zhuqihao's picture

18 7

zhuqihao

zqh11

·

AI & ML interests

None yet

Recent Activity

authored a paper 23 days ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

liked a model 27 days ago

deepseek-ai/DeepSeek-R1-Zero

authored a paper 6 months ago

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

View all activity

Organizations

zqh11's activity

New activity in deepseek-ai/deepseek-coder-33b-instruct 12 months ago

Adding `safetensors` variant of this model

#24 opened 12 months ago by

New activity in deepseek-ai/deepseek-coder-6.7b-instruct about 1 year ago

inference_params

#12 opened about 1 year ago by

New activity in deepseek-ai/deepseek-coder-33b-instruct about 1 year ago

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 196.00 MiB. GPU 0 has a total capacty of 79.11 GiB of which 29.56 MiB is free

#21 opened about 1 year ago by

Set global data for future chats

#17 opened about 1 year ago by

[AUTOMATED] Model Memory Requirements

#18 opened about 1 year ago by

model-sizer-bot

Fine tune the model with part of layers on GPU and rest on CPU

#11 opened about 1 year ago by

New activity in deepseek-ai/deepseek-coder-7b-base-v1.5 about 1 year ago

Update to deepseek-coder-7b-base-v1.5 in code

#1 opened about 1 year ago by

New activity in deepseek-ai/deepseek-coder-33b-instruct about 1 year ago

Context length

#13 opened about 1 year ago by

New activity in deepseek-ai/deepseek-coder-6.7b-instruct about 1 year ago

Do we need BOS token before each turn of chat during finetuning?

#9 opened about 1 year ago by

Wrong result when calling apply_chat_template with add_generation_prompt=False

#8 opened about 1 year ago by

New activity in bigcode/bigcode-models-leaderboard about 1 year ago

[Community Submission] Model: deepseek-ai/deepseek-coder-6.7b-instruct, Username: zqh11

#43 opened about 1 year ago by

[Community Submission] Model: deepseek-ai/deepseek-coder-33b-instruct, Username: zqh11

#42 opened about 1 year ago by

New activity in bigcode/bigcode-models-leaderboard over 1 year ago

[Community Submission] Model: deepseek-ai/deepseek-coder-1.3b-base, Username: zqh11

#33 opened over 1 year ago by

[Community Submission] Model: deepseek-ai/deepseek-coder-6.7b-base, Username: zqh11

#32 opened over 1 year ago by

[Community Submission] Model: deepseek-ai/deepseek-coder-33b-base, Username: zqh11

#31 opened over 1 year ago by

New activity in deepseek-ai/deepseek-coder-6.7b-instruct over 1 year ago

Confirming the EOS token? 32021 or 32014? Or both?

#1 opened over 1 year ago by

New activity in bigcode/bigcode-models-leaderboard over 1 year ago

Cannot sumbit through the button

#29 opened over 1 year ago by