lmdeploy's picture

lmdeploy

unsubscribe

·

https://github.com/InternLM/lmdeploy

AI & ML interests

None yet

Organizations

unsubscribe's activity

New activity in internlm/internlm3-8b-instruct-gptq-int4 3 months ago

update metadata

#1 opened 3 months ago by

New activity in internlm/internlm2_5-7b-chat-gguf 9 months ago

Tool calls broken; Link to fix

#2 opened 10 months ago by

New activity in internlm/internlm2_5-7b-chat 10 months ago

chat prompt

#6 opened 10 months ago by

New activity in internlm/internlm-xcomposer2d5-7b 10 months ago

lmdeploy usage

#4 opened 10 months ago by

New activity in internlm/internlm2_5-7b-chat-gguf 10 months ago

[UNUSEDTOKEN145]

#1 opened 10 months ago by

New activity in internlm/internlm2_5-7b-chat-1m 10 months ago

1M inference error on A100 80GBx4 System

#1 opened 10 months ago by

New activity in internlm/internlm2-chat-20b-4bits about 1 year ago

Update config.json

#4 opened about 1 year ago by

New activity in internlm/internlm2-math-7b over 1 year ago

Apply for community grant: Academic project (gpu)

#1 opened over 1 year ago by

New activity in internlm/InternLM2-Chat-20B-TurboMind-4Bits over 1 year ago

Unable to trigger a next round of discussion

#2 opened over 1 year ago by

Apply for community grant: Academic project (gpu)

#1 opened over 1 year ago by

New activity in internlm/internlm2-chat-20b-4bits over 1 year ago

Update special tokens

#1 opened over 1 year ago by

New activity in internlm/internlm2-chat-7b-4bits over 1 year ago

Update special tokens

#1 opened over 1 year ago by

New activity in lmdeploy/llama2-chat-70b-4bit over 1 year ago

llama2-chat-70b-w4 weights

#1 opened over 1 year ago by

New activity in internlm/internlm-chat-20b-4bit over 1 year ago

Update modeling_internlm.py

#11 opened over 1 year ago by

python3: No module named lmdeploy.serve.turbomind.main;

#1 opened over 1 year ago by

[Bug] win11下gpu：4090使用docker部署internlm-chat-20b-4bit，显示WARNING: Can not find tokenizer.json. It may take long time to initialize the tokenizer.提问时无反馈卡死。

#3 opened over 1 year ago by

推理报错 [TM][ERROR] CUDA runtime error: invalid argument

#5 opened over 1 year ago by

Assertion Error

#6 opened over 1 year ago by

Report a bug?

#7 opened over 1 year ago by

although tokenizer.model exists , deploy is complaining that it does not

#8 opened over 1 year ago by