LLM EXPLORER 59,358 MODELS INDEXED

Stablelm 2 1 6B by stabilityai

By stabilityai · 6627 downloads
HF Repo ↗ Copy URL

Stablelm 2 1 6B is an open-source language model by stabilityai. Features: 6b LLM, VRAM: 3.3GB, Context: 4K, License: other, LLM Explorer Score: 0.19, Arc: 43.3, HellaSwag: 70.5, MMLU: 39, GSM8K: 17.4.

  Arxiv:1607.06450   Arxiv:1910.02054   Arxiv:1910.07467   Arxiv:2101.00027   Arxiv:2104.09864   Arxiv:2204.06745   Arxiv:2206.11147   Arxiv:2305.06161   Arxiv:2305.14201   Arxiv:2307.09288   Arxiv:2309.09400   Arxiv:2309.16609   Arxiv:2402.17834   Dataset:bigcode/starcoderdata   Dataset:carperai/pilev2-dev Dataset:dataprovenanceinitiati... Dataset:tiiuae/falcon-refinedw... Dataset:togethercomputer/redpa...   Dataset:uonlp/culturax   De   En   Endpoints compatible   Es   Fr   It   Nl   Pt   Region:us   Safetensors   Stablelm
Model Card on HF 🤗: https://huggingface.co/stabilityai/stablelm-2-1_6b 

Stablelm 2 1 6B Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
research, commercial applications
Applications:
foundational base model for application-specific fine-tuning
Limitations:
May exhibit unreliable, unsafe, or other undesirable behaviors that must be corrected prior to deployment., Pre-training data may have contained offensive or inappropriate content.
Supported Languages 
en (intermediate), de (intermediate), es (intermediate), fr (intermediate), it (intermediate), nl (intermediate), pt (intermediate)
Training Details 
Data Sources:
tiiuae/falcon-refinedweb, togethercomputer/RedPajama-Data-1T, uonlp/CulturaX, CarperAI/pilev2-dev, bigcode/starcoderdata, DataProvenanceInitiative/Commercially-Verified-Licenses
Data Volume:
2 trillion tokens
Methodology:
Pre-trained on diverse multilingual and code datasets for two epochs
Context Length:
4096
Hardware Used:
512 NVIDIA A100 40GB GPUs (AWS P4d instances)
Model Architecture:
Decoder-only transformer similar to the LLaMA architecture with modifications
Input Output 
Input Format:
prompts in tokenized form
Accepted Modalities:
text
Output Format:
generated text
Performance Tips:
Fine-tuning the base model is recommended for downstream tasks.
LLM NameStablelm 2 1 6b
Repository 🤗https://huggingface.co/stabilityai/stablelm-2-1_6b 
Model Size6b
Required VRAM3.3 GB
Updated2026-08-06
Maintainerstabilityai
Model Typestablelm
Model Files  3.3 GB
Supported Languagesen de es fr it nl pt
Model ArchitectureStableLmForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.38.0
Tokenizer ClassGPT2TokenizerFast
Vocabulary Size100352
Torch Data Typefloat16

Best Alternatives to Stablelm 2 1 6B

Best Alternatives
Context / RAM
Downloads
Likes
Stablelm 2 1 6b Chat4K / 6.6 GB194534
Stablelm 2 1 6b Sft Full4K / 3.3 GB50
Cot 5k4K / 3.3 GB13130
StableGPT4 Micro 1.6B4K / 6.6 GB811
StableLM FineTune GPT44K / 6.6 GB51
Parrot 1 6B4K / 3.3 GB11
Stablelm 2 1 6b4K /  GB182
Stablelm 2 Zephyr 1 6b4K /  GB111
Stablelm 2 Zephyr 1 6b4K / 3.3 GB141
Stablelm 2 Zephyr 1 6b Q44K /  GB141