James Braza's picture

9 1

James Braza

jamesbraza

·

jamesbraza

AI & ML interests

None yet

Recent Activity

new activity about 8 hours ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B:Tokenizer config is wrong

new activity about 8 hours ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B:Tokenizer config's `chat_template` removes everything before `</think>` XML closing tag

updated a dataset about 1 month ago

futurehouse/aviary-paper-data

View all activity

Organizations

jamesbraza's activity

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B about 8 hours ago

Tokenizer config is wrong

#10 opened 9 days ago by

Tokenizer config's `chat_template` removes everything before `</think>` XML closing tag

#21 opened about 8 hours ago by

New activity in vectara/leaderboard 7 months ago

Sorting by Hallucination Rate fails

#5 opened 7 months ago by

New activity in microsoft/phi-1_5 about 1 year ago

Failed to run on MacBook: requiring flash_attn

#72 opened about 1 year ago by

New activity in HuggingFaceH4/zephyr-7b-alpha about 1 year ago

Model answering with all newlines?

#19 opened over 1 year ago by

New activity in microsoft/phi-1_5 about 1 year ago

Failure to reproduce QA Format response from the README

#71 opened about 1 year ago by

New activity in Wauplin/huggingface_hub about 1 year ago

📢 [v0.19.0] Inference Endpoints and robustness!

#2 opened about 1 year ago by

New activity in TheBloke/Llama-2-13B-chat-GGUF over 1 year ago

Are these models trained from scratch, or just different quantizations of the same model?

#2 opened over 1 year ago by

New activity in TheBloke/Llama-2-13B-GGML over 1 year ago

Could not load Llama model from path

#5 opened over 1 year ago by

Could not load Llama model from path

#5 opened over 1 year ago by