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

CodeLlama 34B Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 34B Fp16   URL Share it on

  13   
  Codegen   Codellama   Custom code   Endpoints compatible   Fp16   Llama   Llama2   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-34B-fp16 

CodeLlama 34B Fp16 Benchmarks

ARC: 54.18 vs 96.7 (so35)-44%
HellaSwag: 75.82 vs 95.3 (gpt4)-20.4%
MMLU: 54.92 vs 88.3 (so35)-37.8%
TruthfulQA: 39.11 vs 59 (gpt4)-33.7%
WinoGrande: 73.32 vs 87.5 (gpt4)-16.2%
GSM8K: 34.34 vs 96.4 (so35)-64.4%
HumanEvalA: 33.89
Python Eva: 45.11 vs 92 (so35)-51%
Java Eval: 40.19
Javascript: 41.66
CPP Eval: 41.42
PHP Eval: 40.43
Julia Eval: 31.4
D Eval: 15.27
Lua Eval: 37.49
R Eval: 22.71
Racket Eva: 16.94
Rust Eval: 38.73
Swift Eval: 35.28
LLME Score: 0.12625
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 34B Fp16 (TheBloke/CodeLlama-34B-fp16)
🌟 Advertise your project 🚀

CodeLlama 34B Fp16 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Applications:
code synthesis, understanding tasks, Python programming, code assistant
Primary Use Cases:
code synthesis and understanding tasks, handle the Python programming language
Limitations:
Use in any manner that violates applicable laws or regulations, Use in languages other than English
Considerations:
Developers should perform safety testing and tuning tailored to specific applications.
Supported Languages 
English (proficient)
Training Details 
Data Sources:
same data as Llama 2 with different weights
Context Length:
100000
Hardware Used:
A100-80GB (TDP of 350-400W)
Model Architecture:
autoregressive language models using optimized transformer architectures
Safety Evaluation 
Ethical Considerations:
Testing conducted to date has been in English and has not covered all scenarios. Outputs cannot be predicted in advance and may be inaccurate or objectionable.
Input Output 
Input Format:
text only
Accepted Modalities:
text
Output Format:
text only
Performance Tips:
Load the FP16 models with `trust_remote_code=True` for correct results.
LLM NameCodeLlama 34B Fp16
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-34B-fp16 
Base Model(s)  CodeLlama 34B Hf   NousResearch/CodeLlama-34b-hf
Model Size34b
Required VRAM67.5 GB
Updated2025-12-14
MaintainerTheBloke
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
Quantization Typefp16
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to CodeLlama 34B Fp16

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Instruct Fp1616K / 67.5 GB28196
CodeLlama 34B Python Fp1616K / 67.5 GB185913
Codellama Extraction16K / 67.6 GB50
Phind Codellama 34B V2 EXL216K /  GB216
Codellama 34B Bnb 4bit16K / 18.2 GB10874
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB682
XwinCoder 34B 4.0bpw H6 EXL216K / 17.4 GB61
...Codellama 34B V2 Megacode EXL216K /  GB810
...gpt 32K Codellama 34B Instruct32K / 67.5 GB842
CodeLlama 34B Instruct Hf16K / 67.5 GB34894299
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-34B-fp16.

Rank the CodeLlama 34B Fp16 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? 51598 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 v20241124
  Support LLM Explorer