Brunobkr/OFFELLIA_Quantis
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Brunobkr/OFFELLIA_Quantis
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-11 10:11:17 +08:00
commit 86836ec189
71 changed files with 29901 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
CODIGO CORRETO.txt Normal file
View File

@@ -0,0 +1,20 @@
*funcional para quantizer Q8_0 e MXFP4_MOE
./llama-quantize /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-35B_MXFP4_MOE.gguf_f16.gguf /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-35B_MXFP4_MOE.gguf MXFP4_MOE
python /home/userk21/llama-pure/convert_hf_to_gguf.py /home/userk21/GGUFS/Qwen3.5-27B/ --outtype f32 --outfile /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-27B_f32.gguf
python /home/userk21/llama-pure/convert_hf_to_gguf.py /home/userk21/GGUFS/Qwen3.5-27B/ --outtype f16 --outfile /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-27B_f16.gguf
python /home/userk21/llama-pure/convert_hf_to_gguf.py /home/userk21/GGUFS/Qwen3.5-27B/ --outtype q8_0 --outfile /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-27B_q8_0.gguf
/home/userk21/llama-pure/build/bin/llama-server \
-m /home/userk21/GGUFS/ΩFFΣLLIαHLX_Qwen3.5-35B_MXFP4_MOE.gguf
--ignore-eos \
--temp 0.8 \
--repeat-penalty 1.15 \