Coma 7B V0.1 by DevQuasar

 ยป  All LLMs  ยป  DevQuasar  ยป  Coma 7B V0.1   URL Share it on

  Arxiv:2203.05482   Autotrain compatible Base model:merge:meta-llama/co... Base model:merge:meta-llama/ll... Base model:meta-llama/codellam... Base model:meta-llama/llama-2-...   Codegen   Endpoints compatible   Llama   Merge   Mergekit   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/DevQuasar/coma-7B-v0.1 

Coma 7B V0.1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Coma 7B V0.1 (DevQuasar/coma-7B-v0.1)

Coma 7B V0.1 Parameters and Internals

Additional Notes 
Experiment to try merged models using mergekit.
Training Details 
Methodology:
Merge of pre-trained models using linear merge method
Model Architecture:
Merge of meta-llama/Llama-2-7b-hf and meta-llama/CodeLlama-7b-hf models
LLM NameComa 7B V0.1
Repository ๐Ÿค—https://huggingface.co/DevQuasar/coma-7B-v0.1 
Base Model(s)  Llama 2 7B Hf   CodeLlama 7B Hf   meta-llama/Llama-2-7b-hf   meta-llama/CodeLlama-7b-hf
Model Size7b
Required VRAM13.6 GB
Updated2025-03-14
MaintainerDevQuasar
Model Typellama
Model Files  0.9 GB: 1-of-14   1.0 GB: 2-of-14   1.0 GB: 3-of-14   1.0 GB: 4-of-14   1.0 GB: 5-of-14   0.9 GB: 6-of-14   1.0 GB: 7-of-14   1.0 GB: 8-of-14   1.0 GB: 9-of-14   1.0 GB: 10-of-14   0.9 GB: 11-of-14   1.0 GB: 12-of-14   1.0 GB: 13-of-14   0.9 GB: 14-of-14
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Coma 7B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Coder 6.7B Instruct16K / 13.5 GB88134384
CodeLlama 7B Hf16K / 13.5 GB63516351
CodeLlama 7B Instruct Hf16K / 13.5 GB41958225
CodeLlama 7B Instruct Hf16K / 13.5 GB2815444
GetCode Slerp16K / 13.6 GB17371
MathCoder2 CodeLlama 7B16K / 13.5 GB255
CodeLlama 7B Hf16K / 13.5 GB440788
CodeLlama 7B Python Hf16K / 13.5 GB7179139
Wizardllama 7B16K / 13.5 GB130
CodeLlama 7B Hf16K / 13.5 GB92033
Note: green Score (e.g. "73.2") means that the model is better than DevQuasar/coma-7B-v0.1.

Rank the Coma 7B V0.1 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? 45019 in total.

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