 efort
|
fec6a8e275
|
更新 basic_demo/openai_api_server.py
|
2025-02-10 15:29:49 +08:00 |
|
efort
|
7cf4f4f422
|
更新 basic_demo/openai_api_server.py
|
2025-02-10 15:05:51 +08:00 |
zhipuch
|
64476493cf
|
Merge pull request #701 from openvino-dev-samples/main
Update the introduction to Intel Demo
|
2025-01-17 10:31:15 +08:00 |
Ethan Yang
|
7a4dfa354b
|
Update README_en.md
|
2025-01-15 11:50:31 +08:00 |
|
Ethan Yang
|
8d089917df
|
Update README.md
|
2025-01-15 11:44:59 +08:00 |
|
zhipuch
|
4dc2f76e68
|
update:trans_batch_demo
|
2024-12-31 16:07:08 +08:00 |
zR
|
81ba7e087c
|
add del label
|
2024-12-15 12:43:53 +08:00 |
|
zR
|
52cd14ce8c
|
support NPU 910B
|
2024-12-09 15:58:10 +08:00 |
|
zR
|
e14f187090
|
Merge branch 'main' of https://github.com/THUDM/GLM-4
|
2024-12-09 15:54:29 +08:00 |
sixgod
|
5c70856738
|
fix bug in glm-4v openai_server
|
2024-12-02 18:02:26 +08:00 |
|
Yuxuan.Zhang
|
c23abb0c59
|
Merge pull request #655 from zhipuch/main
correct compute_metrics function
|
2024-11-25 22:38:22 +08:00 |
|
zhipuch
|
7a14e5d352
|
correct compute_metrics function
|
2024-11-19 09:35:07 +08:00 |
|
zR
|
4c66fa48d1
|
Merge branch 'main' of https://github.com/THUDM/GLM-4
|
2024-11-18 11:51:56 +08:00 |
|
zR
|
804733811f
|
change of readme and req for vllm new version
|
2024-11-18 10:10:43 +08:00 |
|
Yuxuan.Zhang
|
b052da77b1
|
Merge pull request #650 from sixsixcoder/main
support vllm 0.6.3
|
2024-11-14 18:41:32 +08:00 |
|
sixsixcoder
|
476a066830
|
support vllm 0.6.3
|
2024-11-12 16:45:17 +08:00 |
|
Yuxuan.Zhang
|
4446f60195
|
Merge pull request #649 from zhipuch/main
process eval issue
|
2024-11-12 15:47:35 +08:00 |
|
zhipuch
|
a7dbfa5ada
|
process eval issue
|
2024-11-11 17:33:43 +08:00 |
|
Yuxuan.Zhang
|
1e0fa42dd8
|
Merge pull request #639 from zhipuch/main
adapt transformers==4.46
|
2024-11-10 20:44:06 +08:00 |
|
zhipuch
|
a0c568753a
|
adapt transformers>=4.46
|
2024-11-06 11:40:09 +00:00 |
|
zhipuch
|
af1d4f2f11
|
adapt transformers==4.46
|
2024-11-04 21:33:07 +08:00 |
|
zR
|
0b37cf22e5
|
model download page
|
2024-11-01 18:52:41 +08:00 |
|
zR
|
d71b8c2284
|
comment with trust_remote_code=True
|
2024-11-01 18:49:55 +08:00 |
|
Yuxuan.Zhang
|
bca86f8c8e
|
Merge pull request #634 from sixsixcoder/main
Support for GLM-4-9B-Chat-hf and GLM-4v-9B models on vLLM >= 0.6.3 and transformers >= 4.46.0
|
2024-11-01 18:23:16 +08:00 |
|
sixgod
|
471943bfd7
|
support INT4 inference
|
2024-11-01 10:21:56 +00:00 |
|
sixgod
|
24c8e1b317
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:24:39 +00:00 |
|
sixgod
|
2ba0aa4b54
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:23:05 +00:00 |
|
sixgod
|
02831d280b
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:20:57 +00:00 |
|
sixgod
|
a8069aca73
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:14:20 +00:00 |
|
sixgod
|
1d68300ecf
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:11:59 +00:00 |
|
sixgod
|
9b39ba6d1b
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:06:04 +00:00 |
|
sixgod
|
e3e6de52c4
|
transformers4.46 and vllm0.6.3
|
2024-11-01 09:00:39 +00:00 |
|
zR
|
6bf9f85f70
|
remove wrong path
|
2024-10-29 01:41:10 +08:00 |
|
zR
|
94776fb841
|
update for transformers 4.46
|
2024-10-29 01:40:11 +08:00 |
|
zR
|
c2c28bc45c
|
transforemrs>=4.46 support
|
2024-10-29 00:13:41 +08:00 |
Zhengxiao Du
|
9cd635a825
|
Update README.md
|
2024-10-28 14:05:15 +08:00 |
|
Yuxuan.Zhang
|
4e9b473d18
|
Merge pull request #563 from huolongguo1O/patch-1
解决finetune.py在加载配置文件时的错误
|
2024-10-16 17:36:19 +08:00 |
|
Yuxuan.Zhang
|
5142bdb6e1
|
Merge pull request #585 from sixsixcoder/main
Add GLM-4v-9B model support for vllm framework
|
2024-10-15 14:55:35 +08:00 |
|
sixgod
|
f25bba83b7
|
Rename llm_cli_vision_demo.py to vllm_cli_vision_demo.py
|
2024-10-12 22:31:04 +08:00 |
|
sixgod
|
df567d31be
|
Create llm_cli_vision_demo.py
|
2024-10-12 22:30:37 +08:00 |
|
sixgod
|
68c6b52f61
|
Update README.md
|
2024-10-12 21:32:23 +08:00 |
|
sixgod
|
9ea3707c9e
|
Update README_en.md
|
2024-10-12 21:30:49 +08:00 |
|
sixgod
|
034bf5c448
|
Update README_en.md: Add GLM-4v-9B model support for vllm framework
|
2024-10-12 21:30:13 +08:00 |
|
zR
|
3e7735d4f7
|
update the req and chatglm_tokenizer.py
|
2024-10-06 14:09:05 +08:00 |
|
Yuxuan.Zhang
|
23773d94e2
|
Merge pull request #569 from zhipuch/main
update readme
|
2024-09-26 13:52:20 +08:00 |
|
zhipuch
|
10f23a0cd3
|
update readme
|
2024-09-24 11:17:59 +00:00 |
|
zhipuch
|
0ef093c1a2
|
update readme
|
2024-09-24 11:15:20 +00:00 |
huolongguo1O
|
f6ee34eb6e
|
Update finetune.py
上一个commit在配置文件添加了freezeV选项，但在finetune.py中没有支持。1c2676415c (diff-a70f5de59d3f0aced07176ede208e2d2f420d7eafd2d9cf2478f93636160e538)
暂时添加一句占位吧，虽然这个选项对纯文本微调没啥用
|
2024-09-17 09:50:19 +08:00 |
|
Yuxuan.Zhang
|
81af3cfc5a
|
Merge pull request #556 from sixsixcoder/main
update that multi-GPUs inference with transformers in glm-4 and glm-4v
|
2024-09-11 19:52:17 +08:00 |
|
sixsixcoder
|
188c7956a1
|
transformers with glm4v lora adapter
|
2024-09-11 10:34:24 +00:00 |