LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Phind CodeLlama 34B V1 GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  Phind CodeLlama 34B V1 GGUF   URL Share it on

  819   
Base model:phind/phind-codella... Base model:quantized:phind/phi...   Code llama   Codegen   Gguf   Llama   Model-index   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/Phind-CodeLlama-34B-v1-GGUF 

Phind CodeLlama 34B V1 GGUF Benchmarks

LLME Score: 0.14133
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phind CodeLlama 34B V1 GGUF (TheBloke/Phind-CodeLlama-34B-v1-GGUF)

Phind CodeLlama 34B V1 GGUF Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model is not chat-tuned. It achieved 67.6% pass@1 on HumanEval and is improved in version v2 at 73.8% pass@1.
Training Details 
Data Sources:
Internal Phind dataset
Data Volume:
~80k high quality programming problems and solutions
Methodology:
Fine-tuned from CodeLlama-34B without using LoRA.
Context Length:
4096
Training Time:
3 hours
Hardware Used:
32 A100-80GB GPUs
Input Output 
Input Format:
{prompt} \n
Accepted Modalities:
text
LLM NamePhind CodeLlama 34B V1 GGUF
Repository 🤗https://huggingface.co/TheBloke/Phind-CodeLlama-34B-v1-GGUF 
Model CreatorPhind
Base Model(s)  Phind CodeLlama 34B V1   Phind/Phind-CodeLlama-34B-v1
Model Size34b
Required VRAM14.2 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  14.2 GB   17.8 GB   16.3 GB   14.6 GB   19.1 GB   20.2 GB   19.1 GB   23.2 GB   23.8 GB   23.2 GB   27.7 GB   35.9 GB
GGUF QuantizationYes
Quantization Typegguf
Generates CodeYes
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Phind CodeLlama 34B V1 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Phind CodeLlama 34B V2 GGUF0K / 14.2 GB3622163
CodeLlama 34B Instruct Hf GGUF0K / 12.5 GB1091
CodeLlama 34B Python Hf GGUF0K / 12.5 GB1001
CodeLlama 34B Hf GGUF0K / 12.5 GB703
CodeLlama 34B Instruct GGUF0K / 14.2 GB255595
CodeLlama 34B GGUF0K / 14.2 GB293455
...allistic CodeLlama 34B V1 GGUF0K / 35.9 GB140
...chless Codellama 34B V2.0 GGUF0K / 14.2 GB42010
CodeLlama 34B Python GGUF0K / 14.2 GB131536
...d CodeLlama 34B Python V1 GGUF0K / 14.2 GB113413
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Phind-CodeLlama-34B-v1-GGUF.

Rank the Phind CodeLlama 34B V1 GGUF Capabilities

🆘 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! 🌟

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? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer