LLM Name | Llava Llama 2 13B Chat Lightning Gptq |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 13b |
Required VRAM | 7.3 GB |
Updated | 2024-07-27 |
Maintainer | liuhaotian |
Model Type | llama |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | LlavaLlamaForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.31.0 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Llava V1.5 13B EXL2 | 0.2 | 4K / 13.2 GB | 12 | 1 |
Llava V1.5 13B 4GB 8bit | 0.2 | 4K / 14.1 GB | 13 | 2 |
Llava 13B V1.1 4bit 128g | 0.1 | 2K / 7.5 GB | 31 | 2 |
Llava V1.5 13B | 0.3 | 4K / 26 GB | 193188 | 443 |
Llava V1.6 Vicuna 13B | 0.3 | 4K / 26.7 GB | 37962 | 43 |
Evalalign V1.0 13B | 0.3 | 4K / 26.7 GB | 260 | 1 |
Table Llava V1.5 13B | 0.3 | 4K / 26.6 GB | 64 | 0 |
Peenoblanc 52 Llava | 0.2 | 4K / 26.7 GB | 7 | 0 |
Otterchecker | 0.2 | 4K / 26.7 GB | 8 | 2 |
Llava 13B Custom | 0.2 | 4K / 26.7 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