Model reference · open weights

stablelm-2-zephyr-1

Available as managed deployment Licence fee LLMs stabilityai Text gen 1 variants 11k dl/mo

stablelm-2-zephyr-1 is an open-weight language model from stabilityai. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Makerstabilityai
TypeLanguage models
TaskText gen
Parameters (lead)1.6B
Runs withtransformers
Released2024-01-19
Popularity11k downloads / month
LicenceCommercial licence needed

About

What stablelm-2-zephyr-1 is

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:

Which famous math number begins with 1.6 ...?
The number you are referring to is 1.618033988749895. This is the famous value known as the golden ratio

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

Training Dataset

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

  1. 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
  1. Preference Datasets:
  • allenai/ultrafeedback_binarized_cleaned
  • Intel/orca_dpo_pairs

Performance

MT-Bench

ModelSizeMT-Bench
Mistral-7B-Instruct-v0.27B7.61
Llama2-Chat70B6.86
stablelm-zephyr-3b3B6.64
MPT-30B-Chat30B6.39
stablelm-2-zephyr-1.6b1.6B5.42
Falcon-40B-Instruct40B5.17
Qwen-1.8B-Chat1.8B4.95
dolphin-2.6-phi-22.7B4.93
phi-22.7B4.29
TinyLlama-1.1B-Chat-v1.01.1B3.46

OpenLLM Leaderboard

ModelSizeAverageARC Challenge (acc_norm)HellaSwag (acc_norm)MMLU (acc_norm)TruthfulQA (mc2)Winogrande (acc)Gsm8k (acc)
microsoft/phi-22.7B61.32%61.09%75.11%58.11%44.47%74.35%54.81%
stabilityai/stablelm-2-zephyr-1_6b1.6B49.89%43.69%69.34%41.85%45.21%64.09%35.18%
microsoft/phi-1_51.3B47.69%52.90%63.79%43.89%40.89%72.22%12.43%
stabilityai/stablelm-2-1_6b1.6B45.54%43.43%70.49%38.93%36.65%65.90%17.82%
mosaicml/mpt-7b7B44.28%47.70%77.57%30.80%33.40%72.14%4.02%
KnutJaegersberg/Qwen-1_8B-Llamaified*1.8B44.75%37.71%58.87%46.37%39.41%61.72%24.41%
openlm-research/open_llama_3b_v23B40.28%40.27%71.60%27.12%34.78%67.01%0.91%
iiuae/falcon-rw-1b1B37.07%35.07%63.56%25.28%35.96%62.04%0.53%
TinyLlama/TinyLlama-1.1B-3T1.1B36.40%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.

L

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys stablelm-2-zephyr-1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (stablelm-2-zephyr-1 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"stablelm-2-zephyr-1","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms