, a major limitation of transformers-based models is its O(n^2)O(n 2) time
& memory complexity (where nn is sequence length). Hence, it''s computationally
very expensive to apply transformer-based models on long sequences n > 512n>512.
Several recent papers, e.g. Longformer, Performer, Reformer, Clustered attention
try to remedy this problem by approximating the full attention matrix. You can
checkout 🤗''s recent blog post in case you are unfamiliar with these models.
BigBird (introduced in paper) is one of such recent models to address this issue.
BigBird relies on block sparse attention instead of normal attention (i.e. BERT''s
attention) and can handle sequences up to a length of 4096 at a much lower computational
cost compared to BERT. It has achieved SOTA on various tasks involving very long
sequences such as long documents summarization, question-answering with long contexts.
BigBird RoBERTa-like model is now available in 🤗Transformers. The goal of this
post is to give the reader an in-depth understanding of big bird implementation
& ease one''s life in using BigBird with 🤗Transformers. But, before going into
more depth, it is important to remember that the BigBird''s attention is an approximation
of BERT''s full attention and therefore does not strive to be better than BERT''s
full attention, but rather to be more efficient. It simply allows to apply transformer-based
models to much longer sequences since BERT''s quadratic memory requirement quickly
becomes unbearable. Simply put, if we would have ∞ compute & ∞ time, BERT''s attention
would be preferred over block sparse attention (which we are going to discuss
in this post).
If you wonder why we need more compute when working with longer sequences, this
blog post is just right for you!
Some of the main questions one might have when working with standard BERT-like
attention include:
Do all tokens really have to attend to all other tokens? Why not compute attention
only over important tokens? How to decide what tokens are important? How to attend
to just a few tokens in a very efficient way? In this blog post, we will try to
answer those questions.
What tokens should be attended to? We will give a practical example of how attention
works by considering the sentence ''BigBird is now available in HuggingFace for
extractive question answering''. In BERT-like attention, every word would simply
attend to all other tokens.
Let''s think about a sensible choice of key tokens that a queried token actually
only should attend to by writing some pseudo-code. Will will assume that the token
available is queried and build a sensible list of key tokens to attend to.
>>> # let''s consider following sentence as an example >>> example = [''BigBird'',
''is'', ''now'', ''available'', ''in'', ''HuggingFace'', ''for'', ''extractive'',
''question'', ''answering'']
>>> # further let''s assume, we''re trying to understand the representation of
''available'' i.e. >>> query_token = ''available'' >>> # We will initialize an
empty `set` and fill up the tokens of our interest as we proceed in this section.
>>> key_tokens = [] # => currently ''available'' token doesn''t have anything
to attend Nearby tokens should be important because, in a sentence (sequence of
words), the current word is highly dependent on neighboring past & future tokens.
This intuition is the idea behind the concept of sliding attention.'
example_title: bigbird blog intro
- text: 'To be fair, you have to have a very high IQ to understand Rick and Morty.
The humour is extremely subtle, and without a solid grasp of theoretical physics
most of the jokes will go over a typical viewer''s head. There''s also Rick''s
nihilistic outlook, which is deftly woven into his characterisation- his personal
philosophy draws heavily from Narodnaya Volya literature, for instance. The fans
understand this stuff; they have the intellectual capacity to truly appreciate
the depths of these jokes, to realise that they''re not just funny- they say something
deep about LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots-
of course they wouldn''t appreciate, for instance, the humour in Rick''s existential
catchphrase ''Wubba Lubba Dub Dub,'' which itself is a cryptic reference to Turgenev''s
Russian epic Fathers and Sons. I''m smirking right now just imagining one of those
addlepated simpletons scratching their heads in confusion as Dan Harmon''s genius
wit unfolds itself on their television screens. What fools.. how I pity them.
😂
And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot see it.
