Lumpiasty/klaster
0
0
Fork 0
Code Issues Pull Requests 4 Packages Projects Releases Wiki Activity

Add mmproj-url for Qwen3.5-35B-A3B-heretic model

Browse Source
This commit is contained in:
Lumpiasty
2026-03-02 03:19:16 +01:00
parent 2bb23c4ed0
commit 78a81c5b72
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
apps/llama/configs/config.yaml
View File

@@ -497,11 +497,14 @@ models:
--port ${PORT} --port ${PORT}
--chat-template-kwargs "{\"enable_thinking\": false}" --chat-template-kwargs "{\"enable_thinking\": false}"
# The "heretic" version does not provide the mmproj
# so providing url to the one from the non-heretic version.
"Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M": "Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M":
ttl: 600 ttl: 600
cmd: | cmd: |
/app/llama-server /app/llama-server
-hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf
--ctx-size 16384 --ctx-size 16384
--temp 1.0 --temp 1.0
--min-p 0.00 --min-p 0.00
@@ -515,6 +518,7 @@ models:
cmd: | cmd: |
/app/llama-server /app/llama-server
-hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf
--ctx-size 16384 --ctx-size 16384
--temp 1.0 --temp 1.0
--min-p 0.00 --min-p 0.00