CodeLlama 70B Instruct GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  CodeLlama 70B Instruct GPTQ   URL Share it on

  Arxiv:2308.12950   4-bit   Autotrain compatible Base model:codellama/codellama... Base model:quantized:codellama...   Code   Codegen   Conversational   Gptq   Instruct   Llama   Llama2   Quantized   Region:us   Safetensors

CodeLlama 70B Instruct GPTQ Benchmarks

nn.n% โ€” How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sponsored by Nebius

CodeLlama 70B Instruct GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
commercial, research
Applications:
code synthesis, code understanding
Primary Use Cases:
code assistant, code generation
Limitations:
Use in languages other than English
Additional Notes 
Code Llama models are pretrained and fine-tuned text models ranging from 7B to 70B parameters, designed for code synthesis and understanding.
Training Details 
Context Length:
16000
Hardware Used:
A100-80GB
Model Architecture:
auto-regressive transformer architecture
Input Output 
Input Format:
text only
Accepted Modalities:
text
Output Format:
text only
LLM NameCodeLlama 70B Instruct GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GPTQ 
Model NameCodellama 70B Instruct
Model CreatorCode Llama
Base Model(s)  CodeLlama 70B Instruct Hf   codellama/CodeLlama-70b-Instruct-hf
Model Size70b
Required VRAM35.3โ€ฏGB
Updated2025-01-04
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  35.3 GB
Supported Languagescode
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 70B Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...70B Instruct Nf4 Fp16 Upscaled4K / 138.7โ€‰GB3252
...Llama 70B Instruct Hf 4bit MLX4K / 39.1โ€‰GB2125
...70B Instruct Hf 5.0bpw H6 EXL22K / 43.6โ€‰GB116
...70B Instruct Hf 2.4bpw H6 EXL22K / 21.3โ€‰GB161
...0B Instruct Hf 2.65bpw H6 EXL22K / 23.4โ€‰GB133
...70B Instruct Hf 4.0bpw H6 EXL22K / 35.1โ€‰GB161
CodeLlama 70B Instruct Hf4K / 72.3โ€‰GB4025204
Code Llama 70B Python Instruct4K / 138.1โ€‰GB851
CodeLlama 70B Instruct Hf4K / 72.3โ€‰GB17516
CodeLlama 70B Instruct Neuron4K / โ€‰GB3391
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-70B-Instruct-GPTQ.

Rank the CodeLlama 70B Instruct GPTQ 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  
โ—โ—โ—โ—
Factuality and Completeness of Knowledge  
โ—โ—โ—โ—
Censorship and Alignment  
โ—โ—โ—โ—
Data Analysis and Insight Generation  
โ—โ—โ—โ—
Text Generation  
โ—โ—โ—โ—
Text Summarization and Feature Extraction  
โ—โ—โ—โ—
Code Generation  
โ—โ—โ—โ—
Multi-Language Support and Translation  
โ—โ—โ—โ—

What open-source LLMs or SLMs are you in search of? 40868 in total.

Our Social Media โ†’  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227