LLM Name | CodeFuse DeepSeek 33B 4bits |
Repository 🤗 | https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B-4bits |
Base Model(s) | |
Model Size | 33b |
Required VRAM | 18.7 GB |
Updated | 2024-09-07 |
Maintainer | codefuse-ai |
Model Type | llama |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.33.2 |
Tokenizer Class | LlamaTokenizerFast |
Beginning of Sentence Token | <|begin▁of▁sentence|> |
End of Sentence Token | <|end▁of▁sentence|> |
Padding Token | <|end▁of▁sentence|> |
Vocabulary Size | 32256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Everyone Coder 33B Base GPTQ | 16K / 17.4 GB | 16 | 2 |
...epseek Coder 33B Instruct GPTQ | 16K / 17.4 GB | 64 | 26 |
Deepseek Coder 33B Base GPTQ | 16K / 17.4 GB | 15 | 2 |
Vicuna 33B Coder GPTQ | 2K / 16.9 GB | 14 | 1 |
...erpreter DS 33B 8.0bpw H8 EXL2 | 16K / 33.5 GB | 14 | 2 |
...erpreter DS 33B 4.0bpw H6 EXL2 | 16K / 17.1 GB | 5 | 4 |
...rpreter DS 33B 4.65bpw H6 EXL2 | 16K / 19.8 GB | 5 | 2 |
...erpreter DS 33B 5.0bpw H6 EXL2 | 16K / 21.2 GB | 4 | 1 |
...erpreter DS 33B 6.0bpw H6 EXL2 | 16K / 25.3 GB | 4 | 1 |
...der 33B V2 Base 8.0bpw H8 EXL2 | 16K / 33.5 GB | 4 | 1 |
🆘 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! 🌟