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
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...th Deepseek FULL ArithHard 30K | — | 16K / 0 GB | 9 | 0 |
...pseek Coder 1.3B Instruct AQLM | — | 16K / 0.7 GB | 15 | 0 |
Deepseek Coder 1.3B Instruct | — | 16K / 2.7 GB | 15940 | 86 |
Pip Code Bandit | — | 16K / 2.7 GB | 22 | 12 |
Datascience Coder 1.3B | — | 16K / 2.7 GB | 4 | 1 |
Speechless Coder Ds 1.3B | — | 16K / 2.7 GB | 1534 | 0 |
...t Structured Output Peft Merge | — | 16K / 2.7 GB | 5 | 0 |
Pip Sql 1.3B | — | 16K / 5.4 GB | 1352 | 74 |
Pip Library Etl 1.3B | — | 16K / 5.4 GB | 616 | 39 |
Pip Api Expert | — | 16K / 5.4 GB | 22 | 3 |
LLM Name | AIFT Instruct SFT 1.3B V2.1 |
Repository | Open on ๐ค |
Model Size | 1.3b |
Required VRAM | 2.9 GB |
Updated | 2024-07-01 |
Maintainer | AIFT |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | cc-by-sa-4.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.2 |
Tokenizer Class | GPT2TokenizerFast |
Padding Token | <||pad||> |
Vocabulary Size | 50304 |
Initializer Range | 0.01 |
Torch Data Type | float16 |
Errors | replace |