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

Stablelm Base Alpha 7B V2 by stabilityai

 »  All LLMs  »  stabilityai  »  Stablelm Base Alpha 7B V2   URL Share it on

  2312   
  Arxiv:1910.02054   Arxiv:2002.05202   Arxiv:2101.00027   Arxiv:2104.09864   Arxiv:2305.06161   Autotrain compatible   Custom code   Dataset:bigcode/starcoderdata   Dataset:carperai/pilev2-dev   Dataset:jeankaddour/minipile Dataset:tiiuae/falcon-refinedw... Dataset:togethercomputer/redpa...   En   Region:us   Safetensors   Sharded   Stablelm alpha   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stabilityai/stablelm-base-alpha-7b-v2 

Stablelm Base Alpha 7B V2 Benchmarks

ARC: 47.35 vs 96.7 (so35)-51%
HellaSwag: 77.08 vs 95.3 (gpt4)-19.1%
MMLU: 45.1 vs 88.3 (so35)-48.9%
TruthfulQA: 36.46 vs 59 (gpt4)-38.2%
WinoGrande: 68.51 vs 87.5 (gpt4)-21.7%
GSM8K: 2.58 vs 96.4 (so35)-97.3%
LLME Score: 0.1562
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stablelm Base Alpha 7B V2 (stabilityai/stablelm-base-alpha-7b-v2)
🌟 Advertise your project 🚀

Stablelm Base Alpha 7B V2 Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
Research, Commercial applications
Limitations:
May contain offensive or inappropriate content due to pre-training data., Not intended for applications that cause harm or distress.
Considerations:
Exercise caution in production systems.
Supported Languages 
English (native)
Training Details 
Data Sources:
tiiuae/falcon-refinedweb, togethercomputer/RedPajama-Data-1T, CarperAI/pilev2-dev, bigcode/starcoderdata, JeanKaddour/minipile
Methodology:
Pre-training with a multi-stage context length extension schedule.
Context Length:
4096
Training Time:
16.33 days
Hardware Used:
384 NVIDIA A100 40GB GPUs on AWS P4d instances
Model Architecture:
Decoder-only transformer with features like SwiGLU activation and rotary position embeddings.
Input Output 
Accepted Modalities:
text
LLM NameStablelm Base Alpha 7B V2
Repository 🤗https://huggingface.co/stabilityai/stablelm-base-alpha-7b-v2 
Model Size7b
Required VRAM27.5 GB
Updated2025-08-20
Maintainerstabilityai
Model Typestablelm_alpha
Model Files  10.0 GB: 1-of-3   9.7 GB: 2-of-3   7.8 GB: 3-of-3
Supported Languagesen
Model ArchitectureStableLMAlphaForCausalLM
Licensecc-by-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.30.2
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typefloat32

Best Alternatives to Stablelm Base Alpha 7B V2

Best Alternatives
Context / RAM
Downloads
Likes
Dragon Stablelm 7B V04K / 13.8 GB14

Rank the Stablelm Base Alpha 7B V2 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? 50767 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.
Release v20241124
  Support LLM Explorer