Arxiv:2308.12950 4-bit Autotrain compatible Base model:codellama/codellama... Base model:quantized:codellama... Code Codegen Gptq Llama Llama2 Quantized Region:us Safetensors
CodeLlama 70B Hf GPTQ Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
CodeLlama 70B Hf GPTQ Parameters and Internals
| LLM Name | CodeLlama 70B Hf GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/CodeLlama-70B-hf-GPTQ |
| Model Name | CodeLlama 70B |
| Model Creator | Code Llama |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 35.3 GB |
| Updated | 2024-09-16 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| Supported Languages | code |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32016 |
| Torch Data Type | bfloat16 |
Best Alternatives to CodeLlama 70B Hf GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeLlama 70B Python GPTQ | 4K / 35.3 GB | 69 | 18 |
| CodeLlama 70B Instruct GPTQ | 4K / 35.3 GB | 72 | 11 |
| ...rpreter CL 70B 4.65bpw H6 EXL2 | 16K / 40.6 GB | 22 | 1 |
| CodeLlama 70B Hf 4bit MLX | 16K / 39.1 GB | 5 | 12 |
| ...odeLlama 70B Hf 2.4bpw H6 EXL2 | 16K / 21.3 GB | 37 | 1 |
| ...odeLlama 70B Hf 4.0bpw H6 EXL2 | 16K / 35 GB | 34 | 1 |
| CodeLLaMA 70B Hf Fp16 | 16K / 138.7 GB | 16 | 2 |
| ...70B Instruct Nf4 Fp16 Upscaled | 4K / 138.7 GB | 244 | 2 |
| ...Llama 70B Instruct Hf 4bit MLX | 4K / 39.1 GB | 4 | 25 |
| ...deLlama 70B Python Hf 4bit MLX | 4K / 39.1 GB | 3 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-70B-hf-GPTQ .
Rank the CodeLlama 70B Hf GPTQ 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! 🌟
What open-source LLMs or SLMs are you in search of? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803