lichaochao's picture

lichaochao

chaochaoli

·

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

FuseAI/FuseChat-Llama-3.1-8B-Instruct

liked a model 2 days ago

intfloat/e5-large-v2

liked a model 2 days ago

intfloat/multilingual-e5-large

View all activity

Organizations

None yet

chaochaoli's activity

commented a paper about 2 months ago

Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models

Paper • 2408.02442 • Published Aug 5 • 21 •

New activity in nvidia/dragon-multiturn-query-encoder 3 months ago

where is high-quality multi-turn dataset？

#4 opened 3 months ago by

New activity in bosonai/Higgs-Llama-3-70B 4 months ago

感觉这个领域，中文模型可能更有市场一点。

#11 opened 5 months ago by

New activity in BAAI/bge-m3 5 months ago

1_Pooling 这个目录的作用是？

#72 opened 5 months ago by

New activity in BAAI/bge-m3 6 months ago

How to use the ONNX format of BERT-based model bge-m3, how to load the model and output sentence embeddings.

#52 opened 7 months ago by

New activity in internlm/internlm2_5-7b-chat 6 months ago

Fine-tuning

#5 opened 6 months ago by

New activity in shenzhi-wang/Llama3-70B-Chinese-Chat-GGUF-4bit 7 months ago

中文理解有点差

#2 opened 7 months ago by

New activity in Qwen/Qwen1.5-110B-Chat-GGUF 8 months ago

int4-gguf推理很容易出现重复现象

#1 opened 8 months ago by

New activity in Qwen/Qwen1.5-110B-Chat-GPTQ-Int4 8 months ago

gguf啥时候可以提供，感谢大佬

#1 opened 8 months ago by

New activity in CohereForAI/c4ai-command-r-plus-4bit 8 months ago

Possible to do inference on long contexts with limited VRAM?

#6 opened 8 months ago by

New activity in Qwen/Qwen1.5-7B-Chat 8 months ago

qwen1.5-7b-chat是不是推理起来比qwen1.5-7b快很多

#9 opened 10 months ago by

New activity in internlm/internlm2-1_8b 10 months ago

1.8b系列大海捞针的模型对比

#2 opened 10 months ago by

New activity in xverse/XVERSE-13B-256K 10 months ago

256k大概需要多少显存才可以支持？

#2 opened 11 months ago by

New activity in OpenAssistant/reward-model-deberta-v3-large-v2 about 1 year ago

How to fine tune this model with the Trainer API?

#8 opened about 1 year ago by

Train Code

#2 opened almost 2 years ago by

synthetic-instruct-gptj-pairwise pairwise data how to pre-process for train data

#9 opened about 1 year ago by

New activity in daryl149/llama-2-7b-chat-hf about 1 year ago

tokenizer.model_max_length for llama-2-7b-chat-hf

#3 opened over 1 year ago by

huggingFace1108

New activity in baichuan-inc/Baichuan2-7B-Chat-4bits over 1 year ago

你们用4bit有感觉到慢吗

#1 opened over 1 year ago by

New activity in daryl149/llama-2-7b-chat-hf over 1 year ago

What's the difference between this and the official llama version?

#4 opened over 1 year ago by

New activity in TMElyralab/lyraChatGLM over 1 year ago

您好，请问可以提供chaglm原始模型转换成"1-gpu-fp16.h5"模型文件的脚本吗

#38 opened over 1 year ago by