LLM Name | CodeLlama 34B Python Fp16 |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 34b |
Required VRAM | 67.5 GB |
Updated | 2024-07-27 |
Maintainer | TheBloke |
Model Type | llama |
Model Files | |
Quantization Type | fp16 |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.32.0 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Codellama Extraction | 0.2 | 16K / 67.6 GB | 7 | 0 |
Codellama 34B Bnb 4bit | 0.2 | 16K / 18.2 GB | 1451 | 2 |
CodeLlama 34B Instruct Fp16 | 0.2 | 16K / 67.5 GB | 1902 | 7 |
Phind Codellama 34B V2 EXL2 | 0.2 | 16K / GB | 9 | 16 |
CodeLlama 34B Fp16 | 0.2 | 16K / 67.5 GB | 19 | 4 |
XwinCoder 34B 4.0bpw H6 EXL2 | 0.2 | 16K / 17.4 GB | 7 | 1 |
...Codellama 34B V2 Megacode EXL2 | 0.2 | 16K / GB | 9 | 10 |
...gpt 32K Codellama 34B Instruct | 0.2 | 32K / 67.5 GB | 2833 | 2 |
CodeLlama 34B Instruct Hf | 0.4 | 16K / 67.5 GB | 28184 | 272 |
Phind CodeLlama 34B V2 | 0.3 | 16K / 67.5 GB | 20706 | 809 |
๐ 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! ๐