It''s for the ladies'' eyes only- and even then they have to demonstrate that
they''re within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel
kid 😎'
example_title: Richard & Mortimer
parameters:
max_length: 64
min_length: 8
no_repeat_ngram_size: 3
early_stopping: true
repetition_penalty: 3.5
length_penalty: 0.3
encoder_no_repeat_ngram_size: 3
num_beams: 4
model-index:
- name: pszemraj/long-t5-tglobal-base-16384-booksum-V12
results:
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge
value: 30.0032
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjk2MTRiNDljZTM4NzliNDdmMTdkZGY3MGY4OTVmMzFhOTdjNGFjYjJhYTBjYTI4Y2VkOGMxYWI5M2M3YWEyZSIsInZlcnNpb24iOjF9.cZtcCwB1Bnnn1g4x8Ia_8oTSK89feGF80r20jwjSb-xy5Xt3eR3dOVjJyjurfN0UOGyEe7inTpneJhcAoRwwBg
- type: rouge
value: 7.2671
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNThiYmJhN2NkYmU0MmZmZGY5MGU2NmEzZGQwNjM0MDEwNzlhNDgzY2E2MzkxMWVkZTUwMWFlZmFhYWEwN2M5ZSIsInZlcnNpb24iOjF9.IaaaHiOxUdh6IDGbb2vCCEcL-YhXCtaFlZnIpcgQwsC3KRgfrpQi5vdhyaaIJSieA2pzbFjUO--WqjylvpysCA
- type: rouge
value: 21.8779
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTc1N2YwODk4YmU1Mjk3NGQ2ZDVkYWVjN2Y1ZDVlOTNkMjU5MjcyYjY0ZWY5NjJkNzZjNjMwZWUxNWY0NTY1ZiIsInZlcnNpb24iOjF9.HhYA0t2Ee3YhtBDPneU7hzEEz5c4FeBcTo-3TSSClltG3A5E3RIgbxUbQNbldRAL9Y44Z8uzEHfe676eL22vBg
- type: rouge
value: 26.4371
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTJmZmJhZTBiZDczYmNkNWQ0MGQ3ZTIyNzc2NGExMGY1MGNkOThlNDg0OWQ3YWFmNDRmYTUxZTYzN2U5Yzc4MCIsInZlcnNpb24iOjF9.fgr8NNlhDCvtXMudOce1pf_slujIhXAEC3a6fH6AAlgIvzxg1oGV5QiUcrPDNhyFD2XazZ39Xk1GhoMk4AnxAQ
- type: loss
value: 2.6383285522460938
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjRiMjAyMjJkM2M5NGZjYzRiZGFlNTJhM2UyNjExODlmNjM4NjRmZTRlMWEzMTUzYTI2NjYzYTAyNmVlYjJjMCIsInZlcnNpb24iOjF9.wKAqpXyvHNGDpxwLmR6mzI4gRwVQI88uFJZJoRAWQD_d-H97y5cpP4VSBes_YfVpFpYzEF8miN9fv660xukiBA
- type: gen_len
value: 54.2357
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzA1Y2IxN2Q4OGU0N2FkNDFmNTFmMjQwZDA4MTczMDJmNWIyMjdhYzhkNTE5ZjI4M2NjZTdkMmUwMTFjMzk1ZCIsInZlcnNpb24iOjF9.JuADjJNIcaqmZTw1RFnklHJYEYfTEKQ0YnmvL1TmvSihIVJORbK-3cFkJLVJdyaaRq40HjhQRw6mmpur9Lq1CQ
- task:
type: summarization
name: Summarization
dataset:
name: launch/gov_report
type: launch/gov_report
config: plain_text
split: test
metrics:
- type: rouge
value: 37.0538
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzViY2Y2ZWIwMDdhNDEzMDU3MmE4ZTBlZjQ2MDI2YTVjOGZjZDM5NzhiZDk2MWJhZWY5MDUwY2NhZTY2OTc5ZSIsInZlcnNpb24iOjF9.p2z_oZD9uVTnBtf7vRRKvisW-rXWVibpU0QQ-S_16CIYLc2kTJRZMLzaMJqbi1d8icBTeG5PdIzKcAVwu7JKCA
- type: rouge
value: 8.1512
