SmolLM - blazingly fast and remarkably powerful
β’
267
Loubna Ben Allal
loubnabnl
AI & ML interests
LLMs, ML for code, Synthetic data
Recent Activity
updated
a dataset
about 1 hour ago
HuggingFaceTB/smoltalk
updated
a Space
about 21 hours ago
HuggingFaceTB/README
posted
an
update
about 21 hours ago
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit π οΈ https://github.com/huggingface/smollm/
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset https://huggingface.co/datasets/HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
Articles
Organizations
loubnabnl's activity
updated
a
dataset
about 1 hour ago
updated
a
Space
about 21 hours ago
posted
an
update
about 21 hours ago
Post
462
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit π οΈ https://github.com/huggingface/smollm/
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
updated
4
models
about 22 hours ago
HuggingFaceTB/SmolLM2-360M-Instruct
Text Generation
β’
Updated
β’
32.4k
β’
54
HuggingFaceTB/SmolLM2-360M
Text Generation
β’
Updated
β’
7.34k
β’
24
HuggingFaceTB/SmolLM2-1.7B
Text Generation
β’
Updated
β’
13.3k
β’
73
HuggingFaceTB/SmolLM2-1.7B-Instruct
Text Generation
β’
Updated
β’
77.9k
β’
β’
360
Reacted to
prithivMLmods's
post with π₯
1 day ago
Post
2435
Weekend Dribble π¦πΊ
Adapters for Product Ad Backdrops, Smooth Polaroids, Minimalist Sketch cards, Super Blends!!
π€Demo on: prithivMLmods/FLUX-LoRA-DLC
Stranger Zones :
ππΌ{ Super Blend } : strangerzonehf/Flux-Super-Blend-LoRA
ππΌ{ Product Concept Ad } : prithivMLmods/Flux-Product-Ad-Backdrop
ππΌ{ Frosted Mock-ups } : prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA
ππΌ{ Polaroid Plus } : prithivMLmods/Flux-Polaroid-Plus
ππΌ{Sketch Cards} : prithivMLmods/Flux.1-Dev-Sketch-Card-LoRA
πStranger Zone: https://huggingface.co/strangerzonehf
πFlux LoRA Collections: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods π€
Adapters for Product Ad Backdrops, Smooth Polaroids, Minimalist Sketch cards, Super Blends!!
π€Demo on: prithivMLmods/FLUX-LoRA-DLC
Stranger Zones :
ππΌ{ Super Blend } : strangerzonehf/Flux-Super-Blend-LoRA
ππΌ{ Product Concept Ad } : prithivMLmods/Flux-Product-Ad-Backdrop
ππΌ{ Frosted Mock-ups } : prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA
ππΌ{ Polaroid Plus } : prithivMLmods/Flux-Polaroid-Plus
ππΌ{Sketch Cards} : prithivMLmods/Flux.1-Dev-Sketch-Card-LoRA
πStranger Zone: https://huggingface.co/strangerzonehf
πFlux LoRA Collections: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods π€
Reacted to
merve's
post with β€οΈπ
1 day ago
Post
2536
your hugging face profile now has your recent activities π€
updated
2
models
1 day ago
About Instruction model evaluation
1
#1 opened 24 days ago
by
ldwang
ldwang
What MMLU (cloze) used for evaluation.
1
#2 opened 12 days ago
by
akhilfau
akhilfau
add base model metadata
1
#4 opened 11 days ago
by
davanstrien
davanstrien
Reproducing Evaluation with lighteval
2
#1 opened 7 days ago
by
PatrickHaller
PatrickHaller
finetuning
4
#2 opened 25 days ago
by
HassanStar
HassanStar
What were the training datasets for this model?
3
#14 opened 17 days ago
by
Weyaxi
Weyaxi
scale-up? or full datasets list?
3
#11 opened 19 days ago
by
lucyknada
lucyknada
Reacted to
merve's
post with π₯
3 days ago
Post
2213
What a week! A recap for everything you missed βοΈ
merve/nov-22-releases-673fbbcfc1c97c4f411def07
Multimodal β¨
> Mistral AI
released Pixtral 124B, a gigantic open vision language model
> Llava-CoT (formerly known as Llava-o1) was released, a multimodal reproduction of o1 model by PKU
> OpenGVLab released MMPR: a new multimodal reasoning dataset
> Jina has released Jina-CLIP-v2 0.98B multilingual multimodal embeddings
> Apple released new SotA vision encoders AIMv2
LLMs π¦
> AllenAI dropped a huge release of models, datasets and scripts for TΓΌlu, a family of models based on Llama 3.1 aligned with SFT, DPO and a new technique they have developed called RLVR
> Jina has released embeddings-v3: new multilingual embeddings with longer context
> Hugging Face released SmolTalk: synthetic dataset used to align SmolLM2 using supervised fine-tuning
> Microsoft released orca-agentinstruct-1M-v1: a gigantic instruction dataset of 1M synthetic instruction pairs
Image Generation πΌοΈ
> Black Forest Labs released Flux 1. tools: four new models for different image modifications and two LoRAs to do image conditioning and better steer generations
Lastly Hugging Face released a new library Observers: a lightweight SDK for monitoring interactions with AI APIs and easily store and browse them π
$ pip install observers
merve/nov-22-releases-673fbbcfc1c97c4f411def07
Multimodal β¨
> Mistral AI
released Pixtral 124B, a gigantic open vision language model
> Llava-CoT (formerly known as Llava-o1) was released, a multimodal reproduction of o1 model by PKU
> OpenGVLab released MMPR: a new multimodal reasoning dataset
> Jina has released Jina-CLIP-v2 0.98B multilingual multimodal embeddings
> Apple released new SotA vision encoders AIMv2
LLMs π¦
> AllenAI dropped a huge release of models, datasets and scripts for TΓΌlu, a family of models based on Llama 3.1 aligned with SFT, DPO and a new technique they have developed called RLVR
> Jina has released embeddings-v3: new multilingual embeddings with longer context
> Hugging Face released SmolTalk: synthetic dataset used to align SmolLM2 using supervised fine-tuning
> Microsoft released orca-agentinstruct-1M-v1: a gigantic instruction dataset of 1M synthetic instruction pairs
Image Generation πΌοΈ
> Black Forest Labs released Flux 1. tools: four new models for different image modifications and two LoRAs to do image conditioning and better steer generations
Lastly Hugging Face released a new library Observers: a lightweight SDK for monitoring interactions with AI APIs and easily store and browse them π
$ pip install observers
- 2 replies