CHEMLLM 2B 1 5 by AI4Chem

 ยป  All LLMs  ยป  AI4Chem  ยป  CHEMLLM 2B 1 5   URL Share it on

  Arxiv:2402.06852   Chemistry   Conversational   Custom code   En   Feature-extraction   Internlm2   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF ๐Ÿค—: https://huggingface.co/AI4Chem/CHEMLLM-2b-1_5 

CHEMLLM 2B 1 5 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CHEMLLM 2B 1 5 (AI4Chem/CHEMLLM-2b-1_5)

CHEMLLM 2B 1 5 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
chemistry, molecule science
Primary Use Cases:
conversation, inference in chemical contexts
Considerations:
Usage in professional settings like chemistry and molecule science.
Additional Notes 
Designed to process chemical information and dialogues with scientific nuances and IUPAC naming.
Supported Languages 
en (English), zh (Chinese)
Input Output 
Input Format:
prompt format with context history, uses Dialogue Templates
Accepted Modalities:
text
Output Format:
IUPAC names, reactions in SMARTS, SELFIES
Performance Tips:
Use Dialogue Templates and System Prompts for optimal performance.
Release Notes 
Version:
ChemLLM-1.5
Date:
2024-4-2
Notes:
Released two versions with updates for performance improvements.
Version:
ChemLLM-1.5
Date:
2024-3-23
Notes:
Updated with a demo site and API reference.
Version:
ChemLLM-1.0
Date:
2024-1-18
Notes:
Initial release of ChemLLM-7B-Chat.
LLM NameCHEMLLM 2B 1 5
Repository ๐Ÿค—https://huggingface.co/AI4Chem/CHEMLLM-2b-1_5 
Model Size2b
Required VRAM3.9 GB
Updated2025-02-05
MaintainerAI4Chem
Model Typeinternlm2
Model Files  1.0 GB: 1-of-4   1.0 GB: 2-of-4   1.0 GB: 3-of-4   0.9 GB: 4-of-4
Supported Languagesen zh
Model ArchitectureInternLM2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Is Biased0
Tokenizer ClassInternLM2Tokenizer
Padding Token</s>
Vocabulary Size92544
Torch Data Typebfloat16

Rank the CHEMLLM 2B 1 5 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227