cunliangkong

cunliangkong pushed to main at cunliangkong/models-deploy

2026-03-21 17:04:46 +08:00

bd67fc088f change to sglang

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-21 01:06:12 +08:00

833f6027b1 [fix] fit neat_packing & mrope model packing (#10283)

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-20 16:46:12 +08:00

d91d8af89e [data] add SGSC zero-hallucination B2B dataset (NOO-Protocol) (#10284)

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-18 22:56:12 +08:00

e67ab9e2f2 fix:MiniCPMVPlugin IndexError in process_messages when training with video (#10276)

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-18 14:36:11 +08:00

2c4f121817 [fix] handle empty content list in system message (#10291)

487f8b8191 [v1] add qwen3 templates and fix rendering plugin. (#10212)

Compare 2 commits »

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-18 06:26:11 +08:00

78cad1e332 [fix] unused keys in ray example (#10290)

cunliangkong pushed to main at cunliangkong/models-deploy

2026-03-17 21:05:25 +08:00

b48d522bb3 deploy qwen3.5 and nemotron

cunliangkong synced commits to main at cunliangkong/LlamaFactory from mirror 2026-03-16 21:51:03 +08:00

70653026f5 [fix] make position_id_per_seconds configurable for Qwen2OmniPlugin (#10281)

cunliangkong pushed to main at cunliangkong/models-deploy

2026-03-16 16:02:26 +08:00

825c64c4dd change python version

cunliangkong pushed to main at cunliangkong/models-deploy

2026-03-16 14:23:18 +08:00

cb454c0f3f init commit

cunliangkong created branch main in cunliangkong/models-deploy

2026-03-16 14:23:18 +08:00

cunliangkong created repository cunliangkong/models-deploy

2026-03-16 14:22:39 +08:00

cunliangkong pushed to yc-4090-48g at cunliangkong/pretrained-models

2026-03-16 10:37:58 +08:00

dc2c35e2fa unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF

cunliangkong pushed to yc-a800-80g at cunliangkong/pretrained-models

2026-03-16 01:39:16 +08:00

6a887d8376 add Qwen/Qwen3-8B

cunliangkong created branch yc-a800-80g in cunliangkong/pretrained-models

2026-03-16 01:39:16 +08:00

cunliangkong pushed to yc-4090-48g at cunliangkong/pretrained-models

2026-03-16 00:30:46 +08:00

8b9f1b84f3 add Qwen/Qwen3.5-27B-FP8

cunliangkong created branch yc-4090-48g in cunliangkong/pretrained-models

2026-03-16 00:30:46 +08:00

cunliangkong pushed to main at cunliangkong/pretrained-models

2026-03-15 23:21:37 +08:00

772bf56d63 dvc cache edit

cunliangkong pushed to main at cunliangkong/pretrained-models

2026-03-15 22:52:01 +08:00

2de94280ff init commit

cunliangkong created branch main in cunliangkong/pretrained-models

2026-03-15 22:52:01 +08:00