Chuan Jianguo's picture

10 1

Chuan Jianguo

cmgzy

·

AI & ML interests

None yet

Recent Activity

new activity 13 days ago

deepseek-ai/DeepSeek-R1:Host of the model

new activity 15 days ago

ibm-granite/granite-3.2-8b-instruct-preview:Cannot solve strawberry problem

new activity 16 days ago

deepseek-ai/DeepSeek-R1:non-reasoning data

View all activity

Organizations

None yet

cmgzy's activity

New activity in deepseek-ai/DeepSeek-R1 13 days ago

Host of the model

#138 opened 13 days ago by

New activity in ibm-granite/granite-3.2-8b-instruct-preview 15 days ago

Cannot solve strawberry problem

#4 opened 15 days ago by

New activity in deepseek-ai/DeepSeek-R1 16 days ago

non-reasoning data

#132 opened 16 days ago by

New activity in mlx-community/c4ai-command-r7b-12-2024-6bit 2 months ago

problem with chinese prompt

#2 opened 2 months ago by

New activity in google/paligemma-3b-pt-224 9 months ago

How <seg[value]> tokens generate the masks in segmentation tasks?

#10 opened 9 months ago by

New activity in mlx-community/Mistral-7B-Instruct-v0.3-8bit 9 months ago

how to make use of function calling in system message

#2 opened 9 months ago by

New activity in mlx-community/paligemma-3b-mix-224-8bit 9 months ago

mlx-vlm 0.0.6 not yet released

#1 opened 9 months ago by

New activity in mlx-community/llava-llama-3-8b-v1_1-8bit 10 months ago

missing preprocessor_config.json

#1 opened 10 months ago by

New activity in mlx-community/Llama-3-8B-Instruct-1048k-8bit 10 months ago

model does not stop even if <|eot_id|> is generated

#1 opened 10 months ago by

New activity in mlx-community/Qwen1.5-MoE-A2.7B-4bit 11 months ago

ValueError: Model type qwen2_moe not supported

#1 opened 11 months ago by