Hugging Face's logo
Régis Pierrard's picture
62 2 11

Régis Pierrard

regisss
Bellamy66's profile picture garrethlee's profile picture martineden's profile picture
·

AI & ML interests

None yet

Recent Activity

updated a dataset about 1 month ago
regisss/benchmarks
Reacted to onekq's post with 🔥 about 1 month ago
I'm now working on finetuning of coding models. If you are GPU-hungry like me, you will find quantized models very helpful. But quantization for finetuning and inference are different and incompatible. So I made two collections here. Inference (GGUF, via Ollama, CPU is enough) https://huggingface.co/collections/onekq-ai/ollama-ready-coding-models-67118c3cfa1af2cf04a926d6 Finetuning (Bitsandbytes, QLora, GPU is needed) https://huggingface.co/collections/onekq-ai/qlora-ready-coding-models-67118771ce001b8f4cf946b2 For quantization, the inference models are far more popular on HF than finetuning models. I use https://huggingface.co/QuantFactory to generate inference models (GGUF), and there are a few other choices. But there hasn't been such a service for finetuning models. DIY isn't too hard though. I made a few myself and you can find the script in the model cards. If the original model is small enough, you can even do it on a free T4 (available via Google Colab). If you know a (small) coding model worthy of quantization, please let me know and I'd love to add it to the collections.
posted an update about 1 month ago
Interested in performing inference with an ONNX model?⚡️ The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler! You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows: ```py from optimum.onnxruntime import ORTModelForSequenceClassification # Load the model from the hub and export it to the ONNX format model_id = "distilbert-base-uncased-finetuned-sst-2-english" model = ORTModelForSequenceClassification.from_pretrained(model_id, export=True) ``` Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
View all activity

Articles

Organizations

Hugging Face's profile picture Habana AI's profile picture Hugging Face Optimum's profile picture group2's profile picture Hugging Face H4's profile picture Hugging Face OSS Metrics's profile picture HuggingFace Doc Builds's profile picture Blog-explorers's profile picture AI Energy Score Project's profile picture Social Post Explorers's profile picture Hugging Face Machine Learning Optimization's profile picture Optimum Internal Testing's profile picture SLLHF's profile picture Privacy Preserving AI Hackathon (Zama, Hugging Face, Entrepreneur First)'s profile picture

regisss's activity

New activity in optimum/llm-perf-leaderboard about 2 months ago

add intel CPU to leaderboard

2
#32 opened 3 months ago by baptistecolle
New activity in hf-doc-build/doc-build 2 months ago

Delete transformers/v4.41.3.zip

4
#29 opened 2 months ago by joaogante

Update transformers/_versions.yml

2
#30 opened 2 months ago by joaogante
New activity in Habana/roberta-large 3 months ago

Update README.md

4
#3 opened 5 months ago by astachowicz
New activity in Habana/bert-large-uncased-whole-word-masking 3 months ago

Update README.md

3
#2 opened 5 months ago by astachowicz
New activity in Habana/bert-base-uncased 3 months ago

Update README.md

5
#2 opened 5 months ago by astachowicz
New activity in Habana/bart 3 months ago

is it ok to use?

1
#2 opened 3 months ago by yash3056
New activity in bigcode/starcoder2-7b 6 months ago

Update values of `bos_token_id` and `eos_token_id` in generation_config.json
#15 opened 6 months ago by regisss
New activity in bigcode/starcoder2-15b 6 months ago

Update values of `bos_token_id` and `eos_token_id` in generation_config.json

1
#25 opened 6 months ago by regisss
New activity in bigcode/starcoder2-15b-instruct-v0.1 6 months ago

Update values of `bos_token_id` and `eos_token_id` in generation_config.json

1
#4 opened 6 months ago by regisss
New activity in Xenova/speecht5_tts 7 months ago

Method for exproting speecht5_tts to ONNX

8
#1 opened 9 months ago by JackismyShephard
New activity in Habana/t5 7 months ago

Fix typo in use_dynamics_shapes

3
#6 opened 7 months ago by mdeopujari

enable dynamic shapes by default

3
#5 opened 8 months ago by skaulintel
New activity in regisss/llama2-70b-fused-qkv-mlperf 8 months ago

Flash Attn Import Errors (https://github.com/huggingface/transformers/issues/28459)

2
#1 opened 8 months ago by rgandikota
New activity in Habana/albert-large-v2 9 months ago

update to use dynamic shapes

1
#3 opened about 1 year ago by skaulintel

use dynamic shapes

1
#4 opened about 1 year ago by skaulintel
New activity in Habana/albert-xxlarge-v1 10 months ago

use dynamic shapes

1
#2 opened about 1 year ago by skaulintel
New activity in Habana/clip 10 months ago

use dynamic shapes

1
#2 opened about 1 year ago by skaulintel
New activity in Habana/wav2vec2 about 1 year ago

Remove hmp from gaudi_config.json and README

2
#2 opened over 1 year ago by jwieczorekhabana
New activity in Habana/gpt2 about 1 year ago

Remove deprecated Habana mixed precision from gaudi config

5
#4 opened over 1 year ago by olszd