You can deploy this model and start earning money today!

jncraton/
Starling-LM-7B-beta-ct2-int8

Name: Starling-LM-7B-beta-ct2-int8
Availability: InStock

Views

No views yet

Starling-LM-7B-beta

Developed by: Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao.
Model type: Language Model finetuned with RLHF / RLAIF
License: Apache-2.0 license under the condition that the model is not used to compete with OpenAI
Finetuned from model: Openchat-3.5-0106 (based on Mistral-7B-v0.1)

We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO). Harnessing the power of our ranking dataset, berkeley-nest/Nectar, our upgraded reward model, Starling-RM-34B, and our new reward training and policy tuning pipeline, Starling-LM-7B-beta scores an improved 8.12 in MT Bench with GPT-4 as a judge. Stay tuned for our forthcoming code and paper, which will provide more details on the whole process.

For more detailed discussions, please check out our original blog post, and stay tuned for our upcoming code and paper!

Blog: https://starling.cs.berkeley.edu/
Paper: Coming soon!
Code: Coming soon!

Uses

Important: Please use the exact chat template provided below for the model. Otherwise there will be a degrade in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.

Our model follows the exact chat template and usage as Openchat-3.5-0106. Please refer to their model card for more details. In addition, our model is hosted on LMSYS Chatbot Arena for free test.

The conversation template is the same as Openchat-3.5-0106:

import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat-3.5-0106")

# Single-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]

# Multi-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]

# Coding Mode
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]

Code Examples

python

import transformers

tokenizer = transformers.AutoTokenizer.from_pretrained("Nexusflow/Starling-LM-7B-beta")
model = transformers.AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta")

def generate_response(prompt):
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
    outputs = model.generate(
        input_ids,
        max_length=256,
        pad_token_id=tokenizer.pad_token_id,
        eos_token_id=tokenizer.eos_token_id,
    )
    response_ids = outputs[0]
    response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
    return response_text

# Single-turn conversation
prompt = "Hello, how are you?"
single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(single_turn_prompt)
print("Response:", response_text)

## Multi-turn conversation
prompt = "Hello"
follow_up_question =  "How are you today?"
response = ""
multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(multi_turn_prompt)
print("Multi-turn conversation response:", response_text)

### Coding conversation
prompt = "Implement quicksort using C++"
coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:"
response = generate_response(coding_prompt)
print("Coding conversation response:", response)

License

The dataset, model and online demo is subject to the Terms of Use of the data generated by OpenAI, and Privacy Practices of ShareGPT. Please contact us if you find any potential violation.

Acknowledgment

We would like to thank Tianle Li from UC Berkeley for detailed feedback and evaluation of this beta release. We would like to thank the LMSYS Organization for their support of lmsys-chat-1M dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT.

Citation

@misc{starling2023,
    title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF},
    url = {},
    author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Ganesan, Karthik and Chiang, Wei-Lin and Zhang, Jian and Jiao, Jiantao},
    month = {November},
    year = {2023}
}

jncraton/Starling-LM-7B-beta-ct2-int8