GGUF
ehartford commited on
Commit
d74a9d2
·
verified ·
1 Parent(s): 9960bf8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  ---
4
 
 
 
5
  # Devstral-Vision-Small-2507 GGUF
6
 
7
  Quantized GGUF versions of [cognitivecomputations/Devstral-Vision-Small-2507](https://huggingface.co/cognitivecomputations/Devstral-Vision-Small-2507) - the multimodal coding specialist that combines Devstral's exceptional coding abilities with vision understanding.
@@ -44,6 +46,9 @@ This is the first vision-enabled version of Devstral, created by transplanting D
44
  huggingface-cli download cognitivecomputations/Devstral-Vision-Small-2507-GGUF \
45
  Devstral-Small-Vision-2507-Q4_K_M.gguf \
46
  --local-dir .
 
 
 
47
 
48
  # Run with llama.cpp
49
  ./llama-cli -m Devstral-Small-Vision-2507-Q4_K_M.gguf \
 
2
  license: apache-2.0
3
  ---
4
 
5
+ NEW - I exported and added mmproj-BF16.gguf to properly support llama.cpp, ollama, and LM Studio.
6
+
7
  # Devstral-Vision-Small-2507 GGUF
8
 
9
  Quantized GGUF versions of [cognitivecomputations/Devstral-Vision-Small-2507](https://huggingface.co/cognitivecomputations/Devstral-Vision-Small-2507) - the multimodal coding specialist that combines Devstral's exceptional coding abilities with vision understanding.
 
46
  huggingface-cli download cognitivecomputations/Devstral-Vision-Small-2507-GGUF \
47
  Devstral-Small-Vision-2507-Q4_K_M.gguf \
48
  --local-dir .
49
+ huggingface-cli download cognitivecomputations/Devstral-Vision-Small-2507-GGUF \
50
+ mmproj-BF16.gguf \
51
+ --local-dir .
52
 
53
  # Run with llama.cpp
54
  ./llama-cli -m Devstral-Small-Vision-2507-Q4_K_M.gguf \