LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Stablelm 2 12B Chat by stabilityai

 »  All LLMs  »  stabilityai  »  Stablelm 2 12B Chat   URL Share it on

  742   

Stablelm 2 12B Chat is an open-source language model by stabilityai. Features: 12b LLM, VRAM: 24.4GB, Context: 4K, License: other, Instruction-Based, HF Score: 68.4, LLM Explorer Score: 0.2, Arc: 64.9, HellaSwag: 86, MMLU: 61.1, TruthfulQA: 62, WinoGrande: 78.5, GSM8K: 57.9.

  Arxiv:2305.18290   Arxiv:2402.17834   Conversational Dataset:allenai/ultrafeedback ...   Dataset:anthropic/hh-rlhf Dataset:glaiveai/glaive-functi...   Dataset:hkust-nlp/deita-10k-v0 Dataset:huggingfaceh4/ultracha...   Dataset:intel/orca dpo pairs   Dataset:ldjnr/capybara   Dataset:meta-math/metamathqa Dataset:openchat/openchat shar... Dataset:wizardlm/wizardlm evol...   En   Endpoints compatible   Instruct   Region:us   Safetensors   Sharded   Stablelm   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stabilityai/stablelm-2-12b-chat 

Stablelm 2 12B Chat Benchmarks

MMLU Pro: 19.27
GPQA: 2.24
MUSR: 7.73
BBH: 25.25
IFEval: 40.82 vs 88 (so35)-53.6%
ARC: 64.85 vs 96.7 (so35)-32.9%
HellaSwag: 85.96 vs 95.3 (gpt4)-9.8%
MMLU: 61.06 vs 88.3 (so35)-30.8%
TruthfulQA: 62.01 vs 59 (gpt4)5.1%
WinoGrande: 78.53 vs 87.5 (gpt4)-10.3%
GSM8K: 57.85 vs 96.4 (so35)-40%
MATH Lvl 5: 5.36
LLME Score: 0.19931
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stablelm 2 12B Chat (stabilityai/stablelm-2-12b-chat)
🌟 Advertise your project 🚀

Stablelm 2 12B Chat Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
chat-like applications
Limitations:
requires guardrails around inputs and outputs to prevent harmful responses, not suitable for applications that may cause harm
Supported Languages 
English (unknown)
Training Details 
Data Sources:
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, Anthropic/hh-rlhf, glaiveai/glaive-function-calling-v2, Internal Safety Dataset
Methodology:
Direct Preference Optimization (DPO)
Model Architecture:
transformer decoder architecture
LLM NameStablelm 2 12B Chat
Repository 🤗https://huggingface.co/stabilityai/stablelm-2-12b-chat 
Model Size12b
Required VRAM24.4 GB
Updated2026-04-25
Maintainerstabilityai
Model Typestablelm
Instruction-BasedYes
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   5.0 GB: 4-of-5   4.4 GB: 5-of-5
Supported Languagesen
Model ArchitectureStableLmForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.40.0
Tokenizer ClassGPT2TokenizerFast
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Rank the Stablelm 2 12B Chat Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53254 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer