metadata

language:
  - en
license: other
tags:
  - causal-lm
datasets:
  - HuggingFaceH4/ultrachat_200k
  - HuggingFaceH4/ultrafeedback_binarized
  - meta-math/MetaMathQA
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - Intel/orca_dpo_pairs
extra_gated_fields:
  Name: text
  Email: text
  Country: text
  Organization or Affiliation: text
  I ALLOW Stability AI to email me about new model releases: checkbox
model-index:
  - name: stablelm-zephyr-3b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 46.08
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 74.16
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 46.17
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 46.49
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 65.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 42.15
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-zephyr-3b
          name: Open LLM Leaderboard

`StableLM Zephyr 3B`

Model Description

StableLM Zephyr 3B is a 3 billion parameter instruction tuned inspired by HugginFaceH4's Zephyr 7B training pipeline this model was trained on a mix of publicly available datasets, synthetic datasets using Direct Preference Optimization (DPO), evaluation for this model based on MT Bench and Alpaca Benchmark

Usage

StableLM Zephyr 3B uses the following instruction format:

<|user|>
List 3 synonyms for the word "tiny"<|endoftext|>
<|assistant|>
1. Dwarf
2. Little
3. Petite<|endoftext|>

This format is also available through the tokenizer's apply_chat_template method:

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-zephyr-3b')
model = AutoModelForCausalLM.from_pretrained(
    'stabilityai/stablelm-zephyr-3b',
    device_map="auto"
)

prompt = [{'role': 'user', 'content': 'List 3 synonyms for the word "tiny"'}]
inputs = tokenizer.apply_chat_template(
    prompt,
    add_generation_prompt=True,
    return_tensors='pt'
)

tokens = model.generate(
    inputs.to(model.device),
    max_new_tokens=1024,
    temperature=0.8,
    do_sample=True
)

print(tokenizer.decode(tokens[0], skip_special_tokens=False))

You can also see how to run a performance optimized version of this model here using OpenVINO from Intel.

Model Details

Developed by: Stability AI
Model type: StableLM Zephyr 3B model is an auto-regressive language model based on the transformer decoder architecture.
Language(s): English
Library: Alignment Handbook
Finetuned from model: stabilityai/stablelm-3b-4e1t
License: StabilityAI Non-Commercial Research Community License. If you want to use this model for your commercial products or purposes, please contact us here to learn more.
Contact: For questions and comments about the model, please email [email protected]

Training Dataset

The dataset is comprised of a mixture of open datasets large-scale datasets available on the HuggingFace Hub:

SFT Datasets

HuggingFaceH4/ultrachat_200k
meta-math/MetaMathQA
WizardLM/WizardLM_evol_instruct_V2_196k
Open-Orca/SlimOrca

Preference Datasets:

HuggingFaceH4/ultrafeedback_binarized
Intel/orca_dpo_pairs

Performance

MT-Bench and Alpaca Bench

Model	Size	Alignment	MT-Bench (score)	AlpacaEval (win rate %)
StableLM Zephyr 3B 🪁	3B	DPO	6.64	76.00
StableLM Zephyr (SFT only)	3B	SFT	6.04	71.15
Capybara v1.9	3B	dSFT	5.94	-
MPT-Chat	7B	dSFT	5.42	-
Xwin-LM v0.1	7B	dPPO	6.19	87.83
Mistral-Instruct v0.1	7B	-	6.84	-
Zephyr-7b-α	7B	dDPO	6.88	-
Zephyr-7b-β	7B	dDPO	7.34	90.60
Falcon-Instruct	40B	dSFT	5.17	45.71
Guanaco	65B	SFT	6.41	71.80
Llama2-Chat	70B	RLHF	6.86	92.66
Vicuna v1.3	33B	dSFT	7.12	88.99
WizardLM v1.0	70B	dSFT	7.71	-
Xwin-LM v0.1	70B	dPPO	-	95.57
GPT-3.5-turbo	-	RLHF	7.94	89.37
Claude 2	-	RLHF	8.06	91.36
GPT-4	-	RLHF	8.99	95.28

Other benchmarks:

Task	Value
ARC (25-shot)	47.0
HellaSwag (10-shot)	74.2
MMLU (5-shot)	46.3
TruthfulQA (0-shot)	46.5
Winogrande (5-shot)	65.5
GSM8K (5-shot)	42.3
BigBench (Avg)	35.26
AGI Benchmark (Avg)	33.23

Training Infrastructure

Hardware: StableLM Zephyr 3B was trained on the Stability AI cluster across 8 nodes with 8 A100 80GBs GPUs for each nodes.
Code Base: We use our internal script for SFT steps and used HuggingFace Alignment Handbook script for DPO training.

Commitment to Ethical AI

In line with our responsibility towards ethical AI development, StableLM Zephyr 3B is released with a focus on ensuring safety, reliability, and appropriateness in its applications. To this end, we have evaluated StableLM Zephyr 3B on 488 malicious prompts and used standard protocols to assess the harmfulness of its outputs. Compared to Zephyr-7b-β, StableLM Zephyr 3B reduces the number of harmful outputs as assessed by GPT-4 by 55. Additionally, we performed an internal red teaming event targeting the following abuse areas:

Self-Harm Methods: (Suicide Methods, Encouragement of Self-Harm, Methods and encouragement of Eating Disorders)
Misinformation: (Health, Conspiracy Theories, Social Unrest/Conflict, Political Misinformation, & Climate change)
Hate Speech: (Race, Stereotypes, Immigrants, Gender, Personally Identifiable Information such as Social security numbers, Full names, ID numbers, Email addresses, and telephone numbers)

We have incorporated the findings of our malicious prompts evaluation and red teaming event into our release. Users are encouraged to fine-tune and evaluate the model to suit their specific needs, considering the potential biases and limitations found in StableLM Zephyr 3B and inherent in other LLM models.

Use and Limitations

Intended Use

The model is intended to be used as a foundational base model for application-specific fine-tuning. Developers must evaluate and fine-tune the model for safe performance in downstream applications.

Limitations and Bias

This model is not trained against adversarial inputs. We strongly recommend pairing this model with an input and output classifier to prevent harmful responses.

Through our internal red teaming, we discovered that while the model will not output harmful information if not prompted to do so, it is willing to output potentially harmful outputs or misinformation when the user requests it. Using this model will require guardrails around your inputs and outputs to ensure that any outputs returned are not misinformation or harmful. Additionally, as each use case is unique, we recommend running your own suite of tests to ensure proper performance of this model. Finally, do not use the models if they are unsuitable for your application, or for any applications that may cause deliberate or unintentional harm to others.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.43
AI2 Reasoning Challenge (25-Shot)	46.08
HellaSwag (10-Shot)	74.16
MMLU (5-Shot)	46.17
TruthfulQA (0-shot)	46.49
Winogrande (5-shot)	65.51
GSM8k (5-shot)	42.15