kvcache-ai/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-03-14 18:37:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove unsupprted paramters, add force think

Browse Source
This commit is contained in:
SkqLiao
2025-03-15 17:04:42 +08:00
parent 4e23a4c024
commit a1891b845d
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/install.yml vendored
View File

@@ -62,7 +62,7 @@ jobs:
export CUDA_HOME=/usr/local/cuda-12.4
cd ${{ github.workspace }}
echo "Running Local Chat 1...(book.txt)"
python ktransformers/local_chat_test.py --model_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/config --gguf_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/ --max_new_tokens 256 --cache_len 1536 --cpu_infer 64 --prompt_file /home/qujing3/prompts/book.txt
python ktransformers/local_chat_test.py --model_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/config --gguf_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/ --max_new_tokens 256 --cpu_infer 64 --prompt_file /home/qujing3/prompts/book.txt
- name: Test Local Chat 2
run: |
set -e
@@ -72,7 +72,7 @@ jobs:
export LD_LIBRARY_PATH=/usr/local/cuda-12.4/lib64:$LD_LIBRARY_PATH
export CUDA_HOME=/usr/local/cuda-12.4
cd ${{ github.workspace }}
echo "Running Local Chat 2...(chinese.txt)"
python ktransformers/local_chat_test.py --model_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/config --gguf_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/ --max_new_tokens 256 --cache_len 1536 --cpu_infer 64 --prompt_file /home/qujing3/prompts/chinese.txt
echo "Running Local Chat 2 [force think]...(chinese.txt)"
python ktransformers/local_chat_test.py --model_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/config --gguf_path /home/qujing3/models/DeepSeek-R1-Q4_K_M/ --max_new_tokens 256 --cpu_infer 64 --prompt_file /home/qujing3/prompts/chinese.txt -f
- run: echo "This job's status is ${{ job.status }}."