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
OFFELLIA_QUANTIS_REAL_QUANTIZATION_CMD.txt Normal file
View File

@@ -0,0 +1,20 @@
#OFFELLIA QUANTIZAÇÃO ZetaHeicoidal real por meio direto "convert_hf_to_gguf.py" e "quants.py", sem uso de quantize.
python /home/userk21/llama.cpp/convert_hf_to_gguf.py /home/userk21/GGUFS/LFM2-24B-A2B/ --outtype q4_0 --outfile /home/userk21/GGUFS/OFFELLIA_LFM2-24B-A2B_Q4_0.gguf
python /home/userk21/llama.cpp/convert_hf_to_gguf.py /home/userk21/GGUFS/LFM2-24B-A2B/ --outtype q8_0 --outfile /home/userk21/GGUFS/OFFELLIA_LFM2-24B-A2B_Q8_0.gguf
./llama.cpp/build/bin/llama-perplexity -m /home/userk21/GGUFS/OFFELLIA_LFM2_8B_q8_0.gguf -f /home/userk21/GGUFS/wikitext-2-raw/wiki.test.raw 2>&1 | tee resultado_perplexity.txt
/home/userk21/llama.cpp/build/bin/llama-server \
-m /home/userk21/GGUFS/OFFELLIA_LFM2-8B-A1B_Q4_0.gguf