michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add dedicated Hermes compression model

Browse Source
This commit is contained in:
Mikei386
2026-08-26 00:45:32 +02:00
parent e872829b11
commit 43d9903d13
8 changed files with 120 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/install.env.example
+5
View File
@@ -72,6 +72,11 @@ EXPERIMENTAL_MODEL_SHA256=40fac4050e940397dbf13087afd50f4734a11805bf9d65ef8ddd74
VISION_PROJECTOR_FILE=qwen/mmproj-BF16.gguf
VISION_PROJECTOR_URL=https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/mmproj-BF16.gguf
VISION_PROJECTOR_SHA256=83ee4f4f205fa514161778c41df1ea14144faa0f713510893b63c2395f5c2d53
COMPRESSION_MODEL_FILE=qwen3.5-2b-compression/Qwen_Qwen3.5-2B-Q4_K_M.gguf
COMPRESSION_MODEL_URL=https://huggingface.co/bartowski/Qwen_Qwen3.5-2B-GGUF/resolve/main/Qwen_Qwen3.5-2B-Q4_K_M.gguf
COMPRESSION_MODEL_SHA256=57a1085840f497d764a7fc5d346922dbde961efb54cc792ea81d694fd846a1d8
COMPRESSION_CONTEXT=65536
COMPRESSION_GPU_DEVICE=GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
# All standard profiles use the MTP tensor embedded in their GGUF. A separate
# draft-model artifact is neither downloaded nor passed to llama-server.