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWUzZGM0ZGJiMDYwM2ZmYjI5Mzk5MTU2N2JlZGVlOGRjMTJjY2QwOWIwMjgyMjM0ZjIzY2Q4MzJjNDkxZmVhMCIsInZlcnNpb24iOjF9.z6pMF8l4uMQIEcdyU1kgDc1v3rCn-0TVxntKP3hmOEwRJqfbeqDmhhAROWadYTPNewpfsCpShVHGJt9DvH55BQ
- type: rouge
value: 17.6645
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWNkYzY2NGY4YmFiNWRhODAwZmFmOTkzM2M3MGY0ZTQzZTUwNmExNDc5ZDdhZWVhZjFhYTUyYjFlZjQ3ZDA4ZCIsInZlcnNpb24iOjF9.XbVCDhR_l7OalwF2DsHJSZ39z_HHdG3PlwKL0Ls9lBvRo4E8sk00vrQy4IRCqPF8hPJusl2Nb65V3CvgIldqAA
- type: rouge
value: 33.4275
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdiYzI0MDlmYjg0MWFjZDBmMmIyZWUyNzNhYTUyNTU1ZDdhODE4ZTlmMTg5MDY1MDhhMGRlMGU1OTA3YzM4ZSIsInZlcnNpb24iOjF9.pDHKUDMXHihmLSQzYq6bxclcLyajcRf6Q5ImhpvpoepG8du5ggwb1q_2anGfDjJ0kkFa-Iwtbl8KmdqD7TTCAQ
- type: loss
value: 2.6052205562591553
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjk0YWNjMjkxZjUwMDBlODNkNjE0ZWRkYzYxZmRjNjBhMmVjNTE2OWFkZTU1OTYzMzMxNzdkMGFlODVjOWVkNCIsInZlcnNpb24iOjF9.n-p8JJBe9nOsKwvS2CHO6HBiI6b-0dUZuVaL9aQgX_qFhETvwR_gHggWXU6sCiLCzkElH6ZpGpcMw9AogJWkCw
- type: gen_len
value: 201.5951
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzMyYWViNDNjMzY2NmQyZjI5MWU2ZjMwMmYyOGFkMzM0YzgwMzg5ZDhmYzYzYzg0OTMzOWY5ZDRiM2NkNWViOSIsInZlcnNpb24iOjF9.6T6C1dimUVOHNbqm5drVZmiWVrQEC0VBc7nSAiyLm2K3WE99FisSByk4zhBtUf_CntT_TZm1dBpfTaAUVPDOAQ
- task:
type: summarization
name: Summarization
dataset:
name: kmfoda/booksum
type: kmfoda/booksum
config: kmfoda--booksum
split: test
metrics:
- type: rouge
value: 36.1423
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTZkYTA5N2FhNjVhMzg1ZDRjOThhZjcwMjdmYzQ1MGE5N2RhNTM0MmNjMzVkYjNlYmZjOGZjMDFlZDBkMGM5MSIsInZlcnNpb24iOjF9.odQ-NMcQ06o2mqzXOfGY1c967_RUfg93YfGnMTpKUXPM5dGawkdVYGO8rPCHt5bttPvYlBmRgNl6Z7H_OhgnCA
- type: rouge
value: 5.634
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkODViOTg2MDYxZDhlMjZiOTNjZWE2ZTI5YmVhYWRiNGM1OTAzZDEzN2Y1ODI4OWI3NzU2ZmZlMGJjNGIyZiIsInZlcnNpb24iOjF9.4-VpnxVDiC0AG-de1dFr6VHNNbK2qZhAMQ62EpVU7Et-n25w8GPcoyr9l4AXIodQpU6p0H0pdntEUqQwJOHaDg
- type: rouge
value: 16.3747
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzkzYWY1NmEyMWNkODQ2N2ExYzMwNWExZDgwNTkxMTg5OTNjYjU5NjMwNWU3NzZhZDYwYzA4M2I0ZmU3Yjg2NiIsInZlcnNpb24iOjF9.tY2mQ0bZU9GMYYTJPot_vgvmiAoubdYWAzEQSQskigleh7AWtsXbO2CnhBsE_7UpsLPVWGccP0IWkHdHRg9zAA
- type: rouge
value: 33.0665
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTEyZGZlNmRhNjllMGExZTJhOWE0NDQwN2Q3MjQyZmM5OGZjZDQwMGE4MGRiMjJmMWVmNjc2ZTQwOWFlMTdmNyIsInZlcnNpb24iOjF9.W1bgFs6XhmbeWJlX_6IvWx6MX-yUj5ErdBU1cGAAZRrEA0elBa_-FdbRkwnLDcBNmBm16vtxPAQfQgJQXmIcDA
- type: loss
value: 2.454127550125122
