MathCoder CL 34B by MathLLMs

 ยป  All LLMs  ยป  MathLLMs  ยป  MathCoder CL 34B   URL Share it on

  Arxiv:2310.03731   Autotrain compatible   Codegen   En   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow

MathCoder CL 34B Benchmarks

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

MathCoder CL 34B Parameters and Internals

Model Type 
text generation
Additional Notes 
The models are specifically tailored for general math problem-solving.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
MathCodeInstruct Dataset
Methodology:
Fine-tuned with the MathCodeInstruct dataset using the original Llama-2 and CodeLlama models as base models
LLM NameMathCoder CL 34B
Repository ๐Ÿค—https://huggingface.co/MathLLMs/MathCoder-CL-34B 
Model Size34b
Required VRAM67.5 GB
Updated2024-11-21
MaintainerMathLLMs
Model Typellama
Instruction-BasedYes
Model Files  9.8 GB: 1-of-7   9.7 GB: 2-of-7   9.7 GB: 3-of-7   9.7 GB: 4-of-7   9.7 GB: 5-of-7   9.7 GB: 6-of-7   9.2 GB: 7-of-7
Supported Languagesen
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32008
Torch Data Typebfloat16
MathCoder CL 34B (MathLLMs/MathCoder-CL-34B)

Best Alternatives to MathCoder CL 34B

Best Alternatives
Context / RAM
Downloads
Likes
...gpt 32K Codellama 34B Instruct32K / 67.5 GB8692
CodeLlama 34B Instruct Hf16K / 67.5 GB12497278
Speechless Codellama 34B V2.016K / 67.5 GB140017
CodeLlama 34B Instruct Hf16K / 67.5 GB367413
Speechless Codellama 34B V1.916K / 67.5 GB13870
XAgentLLaMa 34B Preview16K / 157.3 GB233
CodeLlama 34B Instruct Hf16K / 1.4 GB223
...gpt 16K Codellama 34B Instruct16K / 67.5 GB244
CodeLlama 34B Instruct Fp1616K / 67.5 GB23677
...M 1.0 Uncensored CodeLlama 34B16K / 67.5 GB2227
Note: green Score (e.g. "73.2") means that the model is better than MathLLMs/MathCoder-CL-34B.

Rank the MathCoder CL 34B 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? 38199 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110