Nicolas Patry's picture

Nicolas Patry

Narsil

·

https://github.com/Narsil/

AI & ML interests

None yet

Recent Activity

updated a model 16 days ago

Narsil/silero

published a model 16 days ago

Narsil/silero

reacted to fdaudens's post with ❤️ 18 days ago

Tried something new: an AI-generated podcast that breaks down the top research paper each day. Fully automated, now live on Spotify. I built this prototype to help keep up with the rapid pace of AI developments and, hopefully, make cutting-edge research more accessible. I don’t know about you, but just listening to a conversation about a paper really helps the content sink in for me. This build taught me a lot about full automation. If you’re into the technical weeds: Qwen3 runs on Inference to handle the script, Kokoro does the voice, and the whole thing gets published automatically thanks to the Hugging Face Jobs API and Gradio deployment. It’s not perfect yet — I’ll be monitoring for hallucinations and incoherence. The voice model still needs polish, but it’s a promising start. Would love to build this with the community — submit a PR or send feedback. It’s just a beta of an experimental idea! Big kudos to @m-ric, whose Open NotebookLM this is based on, and to @nielsr for his terrific work making research papers more accessible. - Podcast on Spotify: https://open.spotify.com/show/3PTucIW1w1GIkqTYm32ka7?si=c7a851f83e6d4331 (Apple Podcasts soon) - Code: https://huggingface.co/spaces/fdaudens/podcast-jobs - Open NotebookLM: https://huggingface.co/spaces/m-ric/open-notebooklm - Also super helpful, @qgallouedec's tutorial on HF Jobs API: https://huggingface.co/spaces/qgallouedec/run-hello-world/blob/main/README.md

View all activity

Organizations

Narsil's activity

New activity in safetensors/convert 4 months ago

Allow running conversion after closing a previous PR.

#21 opened over 1 year ago by

New activity in huggingchat/chat-ui 6 months ago

Your feedback on HuggingChat

#1 opened about 2 years ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 10 months ago

"Model mistralai/Mistral-Nemo-Instruct-2407 time out" in Inference APIs

#42 opened 11 months ago by

New activity in 01-ai/Yi-1.5-34B-Chat about 1 year ago

Adding a fast tokenizer

#10 opened about 1 year ago by

New activity in 01-ai/Yi-1.5-9B-Chat about 1 year ago

Add fast tokenizer

#9 opened about 1 year ago by

New activity in ibm-ai-platform/llama3-8b-accelerator about 1 year ago

ValueError: Unsupported model type mlp_speculator using TGI server

#2 opened about 1 year ago by

rishabh-simpplr

New activity in text-generation-inference/commandrplus-medusa about 1 year ago

Is `--speculate` needed for Medusa in TGI?

#1 opened about 1 year ago by

New activity in CohereLabs/c4ai-command-r-plus about 1 year ago

Is <BOS_TOKEN> really needed?

#22 opened about 1 year ago by

New activity in diffusers/convert about 1 year ago

Error: 'NoneType' object has no attribute 'pr_url'

#4 opened about 1 year ago by

New activity in cognitivecomputations/dolphin-2.1-mistral-7b over 1 year ago

Adding `safetensors` variant of this model

#21 opened over 1 year ago by

New activity in FasterDecoding/medusa-vicuna-7b-v1.3 over 1 year ago

Adding safetensors variant

#1 opened over 1 year ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 over 1 year ago

CUDA error when initialising model with text-generation-inference

#22 opened over 1 year ago by

sliding_window

#37 opened over 1 year ago by

New activity in cognitivecomputations/dolphin-2.2-70b over 1 year ago

Safetensors version?

#2 opened over 1 year ago by

New activity in Narsil/small2 over 1 year ago

Adding `safetensors` variant of this model

#4 opened over 1 year ago by

Adding `safetensors` variant of this model

#3 opened over 1 year ago by

Adding `safetensors` variant of this model

#2 opened over 1 year ago by

New activity in tiiuae/falcon-7b-instruct over 1 year ago

Adding `safetensors` variant of this model

#107 opened over 1 year ago by

Adding `safetensors` variant of this model

#106 opened over 1 year ago by

Adding `safetensors` variant of this model

#105 opened over 1 year ago by