zhang

redauzhang's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in tencent/Hy-MT2-1.8B-2Bit-GGUF 8 days ago

Hy-MT2-1.8B-2Bit.gguf fails to load in llama.cpp and llama-cpp-python: tensor offset mismatch

👍 1

2

#6 opened about 1 month ago by

nedo1993

New activity in yuxinlu1/qwen3-6-27b-chinese-xianxia-lora-v2 16 days ago

真实效果怎么样，这个是不是agentic+RAG+harness来强化场景和细节的

#1 opened 16 days ago by

redauzhang

New activity in YangYang-Research/web-attack-detection 7 months ago

why not using bert for classfication (codebert or distilBert) ?

#1 opened 7 months ago by

redauzhang

Communication regarding data sources and accuracy

#2 opened 7 months ago by

redauzhang

New activity in FlagAlpha/Llama2-Chinese-7b-Chat almost 3 years ago

有没有最佳实践得指导呀，比如prompt得编写偏好指导，langchian+embediding+textspliter的配置

#1 opened almost 3 years ago by

redauzhang

New activity in baichuan-inc/Baichuan-7B almost 3 years ago

又可用的 baichuan.cpp 借用avx2运行的吗，我看都是 csm家族的模型呢

2

#19 opened about 3 years ago by

redauzhang

New activity in bigscience/bloom-7b1 about 3 years ago

Is it possible to fine-tuning the 7b1 model on 4 A100 (80G) gpus?

3

#44 opened over 3 years ago by

TTCoding

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1 about 3 years ago

您好，add_token.json内容和models不匹配，这个应该怎么修改

2

#22 opened about 3 years ago by

redauzhang

New activity in hkunlp/instructor-xl about 3 years ago

中文效果怎么样？

2

#17 opened about 3 years ago by

redauzhang

New activity in zai-org/chatglm-6b about 3 years ago

transformers 从4.26.1 升级至4.27.1 后报错 ModuleNotFoundError: No module named 'transformers_modules.THUDM/chatglm-6b'

2

#42 opened about 3 years ago by

liuhantao