ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)

Browse source 
* wip

* qwen2.5vl ok

* vision: fix models missing "text_config"

* add test

* fix test repo name

* fix 32B model

* Revert "fix 32B model"

This reverts commit 651752f1ae25fe8a01c1e57c18cf2eca80b2774e.

* clarify about 32B

* rm qwen surgery script

* update llava/readme

* move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel
This commit is contained in:
Xuan-Son Nguyen 2025-05-02 17:17:15 +02:00 • committed by GitHub
parent c642bc014c
commit 074e42ab31
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 132 additions and 233 deletions
Download patch file Download diff file Expand all files Collapse all files

18
examples/llava/tests.sh
View file

@ -36,12 +36,6 @@ add_test() {
arr_tmpl+=("$tmpl")
}
add_test_big() {
if [ "$RUN_BIG_TESTS" = true ]; then
add_test "$@"
fi
}
add_test "llama-mtmd-cli" "ggml-org/SmolVLM-500M-Instruct-GGUF:Q8_0"
add_test "llama-mtmd-cli" "ggml-org/SmolVLM2-2.2B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/SmolVLM2-500M-Video-Instruct-GGUF:Q8_0"
@ -58,8 +52,16 @@ add_test "llama-mtmd-cli" "bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/Qwen2.5-VL-3B-Instruct-GGUF:Q4_K_M"
# to test the big models, run: ./tests.sh big
add_test_big "llama-mtmd-cli" "ggml-org/pixtral-12b-GGUF:Q4_K_M"
add_test_big "llama-mtmd-cli" "ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF" "mistral-v7"
if [ "$RUN_BIG_TESTS" = true ]; then
add_test "llama-mtmd-cli" "ggml-org/pixtral-12b-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF" "mistral-v7"
add_test "llama-mtmd-cli" "ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/Qwen2-VL-7B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/Qwen2.5-VL-3B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/Qwen2.5-VL-7B-Instruct-GGUF:Q4_K_M"
# add_test "llama-mtmd-cli" "ggml-org/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M" # does not work on my mac M3 Ultra
# add_test "llama-mtmd-cli" "ggml-org/Qwen2.5-VL-72B-Instruct-GGUF:Q4_K_M" # too big
fi
# these models always give the wrong answer, not sure why
# add_test "llama-mtmd-cli" "ggml-org/SmolVLM-Instruct-GGUF:Q4_K_M"