LLM Name | CT LLM SFT |
Repository ๐ค | https://huggingface.co/m-a-p/CT-LLM-SFT |
Model Size | 2.1b |
Required VRAM | 0 GB |
Updated | 2024-10-18 |
Maintainer | m-a-p |
Model Type | llama |
Model Files | |
Model Architecture | LlamaForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.2 |
Tokenizer Class | BaichuanTokenizer |
Padding Token | <unk> |
Vocabulary Size | 125824 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi 3 Orpo V9.4 | 4K / 2.3 GB | 8 | 1 |
CT LLM Base | 4K / 4.3 GB | 73 | 10 |
CT LLM SFT DPO | 4K / 0 GB | 14 | 5 |
Phi 3.5 Mini Instruct Bnb 4bit | 128K / 2.3 GB | 81499 | 9 |
...penbuddy Llama2 13b64k V15 AWQ | 64K / 7.4 GB | 8 | 1 |
...enbuddy Llama2 13b64k V15 GPTQ | 64K / 7.4 GB | 13 | 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