LLM Name | Llava 1.6 Gptq 8bit |
Repository ๐ค | https://huggingface.co/panoyo9829/llava-1.6-gptq-8bit |
Model Size | 7b |
Required VRAM | 9.6 GB |
Updated | 2024-12-26 |
Maintainer | panoyo9829 |
Model Type | llava |
Instruction-Based | Yes |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|8bit |
Model Architecture | LlavaLlamaForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Llava V1.6 Mistral 7B PATCHED | 32K / 15.1 GB | 23 | 8 |
Table Llava V1.5 7B | 4K / 14.2 GB | 168 | 11 |
Quilt Llava V1.5 7B | 4K / 14.2 GB | 461 | 4 |
Co Instruct Llava V1.5 7B | 4K / 14.1 GB | 15 | 1 |
...V1.5 7b Qinstruct Preview V0.1 | 4K / 14.2 GB | 513 | 4 |
...ct4V LLaVA Instruct Mix880k 7B | 4K / 14.2 GB | 15 | 3 |
Chinese LLaVA Baichuan | 2K / 28 GB | 23 | 8 |
KoLLaVA KoVicuna 7B | 2K / 27 GB | 189 | 12 |
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