Hu's picture

21 14

Hu

Moses25

·

moseshu

AI & ML interests

None yet

Recent Activity

new activity 16 days ago

deepseek-ai/DeepSeek-R1:输出乱码

new activity 22 days ago

deepseek-ai/DeepSeek-R1:Adding <think>\n after chat template will cause vllm to not return reasoning_content (null) when reasoning

new activity about 2 months ago

Qwen/Qwen2.5-7B-Instruct:vllm 0.6.6加速qwen2.5-7B模型出错

View all activity

Organizations

Collections 2

spaces 2

Llama 3 8B Chatbot

Moses25 Mistral 7B Instruct 32K AWQ

models 16

Moses25/Llama-3-8B-chat-32K

Text Generation • Updated Oct 25, 2024 • 34 • 3

Moses25/LlaMA-3-8B-32K-INT8

Text Generation • Updated Jul 28, 2024 • 10

Moses25/Mistral-7B-Instruct-32K-GPTQ-INT8

Text Generation • Updated Jul 13, 2024 • 15 • 1

Moses25/Mistral-7B-Base-V1

Text Generation • Updated Jul 12, 2024 • 20 • 1

Moses25/Llama-3-8B-Instruct-V1.0

Text Generation • Updated Jul 3, 2024 • 31 • 1

Moses25/Llama-3-8B-chat-32K-AWQ

Text Generation • Updated Jun 6, 2024 • 13 • 1

Moses25/Mistral-7B-Instruct-32K-AWQ

Text Generation • Updated Jun 5, 2024 • 14 • 1

Moses25/Mistral-7B-chat-32k

Text Generation • Updated Jun 3, 2024 • 20 • 1

Moses25/Meta-LlaMA-3-8B-Instruct-16k

Text Generation • Updated May 6, 2024 • 43 • 2

Moses25/Mistral-7B-Instruct-16k

Text Generation • Updated May 5, 2024 • 21 • 1

datasets 3

Moses25/generate-Instruction-output-190k

Viewer • Updated Jul 28, 2024 • 197k • 84

Moses25/Instruct-dataset11M

Viewer • Updated Jun 21, 2024 • 1.69M • 104

Moses25/llava_instruction_80k

Preview • Updated Jun 21, 2024 • 99 • 3