wehub/modelscope--ms-swift
1
0
Fork 0
Code Issues Pull Requests Actions 1 Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution
Lint test / lint (push) Has been cancelled
Details

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:34:58 +08:00
commit a203934033
1368 changed files with 175001 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/export/quantize/reward_model/bnb.sh
+12
View File
@@ -0,0 +1,12 @@
# bnb quantize
CUDA_VISIBLE_DEVICES=0 swift export \
--model Shanghai_AI_Laboratory/internlm2-1_8b-reward \
--output_dir output/internlm2-1_8b-reward-bnb-int4 \
--quant_bits 4 \
--quant_method bnb
# infer
CUDA_VISIBLE_DEVICES=0 swift infer \
--model output/internlm2-1_8b-reward-bnb-int4 \
--val_dataset 'AI-ModelScope/alpaca-gpt4-data-zh#1000' \
--max_batch_size 16
examples/export/quantize/reward_model/gptq.sh
+14
View File
@@ -0,0 +1,14 @@
# gptq quantize
CUDA_VISIBLE_DEVICES=0 swift export \
--model Shanghai_AI_Laboratory/internlm2-1_8b-reward \
--output_dir output/internlm2-1_8b-reward-gptq-int4 \
--quant_bits 4 \
--max_length 2048 \
--quant_method gptq \
--dataset 'AI-ModelScope/alpaca-gpt4-data-zh#1000' 'AI-ModelScope/alpaca-gpt4-data-en#1000'
# infer
CUDA_VISIBLE_DEVICES=0 swift infer \
--model output/internlm2-1_8b-reward-gptq-int4 \
--val_dataset 'AI-ModelScope/alpaca-gpt4-data-zh#1000' \
--max_batch_size 16