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 Python V1 AWQ by TheBloke

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

  27   
  4-bit   Autotrain compatible   Awq Base model:phind/phind-codella... Base model:quantized:phind/phi...   Code llama   Codegen   Llama   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Phind-CodeLlama-34B-Python-v1-AWQ 

Phind CodeLlama 34B Python V1 AWQ Benchmarks

LLME Score: 0.13917
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 Python V1 AWQ (TheBloke/Phind-CodeLlama-34B-Python-v1-AWQ)

Phind CodeLlama 34B Python V1 AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
Programming
Primary Use Cases:
Code generation
Limitations:
Model has limited testing and may not be reliable for critical tasks
Considerations:
Should not use the Llama chat markup; rather use plain instructions ending with '\n'
Additional Notes 
Compatible with AWQ, vLLM, and AutoAWQ
Training Details 
Data Volume:
~80k high quality programming problems
Methodology:
Fine-tuning without LoRA using DeepSpeed ZeRO 3 and Flash Attention 2
Context Length:
4096
Training Time:
90 GPU-hours
Hardware Used:
32 A100-80GB GPUs
Model Architecture:
Native fine-tune of CodeLlama-34B and CodeLlama-34B-Python
Safety Evaluation 
Ethical Considerations:
This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
Input Output 
Input Format:
Plain text with newline ending
Accepted Modalities:
text
Output Format:
Text generation
Performance Tips:
Avoid using Llama chat markup; use plain instruction ending with '\n'
Release Notes 
Version:
1.0
Notes:
Initial release with 69.5% pass@1 on HumanEval
LLM NamePhind CodeLlama 34B Python V1 AWQ
Repository 🤗https://huggingface.co/TheBloke/Phind-CodeLlama-34B-Python-v1-AWQ 
Model CreatorPhind
Base Model(s)  Phind CodeLlama 34B Python V1   Phind/Phind-CodeLlama-34B-Python-v1
Model Size34b
Required VRAM18.3 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-2   8.4 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.33.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Phind CodeLlama 34B Python V1 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Phind CodeLlama 34B V2 AWQ16K / 18.3 GB18132
...echless Codellama 34B V2.0 AWQ16K / 18.3 GB246
...enbuddy Coder 34B V11 Bf16 AWQ16K / 18.5 GB321
CodeLlama 34B Instruct AWQ16K / 18.3 GB462
Synthia 34B V1.2 AWQ16K / 18.3 GB510
...izardCoder Python 34B V1.0 AWQ16K / 18.3 GB166
MAmmoTH Coder 34B AWQ16K / 18.3 GB211
CodeFuse CodeLlama 34B AWQ16K / 18.3 GB242
CodeLlama 34B AWQ16K / 18.3 GB232
CodeLlama 34B Python AWQ16K / 18.3 GB222
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Phind-CodeLlama-34B-Python-v1-AWQ.

Rank the Phind CodeLlama 34B Python V1 AWQ 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? 40066 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 v20241217
  Support LLM Explorer