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

mtmd : support InternVL 2.5 and 3 (#13422)

Browse source 
* convert : internvl support

* InternVL3-1B working

* fix regression

* rm mobilevlm from test

* fix conversion

* add test for internvl

* add to list of pre-quant

* restore boi/eoi check

* add clarify comment for norm eps
This commit is contained in:
Xuan-Son Nguyen 2025-05-10 16:26:42 +02:00 • committed by GitHub
parent d8919424f1
commit 053367d149
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 243 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tools/mtmd/tests.sh
View file

@ -40,7 +40,6 @@ 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"
add_test "llama-mtmd-cli" "ggml-org/gemma-3-4b-it-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "guinmoon/MobileVLM-3B-GGUF:Q4_K_M" "deepseek"
add_test "llama-mtmd-cli" "THUDM/glm-edge-v-5b-gguf:Q4_K_M"
add_test "llama-mtmd-cli" "second-state/Llava-v1.5-7B-GGUF:Q2_K" "vicuna"
add_test "llama-mtmd-cli" "cjpais/llava-1.6-mistral-7b-gguf:Q3_K" "vicuna"
@ -50,6 +49,8 @@ add_test "llama-mtmd-cli" "openbmb/MiniCPM-V-2_6-gguf:Q2_K"
add_test "llama-mtmd-cli" "openbmb/MiniCPM-o-2_6-gguf:Q4_0"
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"
add_test "llama-mtmd-cli" "ggml-org/InternVL2_5-1B-GGUF:Q8_0"
add_test "llama-mtmd-cli" "ggml-org/InternVL3-1B-Instruct-GGUF:Q8_0"
# to test the big models, run: ./tests.sh big
if [ "$RUN_BIG_TESTS" = true ]; then
@ -59,6 +60,8 @@ if [ "$RUN_BIG_TESTS" = true ]; then
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/InternVL3-8B-Instruct-GGUF:Q4_K_M"
add_test "llama-mtmd-cli" "ggml-org/InternVL3-14B-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
@ -70,6 +73,7 @@ fi
# this model has broken chat template, not usable
# add_test "llama-mtmd-cli" "cmp-nct/Yi-VL-6B-GGUF:Q5_K"
# add_test "llama-mtmd-cli" "guinmoon/MobileVLM-3B-GGUF:Q4_K_M" "deepseek"
###############