HuggingFaceH4

zephyr-7b-beta

Deploy Dedicated

Model description

Model type: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
Language(s) (NLP): Primarily English
License: MIT
Finetuned from model: mistralai/Mistral-7B-v0.1

Model Sources

Repository: https://github.com/huggingface/alignment-handbook
Demo: https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org

Performance

At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:

Table with columns: Model, Size, Alignment, MT-Bench (score), AlpacaEval (win rate %)
Model	Size	Alignment	MT-Bench (score)	AlpacaEval (win rate %)
StableLM-Tuned-α	7B	dSFT	2.75	-
MPT-Chat	7B	dSFT	5.42	-
Xwin-LMv0.1	7B	dPPO	6.19	87.83

In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:

image/png

However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.

Intended uses & limitations

The model was initially fine-tuned on a filtered and preprocessed of the UltraChat dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with 🤗 TRL's DPOTrainer on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.

You can find the datasets used for training Zephyr-7B-β here

Here's how you can run the model using the pipeline() function from 🤗 Transformers:

python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!

Bias, Risks, and Limitations

Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.1), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.

Training and evaluation data

During DPO training, this model achieves the following results on the evaluation set:

Loss: 0.7496
Rewards/chosen: -4.5221
Rewards/rejected: -8.3184
Rewards/accuracies: 0.7812
Rewards/margins: 3.7963
Logps/rejected: -340.1541
Logps/chosen: -299.4561
Logits/rejected: -2.3081
Logits/chosen: -2.3531

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 32
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

The table below shows the full set of DPO training metrics:

Table with columns: Training Loss, Epoch, Step, Validation Loss, Rewards/chosen, Rewards/rejected, Rewards/accuracies, Rewards/margins, Logps/rejected, Logps/chosen, Logits/rejected, Logits/chosen
Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6284	0.05	100	0.6098	0.0425	-0.1872	0.7344

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.14.0

Citation

If you find Zephyr-7B-β is useful in your work, please cite it with:

markdown
@misc{tunstall2023zephyr,
      title={Zephyr: Direct Distillation of LM Alignment}, 
      author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
      year={2023},
      eprint={2310.16944},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

If you use the UltraChat or UltraFeedback datasets, please cite the original works:

markdown
@misc{ding2023enhancing,
      title={Enhancing Chat Language Models by Scaling High-quality Instructional Conversations}, 
      author={Ning Ding and Yulin Chen and Bokai Xu and Yujia Qin and Zhi Zheng and Shengding Hu and Zhiyuan Liu and Maosong Sun and Bowen Zhou},
      year={2023},
      eprint={2305.14233},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{cui2023ultrafeedback,
      title={UltraFeedback: Boosting Language Models with High-quality Feedback}, 
      author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
      year={2023},
      eprint={2310.01377},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Table with columns: Metric, Value
Metric	Value
Avg.	52.15
ARC (25-shot)	62.03
HellaSwag (10-shot)	84.36
MMLU (5-shot)	61.07
TruthfulQA (0-shot)	57.45
Winogrande (5-shot)	77.74
GSM8K (5-shot)	12.74
DROP (3-shot)	9.66

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

HuggingFaceH4

Model Tree

Base

mistralai/Mistral-7B-v0.1

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

Model description

Model type: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
Language(s) (NLP): Primarily English
License: MIT
Finetuned from model: mistralai/Mistral-7B-v0.1

Model Sources

Repository: https://github.com/huggingface/alignment-handbook
Demo: https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org

Performance

At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:

Table with columns: Model, Size, Alignment, MT-Bench (score), AlpacaEval (win rate %)
Model	Size	Alignment	MT-Bench (score)	AlpacaEval (win rate %)
StableLM-Tuned-α	7B	dSFT	2.75	-
MPT-Chat	7B	dSFT	5.42	-
Xwin-LMv0.1	7B	dPPO	6.19	87.83

In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:

image/png

However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.

Intended uses & limitations

You can find the datasets used for training Zephyr-7B-β here

Here's how you can run the model using the pipeline() function from 🤗 Transformers:

python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!

Bias, Risks, and Limitations

Training and evaluation data

During DPO training, this model achieves the following results on the evaluation set:

Loss: 0.7496
Rewards/chosen: -4.5221
Rewards/rejected: -8.3184
Rewards/accuracies: 0.7812
Rewards/margins: 3.7963
Logps/rejected: -340.1541
Logps/chosen: -299.4561
Logits/rejected: -2.3081
Logits/chosen: -2.3531

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 32
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

The table below shows the full set of DPO training metrics:

Table with columns: Training Loss, Epoch, Step, Validation Loss, Rewards/chosen, Rewards/rejected, Rewards/accuracies, Rewards/margins, Logps/rejected, Logps/chosen, Logits/rejected, Logits/chosen
Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6284	0.05	100	0.6098	0.0425	-0.1872	0.7344

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.14.0

Citation

If you find Zephyr-7B-β is useful in your work, please cite it with:

markdown
@misc{tunstall2023zephyr,
      title={Zephyr: Direct Distillation of LM Alignment}, 
      author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
      year={2023},
      eprint={2310.16944},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

If you use the UltraChat or UltraFeedback datasets, please cite the original works:

markdown
@misc{ding2023enhancing,
      title={Enhancing Chat Language Models by Scaling High-quality Instructional Conversations}, 
      author={Ning Ding and Yulin Chen and Bokai Xu and Yujia Qin and Zhi Zheng and Shengding Hu and Zhiyuan Liu and Maosong Sun and Bowen Zhou},
      year={2023},
      eprint={2305.14233},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{cui2023ultrafeedback,
      title={UltraFeedback: Boosting Language Models with High-quality Feedback}, 
      author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
      year={2023},
      eprint={2310.01377},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Table with columns: Metric, Value
Metric	Value
Avg.	52.15
ARC (25-shot)	62.03
HellaSwag (10-shot)	84.36
MMLU (5-shot)	61.07
TruthfulQA (0-shot)	57.45
Winogrande (5-shot)	77.74
GSM8K (5-shot)	12.74
DROP (3-shot)	9.66

zephyr-7b-beta

README

Model description

Model Sources

Performance

Intended uses & limitations

Bias, Risks, and Limitations

Training and evaluation data

Training hyperparameters

Training results

Framework versions

Citation

Open LLM Leaderboard Evaluation Results

Explore FriendliAI today

README

Model description

Model Sources

Performance

Intended uses & limitations

Bias, Risks, and Limitations

Training and evaluation data

Training hyperparameters

Training results

Framework versions

Citation

Open LLM Leaderboard Evaluation Results