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTQ0OGMyZGNmZjVlMDYzOTA1NjdlZjZhOThhN2M3ZTZjNWM5N2Y2MjQwZjg4Y2E4MjhiOWUzODFiMzY1YzU0NyIsInZlcnNpb24iOjF9.TOjsyBEWqDD5N9FzJPE9Z7Poj0oXefGryUy7rgj4uXbbWb8DMsMXMcxNVEKixG_vbGyFyASSmgyeW6bAFHaPCw
- type: gen_len
value: 239.4179
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGZmOWY5NmMyNjUzZDM2NmNjNzBjMzU2OTMxYWE2MGFhM2JiMmFmNzQwOTg4NGY5Yzc1NmZjNGZmZjM5NWQzNyIsInZlcnNpb24iOjF9.piE6u39D58dKz2HimpE4Fng7cHELJPuSpZaoEU3gOXSXYw_lx2KQhi2VfFg-mUasmLuQn4bBvMJcWXyBTY8YBw
- task:
type: summarization
name: Summarization
dataset:
name: big_patent
type: big_patent
config: y
split: test
metrics:
- type: rouge
value: 35.615
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWM4ZWQxMjBmNzFlYWMwODg5YTEzOWRmYzBiNmI4ZjBmNmFiZjk2NWQxNDFmY2QzNTA3ZTc5ODZkNmJkZGE4NSIsInZlcnNpb24iOjF9.MABjYbSyTQrT0QxzXM9VRpdDb5dchk1GI_TD_NSB27ozZdWEXyZ-dp44jR-M9mJTSsGk60czxmCF1gq-e4YhAQ
- type: rouge
value: 8.2625
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTk3MmI3ZmQyOTlmYzc4YTkwNjBjOTM3YmE5NjQxOGVkMDFlODc4YjgxMzlhNGRkYThkMzQ5OTU4YWFjYTg0NiIsInZlcnNpb24iOjF9.KHipwLhPWwc55GQpvNe3bSrKOgaAs4sFvLEGvzVa4HWWyvz4oX2ZaytYnURH9Xid7d9nTr7zWYYiwQ7TmSXPDA
- type: rouge
value: 19.9883
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTlhZDk5ZmEyYzgxY2IyNWI1MTk1Nzg2YmVlNmRhMjcyZmFmMWZkNGQ4OWEwYjQwYTk3YzllODdiNzRkN2M5ZCIsInZlcnNpb24iOjF9.ah1-tJ5rUuUToNUHUMf9v9_TGJdhffBMdPDthvo3fmKcFtUQFAMwIloGLp0ePcCS_h8IMEyrtpMwqcDc7jrgAw
- type: rouge
value: 30.1801
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzViMzBiY2I2NWNkMjJmMmZhOTk2YzY3NTFhZTIxOTAzY2ZmNmJlYTlmZDI4YjAyYmRiNDRlNTk0MWJjMmY1MCIsInZlcnNpb24iOjF9.KUPyHMK77clPtJHyXR5WirKcy5O5hZP-MBZE-gFRy21S_sIsHpZNnBuGTJ6AMVi_38MNvDgLQWwSE-4y9eG8Dg
- type: loss
value: 2.8106656074523926
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjA1ZTk2NzA5NDUwMjQ1ZDcxZTA0ZTA3YzdjYzhhZWM1ZjI3MTllYTg2YzAxOTk0Nzk1Yjc0OTRiNzIyOWExZSIsInZlcnNpb24iOjF9.q2sdYyFeFxpjGPKGpJDnoOmzTznwA1Z99GBWOHA-9YUI5q_w_kbV8JdfbiQ9GsaN8EqDlmkCL2kv5lC3xvvUAA
- type: gen_len
value: 170.3483
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2MxNWFjYTg1Yjc3YmNjMjViYjM5ZDdmY2NhNjFjMWQxYWQwOWI3NTczY2M5ZWVmMGM2MmQ0ZmY3M2Y0MDEwZiIsInZlcnNpb24iOjF9.J80uRlSZCVIsvyVkO8rqQ4vyZrgBMu1YpOckAzIaj_jTWKGaOPM3kj6sSePiEN8OLZYwDueqLsKkPa0B6ZXIBw
---
# pszemraj/long-t5-tglobal-base-16384-booksum-V12
> this checkpoint has some further training and is **exists separately to confirm metrics before merging to main**
- training metadata data in [this json](training_metadata.json)
- the main model can be found [here](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary)
|
Subsets and Splits