Model Type |
| |||||||||
Use Cases |
| |||||||||
Additional Notes |
| |||||||||
Training Details |
| |||||||||
Input Output |
|
LLM Name | CodeLlama 70B Hf GPTQ |
Repository π€ | 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 | 2024-12-22 |
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 |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
CodeLlama 70B Python GPTQ | 4K / 35.3 GB | 43 | 18 |
CodeLlama 70B Instruct GPTQ | 4K / 35.3 GB | 31 | 12 |
...rpreter CL 70B 4.65bpw H6 EXL2 | 16K / 40.6 GB | 7 | 1 |
CodeLlama 70B Hf 4bit MLX | 16K / 39.1 GB | 15 | 12 |
CodeLLaMA 70B Hf Fp16 | 16K / 138.7 GB | 14 | 2 |
...odeLlama 70B Hf 4.0bpw H6 EXL2 | 16K / 35 GB | 11 | 1 |
...odeLlama 70B Hf 2.4bpw H6 EXL2 | 16K / 21.3 GB | 9 | 1 |
...70B Instruct Nf4 Fp16 Upscaled | 4K / 138.7 GB | 409 | 2 |
...Llama 70B Instruct Hf 4bit MLX | 4K / 39.1 GB | 23 | 25 |
...deLlama 70B Python Hf 4bit MLX | 4K / 39.1 GB | 11 | 11 |
π 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! π