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

add qwen3.5 4b heretic

Browse Source
This commit is contained in:
Lumpiasty
2026-03-08 21:39:53 +01:00
parent e72a79be8f
commit 39fc38d62b
1 changed files with 21 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
apps/llama/configs/config.yaml
View File

@@ -9,6 +9,7 @@ macros:
qwen35_sampling: "--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00"
qwen35_35b_args: "--temp 1.0 --min-p 0.00 --top-p 0.95 --top-k 20"
qwen35_35b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf"
qwen35_4b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-4B-GGUF_mmproj-F16.gguf"
thinking_on: "--chat-template-kwargs '{\"enable_thinking\": true}'"
thinking_off: "--chat-template-kwargs '{\"enable_thinking\": false}'"
@@ -174,6 +175,26 @@ models:
${common_args}
${thinking_off}
"Qwen3.5-4B-heretic-GGUF:Q4_K_M":
ttl: 600
cmd: |
/app/llama-server
-hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
${qwen35_4b_heretic_mmproj}
${qwen35_sampling}
${common_args}
${thinking_on}
"Qwen3.5-4B-heretic-GGUF-nothink:Q4_K_M":
ttl: 600
cmd: |
/app/llama-server
-hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
${qwen35_4b_heretic_mmproj}
${qwen35_sampling}
${common_args}
${thinking_off}
"Qwen3.5-9B-GGUF:Q4_K_M":
ttl: 600
cmd: |