metadata

language:
  - en
license: other
tags:
  - causal-lm
datasets:
  - HuggingFaceH4/ultrachat_200k
  - allenai/ultrafeedback_binarized_cleaned
  - meta-math/MetaMathQA
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - openchat/openchat_sharegpt4_dataset
  - LDJnr/Capybara
  - Intel/orca_dpo_pairs
  - hkust-nlp/deita-10k-v0
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-2-zephyr-1_6b
    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: 43.69
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          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: 69.3
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          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: 42.03
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          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: 45.11
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          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: 64.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          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: 35.33
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/stablelm-2-zephyr-1_6b
          name: Open LLM Leaderboard

`StableLM 2 Zephyr 1.6B`

Model Description

Stable LM 2 Zephyr 1.6B is a 1.6 billion parameter instruction tuned language model inspired by HugginFaceH4's Zephyr 7B training pipeline. The model is trained on a mix of publicly available datasets and synthetic datasets, utilizing Direct Preference Optimization (DPO).

Usage

StableLM 2 Zephyr 1.6B uses the following instruction format:

<|user|>
Which famous math number begins with 1.6 ...?<|endoftext|>
<|assistant|>
The number you are referring to is 1.618033988749895. This is the famous value known as the golden ratio<|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-2-zephyr-1_6b')
model = AutoModelForCausalLM.from_pretrained(
    'stabilityai/stablelm-2-zephyr-1_6b',
    device_map="auto"
)

prompt = [{'role': 'user', 'content': 'Which famous math number begins with 1.6 ...?'}]
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=0.5,
    do_sample=True
)

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

Model Details

Developed by: Stability AI
Model type: StableLM 2 Zephyr 1.6B model is an auto-regressive language model based on the transformer decoder architecture.
Language(s): English
Paper: Stable LM 2 1.6B Technical Report
Library: Alignment Handbook
Finetuned from model: https://huggingface.co/stabilityai/stablelm-2-1_6b
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 lm@stability.ai

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
openchat/openchat_sharegpt4_dataset
LDJnr/Capybara
hkust-nlp/deita-10k-v0

Preference Datasets:

allenai/ultrafeedback_binarized_cleaned
Intel/orca_dpo_pairs

Performance

MT-Bench

Model	Size	MT-Bench
Mistral-7B-Instruct-v0.2	7B	7.61
Llama2-Chat	70B	6.86
stablelm-zephyr-3b	3B	6.64
MPT-30B-Chat	30B	6.39
stablelm-2-zephyr-1.6b	1.6B	5.42
Falcon-40B-Instruct	40B	5.17
Qwen-1.8B-Chat	1.8B	4.95
dolphin-2.6-phi-2	2.7B	4.93
phi-2	2.7B	4.29
TinyLlama-1.1B-Chat-v1.0	1.1B	3.46

OpenLLM Leaderboard

Model	Size	Average	ARC Challenge (acc_norm)	HellaSwag (acc_norm)	MMLU (acc_norm)	TruthfulQA (mc2)	Winogrande (acc)	Gsm8k (acc)
microsoft/phi-2	2.7B	61.32%	61.09%	75.11%	58.11%	44.47%	74.35%	54.81%
stabilityai/stablelm-2-zephyr-1_6b	1.6B	49.89%	43.69%	69.34%	41.85%	45.21%	64.09%	35.18%
microsoft/phi-1_5	1.3B	47.69%	52.90%	63.79%	43.89%	40.89%	72.22%	12.43%
stabilityai/stablelm-2-1_6b	1.6B	45.54%	43.43%	70.49%	38.93%	36.65%	65.90%	17.82%
mosaicml/mpt-7b	7B	44.28%	47.70%	77.57%	30.80%	33.40%	72.14%	4.02%
KnutJaegersberg/Qwen-1_8B-Llamaified*	1.8B	44.75%	37.71%	58.87%	46.37%	39.41%	61.72%	24.41%
openlm-research/open_llama_3b_v2	3B	40.28%	40.27%	71.60%	27.12%	34.78%	67.01%	0.91%
iiuae/falcon-rw-1b	1B	37.07%	35.07%	63.56%	25.28%	35.96%	62.04%	0.53%
TinyLlama/TinyLlama-1.1B-3T	1.1B	36.40%	33.79%	60.31%	26.04%	37.32%	59.51%	1.44%

Training Infrastructure

Hardware: StableLM 2 Zephyr 1.6B 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.

Use and Limitations

Intended Use

The model is intended to be used in chat-like applications. Developers must evaluate the model for safety performance in their specific use case. Read more about safety and limitations below.

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 will hallucinate many facts. It is also 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.

How to Cite

@misc{StableLM-2-1.6B,
      url={[https://huggingface.co/stabilityai/stablelm-2-1.6b](https://huggingface.co/stabilityai/stablelm-2-1.6b)},
      title={Stable LM 2 1.6B},
      author={Stability AI Language Team}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	49.99
AI2 Reasoning Challenge (25-Shot)	43.69
HellaSwag (10-Shot)	69.30
MMLU (5-Shot)	42.03
TruthfulQA (0-shot)	45.11
Winogrande (5-shot)	64.48
GSM8k (5-shot)	35.33