Llava-v1.5-7B-GGUF

Original Model

liuhaotian/llava-v1.5-7b

Run with LlamaEdge

  • LlamaEdge version: comming soon

  • Prompt template

    • Prompt type: vicuna-llava

    • Prompt string

      <system_prompt>\nUSER:<image_embeddings>\n<textual_prompt>\nASSISTANT:
      
  • Context size: 4096

  • Run as LlamaEdge service

    wasmedge --dir .:. \
      --nn-preload default:GGML:AUTO:llava-v1.5-7b-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template vicuna-llava \
      --ctx-size 4096 \
      --llava-mmproj llava-v1.5-7b-mmproj-model-f16.gguf \
      --model-name llava-v1.5
    

Quantized GGUF Models

Name Quant method Bits Size Use case
llava-v1.5-7b-Q2_K.gguf Q2_K 2 2.53 GB smallest, significant quality loss - not recommended for most purposes
llava-v1.5-7b-Q3_K_L.gguf Q3_K_L 3 3.6 GB small, substantial quality loss
llava-v1.5-7b-Q3_K_M.gguf Q3_K_M 3 3.3 GB very small, high quality loss
llava-v1.5-7b-Q3_K_S.gguf Q3_K_S 3 2.95 GB very small, high quality loss
llava-v1.5-7b-Q4_0.gguf Q4_0 4 3.83 GB legacy; small, very high quality loss - prefer using Q3_K_M
llava-v1.5-7b-Q4_K_M.gguf Q4_K_M 4 4.08 GB medium, balanced quality - recommended
llava-v1.5-7b-Q4_K_S.gguf Q4_K_S 4 3.86 GB small, greater quality loss
llava-v1.5-7b-Q5_0.gguf Q5_0 5 4.65 GB legacy; medium, balanced quality - prefer using Q4_K_M
llava-v1.5-7b-Q5_K_M.gguf Q5_K_M 5 4.78 GB large, very low quality loss - recommended
llava-v1.5-7b-Q5_K_S.gguf Q5_K_S 5 4.65 GB large, low quality loss - recommended
llava-v1.5-7b-Q6_K.gguf Q6_K 6 5.53 GB very large, extremely low quality loss
llava-v1.5-7b-Q8_0.gguf Q8_0 8 7.16 GB very large, extremely low quality loss - not recommended
llava-v1.5-7b-mmproj-model-f16.gguf f16 8 624 MB

Quantized with llama.cpp b2230

Downloads last month
13,764
GGUF
Model size
6.74B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for second-state/Llava-v1.5-7B-GGUF

Quantized
(2)
this model