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

mtmd : support SmolVLM (version 1 and 2) (#13050)

Browse source 
* mtmd : support SmolVLM (version 1 and 2)

* correct chat template

* fix n_patches

* scale_factor is an int

* add more models to test
This commit is contained in:
Xuan-Son Nguyen 2025-04-22 16:24:54 +02:00 • committed by GitHub
parent ab47dec3d3
commit dc39a5e7a8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 279 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/llava/tests.sh
View file

@ -28,6 +28,9 @@ add_test() {
arr_tmpl+=("$tmpl")
}
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"
@ -39,7 +42,13 @@ 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-qwen2vl-cli" "bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M"
# add_test "llama-mtmd-cli" "cmp-nct/Yi-VL-6B-GGUF:Q5_K" # this model has broken chat template, not usable
# these models always give the wrong answer, not sure why
# add_test "llama-mtmd-cli" "ggml-org/SmolVLM-Instruct-GGUF:Q4_K_M"
# add_test "llama-mtmd-cli" "ggml-org/SmolVLM-256M-Instruct-GGUF:Q8_0"
# add_test "llama-mtmd-cli" "ggml-org/SmolVLM2-256M-Video-Instruct-GGUF:Q8_0"
# this model has broken chat template, not usable
# add_test "llama-mtmd-cli" "cmp-nct/Yi-VL-6B-GGUF:Q5_K"
###############