LLM Name | Llama 3 8B Chat Doctor |
Repository ๐ค | https://huggingface.co/Horizon6957/llama-3-8b-chat-doctor |
Model Size | 8b |
Required VRAM | 2.3 GB |
Updated | 2024-08-01 |
Maintainer | Horizon6957 |
Model Type | llama |
Model Files | |
Model Architecture | AutoModel |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.42.3 |
Is Biased | none |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|im_end|> |
Vocabulary Size | 128258 |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | up_proj|q_proj|o_proj|v_proj|down_proj|gate_proj|k_proj |
LoRA Alpha | 32 |
LoRA Dropout | 0.05 |
R Param | 16 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...3 Sqlcoder 8B Ct2 Int8 Float16 | 0K / 8 GB | 334 | 0 |
... Instruct Abliteration LoRA 8B | 0K / 0.2 GB | 0 | 5 |
...IProfessions Doctor Llama 3 8B | 0K / 2.3 GB | 5 | 0 |
Llama3 8B Hikikomori V0.4 | 0K / 0.2 GB | 0 | 1 |
Llama 3 8B Instruct Checkit | 0K / 0.2 GB | 0 | 1 |
...terative DPO LLaMA 3 8B R Lora | 0K / 0.2 GB | 0 | 2 |
...LX 8B Chat Alpha1 Law Finetune | 0K / 0.2 GB | 0 | 2 |
Llama3 ChatQA 1.5 8B Lora | 0K / 0.7 GB | 0 | 4 |
...3 8B Instruct Ct2 Int8 Float16 | 0K / 8 GB | 25 | 0 |
BioMed Tuned Llama 3 8B | 0K / 0.1 GB | 0 | 7 |
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