CodeLlama 34B Instruct Hf by premai-io

 ยป  All LLMs  ยป  premai-io  ยป  CodeLlama 34B Instruct Hf   URL Share it on

  Autotrain compatible   Code   Codegen   Endpoints compatible   Instruct   Llama   Llama2   Region:us   Safetensors

CodeLlama 34B Instruct Hf Benchmarks

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

CodeLlama 34B Instruct Hf Parameters and Internals

Model Type 
text generation
Additional Notes 
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered all scenarios, so the potential outputs cannot be predicted in advance.
Responsible Ai Considerations 
Mitigation Strategies:
Before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
LLM NameCodeLlama 34B Instruct Hf
Repository ๐Ÿค—https://huggingface.co/premai-io/CodeLlama-34b-Instruct-hf 
Model Size34b
Required VRAM1.4 GB
Updated2024-11-21
Maintainerpremai-io
Model Typellama
Instruction-BasedYes
Model Files  1.4 GB: 1-of-49   1.4 GB: 2-of-49   1.4 GB: 3-of-49   1.4 GB: 4-of-49   1.4 GB: 5-of-49   1.4 GB: 6-of-49   1.4 GB: 7-of-49   1.4 GB: 8-of-49   1.4 GB: 9-of-49   1.4 GB: 10-of-49   1.4 GB: 11-of-49   1.4 GB: 12-of-49   1.4 GB: 13-of-49   1.4 GB: 14-of-49   1.4 GB: 15-of-49   1.4 GB: 16-of-49   1.4 GB: 17-of-49   1.4 GB: 18-of-49   1.4 GB: 19-of-49   1.4 GB: 20-of-49   1.4 GB: 21-of-49   1.4 GB: 22-of-49   1.4 GB: 23-of-49   1.4 GB: 24-of-49   1.4 GB: 25-of-49   1.4 GB: 26-of-49   1.4 GB: 27-of-49   1.4 GB: 28-of-49   1.4 GB: 29-of-49   1.4 GB: 30-of-49   1.4 GB: 31-of-49   1.4 GB: 32-of-49   1.4 GB: 33-of-49   1.4 GB: 34-of-49   1.4 GB: 35-of-49   1.4 GB: 36-of-49   1.4 GB: 37-of-49   1.4 GB: 38-of-49   1.4 GB: 39-of-49   1.4 GB: 40-of-49   1.4 GB: 41-of-49   1.4 GB: 42-of-49   1.4 GB: 43-of-49   1.4 GB: 44-of-49
Supported Languagescode
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0.dev0
Vocabulary Size32000
Torch Data Typebfloat16
CodeLlama 34B Instruct Hf (premai-io/CodeLlama-34b-Instruct-hf)

Quantized Models of the CodeLlama 34B Instruct Hf

Model
Likes
Downloads
VRAM
CodeLlama 34B Instruct Fp167236767 GB

Best Alternatives to CodeLlama 34B Instruct Hf

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
MathCoder CL 34B16K / 67.5 GB892
...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 premai-io/CodeLlama-34b-Instruct-hf.

Rank the CodeLlama 34B Instruct Hf 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