LLM Name | Llama 2 Ko 7B Chat Vicuna Hf 4bit |
Repository ๐ค | https://huggingface.co/quantumaikr/llama-2-ko-7b-chat-vicuna-hf-4bit |
Model Size | 7b |
Required VRAM | 0.1 GB |
Updated | 2024-09-07 |
Maintainer | quantumaikr |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Adapter |
Is Biased | none |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | q_proj|v_proj |
LoRA Alpha | 8 |
LoRA Dropout | 0.1 |
R Param | 32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Atomgpt Mistral Tc Supercon | 0K / 0.2 GB | 191 | 2 |
...Generator For Emotion Chat Bot | 0K / 1.6 GB | 196 | 0 |
...hat Hf Hotel Booking Assistant | 0K / 0.2 GB | 35 | 0 |
Mistral Numericnlg FV | 0K / 0.3 GB | 5 | 0 |
Mistral Wikitable FV | 0K / 0.3 GB | 6 | 0 |
Mistral Charttotext FV | 0K / 0.3 GB | 6 | 0 |
Gemma 7B Us Minecraft | 0K / 0 GB | 25 | 0 |
Gemma7b SFT | 0K / 0 GB | 24 | 0 |
RP Format Test | 0K / 0.7 GB | 2 | 4 |
Synthetic Soul 1k Mistral 128 | 0K / 1.3 GB | 7 | 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