CodeLlama 34B Guanaco by mzbac

 ยป  All LLMs  ยป  mzbac  ยป  CodeLlama 34B Guanaco   URL Share it on

  Autotrain compatible   Codegen   Endpoints compatible   Llama   Pytorch   Region:us   Sharded

CodeLlama 34B Guanaco 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 Guanaco (mzbac/CodeLlama-34b-guanaco)

CodeLlama 34B Guanaco Parameters and Internals

Model Type 
fine-tuned, text generation
Use Cases 
Limitations:
struggles to determine the end of the answer
Training Details 
Data Sources:
OpenAssistant-Guanaco dataset
Methodology:
fine-tuned on text chunks instead of Q&A pairs
Input Output 
Input Format:
### Human: {prompt} ### Assistant:
Accepted Modalities:
text
Performance Tips:
Recommend using a stop string like "### Human:" to prevent the model from talking to itself.
LLM NameCodeLlama 34B Guanaco
Repository ๐Ÿค—https://huggingface.co/mzbac/CodeLlama-34b-guanaco 
Model Size34b
Required VRAM67.5 GB
Updated2024-12-22
Maintainermzbac
Model Typellama
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
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.34.0
Tokenizer ClassCodeLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the CodeLlama 34B Guanaco

Model
Likes
Downloads
VRAM
CodeLlama 34B Guanaco Gptq573718 GB

Best Alternatives to CodeLlama 34B Guanaco

Best Alternatives
Context / RAM
Downloads
Likes
...gpt 32K Codellama 34B Instruct32K / 67.5 GB4812
CodeLlama 34B Instruct Hf16K / 67.5 GB45712280
ReflectionCoder CL 34B16K / 67.6 GB35720
Phind CodeLlama 34B V216K / 67.5 GB2736830
Speechless Codellama 34B V2.016K / 67.5 GB116617
Phind CodeLlama 34B V116K / 67.5 GB942324
CodeLlama 34B Hf16K / 67.5 GB8286168
CodeLlama 34B Instruct Hf16K / 67.5 GB212214
Phind CodeLlama 34B Python V116K / 67.5 GB916253
CodeLlama 34B Python Hf16K / 67.5 GB414194
Note: green Score (e.g. "73.2") means that the model is better than mzbac/CodeLlama-34b-guanaco.

Rank the CodeLlama 34B Guanaco 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? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217