Gemma ChemWiz 16bit by dbands

 ยป  All LLMs  ยป  dbands  ยป  Gemma ChemWiz 16bit   URL Share it on

  16bit   Dataset:ai-mo/numinamath-cot   Dataset:ai4chem/chemdata700k Dataset:andersonbcdefg/chemist... Dataset:medalpaca/medical mead...   Gemma   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Gemma ChemWiz 16bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma ChemWiz 16bit (dbands/Gemma_ChemWiz_16bit)

Gemma ChemWiz 16bit Parameters and Internals

Model Type 
text-generation-inference, transformers
Additional Notes 
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
Supported Languages 
en (high)
Training Details 
Data Sources:
AI-MO/NuminaMath-CoT, AI4Chem/ChemData700K, medalpaca/medical_meadow_mediqa, andersonbcdefg/chemistry
Methodology:
Fine-tuned on chemical memory and logical reasoning using datasets.
Release Notes 
Version:
2024-08-15
Date:
2024-08-15
Notes:
This is now the base model. The model with python RDKit training is created as Gemma_ChemWiz_rdkit_16bit.
Version:
2024-08-15
Date:
2024-08-15
Notes:
Splitting model today. This model will be the base ChemWiz Model.
Version:
2024-08-13
Date:
2024-08-13
Notes:
Second round of AI4Chem/ChemData700K, results of chemical smiles are very low.
Version:
2024-08-12
Date:
2024-08-12
Notes:
medalpaca/medical_meadow_mediqa dataset was used, model converged in less than one epoch.
Version:
2024-08-12
Date:
2024-08-12
Notes:
Fine-tuning on chemical memory rather than chemistry reasoning.
Version:
2024-08-09
Date:
2024-08-09
Notes:
Fine-tuned for logical reasoning, model still experimental.
LLM NameGemma ChemWiz 16bit
Repository ๐Ÿค—https://huggingface.co/dbands/Gemma_ChemWiz_16bit 
Model Size8.5b
Required VRAM17.1 GB
Updated2025-01-20
Maintainerdbands
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
Quantization Type16bit
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.44.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Quantized Models of the Gemma ChemWiz 16bit

Model
Likes
Downloads
VRAM
Gemma ChemWiz Rdkit 16bit0817 GB

Best Alternatives to Gemma ChemWiz 16bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma ChemWiz Rdkit 16bit8K / 17.1 GB80
Openchat 3.5 0106 Gemma8K / 17.1 GB828257
FiLLM3 NER8K / 17.1 GB240
FiLLM Experimental8K / 17.1 GB200
... Health Counseling V0.1 Merged8K / 9.4 GB260
Note: green Score (e.g. "73.2") means that the model is better than dbands/Gemma_ChemWiz_16bit.

Rank the Gemma ChemWiz 16bit 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? 41636 in total.

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