Lawrence Wu's picture

18 2

Lawrence Wu

llllvvuu

·

https://llllvvuu.dev

AI & ML interests

None yet

Organizations

New activity in mlx-community/Minitron-4B-Base over 1 year ago

Upload folder using huggingface_hub

#1 opened over 1 year ago by

New activity in mlx-community/Minitron-4B-Base-8bit over 1 year ago

Upload folder using huggingface_hub

#1 opened over 1 year ago by

New activity in mlx-community/Minitron-4B-Base-4bit over 1 year ago

Upload folder using huggingface_hub

#1 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-Base over 1 year ago

the config class and config.json uses DeepseekConfig, not v2

#5 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-SFT over 1 year ago

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture

#1 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-Base over 1 year ago

Config / model type could probably just be `llama` / `LlamaForCausalLM`

#2 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-RL over 1 year ago

Config / model type could probably just be `llama` / `LlamaForCausalLM`

#2 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-SFT over 1 year ago

Set `model_type` to `llama`

#3 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-Base over 1 year ago

Set `model_type` to `llama`

#3 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-RL over 1 year ago

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture

#1 opened over 1 year ago by

Set `model_type` to `llama`

#6 opened over 1 year ago by

New activity in deepseek-ai/DeepSeek-Prover-V1.5-Base over 1 year ago

fix: modeling_deepseek.py should use `deepseek` instead of `deepseek_v2` architecture

#1 opened over 1 year ago by

Set `model_type` to `llama`

#3 opened over 1 year ago by

Set `model_type` to `llama`

#3 opened over 1 year ago by