LLM Name | Ntp Mathlib St Deepseek Coder 1.3B |
Repository ๐ค | https://huggingface.co/l3lab/ntp-mathlib-st-deepseek-coder-1.3b |
Model Size | 1.3b |
Required VRAM | 2.7 GB |
Updated | 2024-09-16 |
Maintainer | l3lab |
Model Type | llama |
Model Files | |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
License | mit |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.38.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <pad> |
Vocabulary Size | 32256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Deepseek Coder 1.3B Instruct | 16K / 2.7 GB | 24068 | 96 |
Llm4decompile 1.3B V2 | 16K / 2.7 GB | 303 | 4 |
Speechless Coder Ds 1.3B | 16K / 2.7 GB | 686 | 0 |
Deepseek Coder 1.3B Base | 16K / 2.7 GB | 21203 | 60 |
Deepseek Coder 1.3B Chat | 16K / 2.7 GB | 85 | 1 |
...1.3B Chat And Function Calling | 16K / 2.7 GB | 65 | 0 |
Deepseek Coder 1.3B Kexer | 16K / 2.7 GB | 147 | 1 |
Ds Full Ctxt16K V0 | 16K / 2.7 GB | 5 | 0 |
Llm4decompile 1.3B V1.5 | 16K / 2.7 GB | 33 | 2 |
... 1.3B Instruct Trt Int4 G64 Hf | 16K / 0.9 GB | 5 | 0 |
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