SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper
•
2502.02737
•
Published
•
61
nltpt-q
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
nltpt-q's activity
cfahlgren1
authored
a
paper
about 1 hour ago
reach-vb
authored
a
paper
about 1 hour ago
cfahlgren1
posted
an
update
9 days ago
Post
1841
If you haven't seen yet, we just released Inference Providers 🔀
> 4 new serverless inference providers on the Hub 🤯
> Use your HF API key or personal key with all providers 🔑
> Chat with Deepseek R1, V3, and more on HF Hub 🐋
> We support Sambanova, TogetherAI, Replicate, and Fal.ai 💪
Best of all, we don't charge any markup on top of the provider 🫰 Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
> 4 new serverless inference providers on the Hub 🤯
> Use your HF API key or personal key with all providers 🔑
> Chat with Deepseek R1, V3, and more on HF Hub 🐋
> We support Sambanova, TogetherAI, Replicate, and Fal.ai 💪
Best of all, we don't charge any markup on top of the provider 🫰 Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
Post
1948
Tried my hand at simplifying the derivations of Direct Preference Optimization.
I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.
Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo
I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.
Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo
Post
1889
Timm ❤️ Transformers
Wtih the latest version of transformers you can now use any timm model with the familiar transformers API.
Blog Post: https://huggingface.co/blog/timm-transformers
Repository with examples: https://github.com/ariG23498/timm-wrapper-examples
Collection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1
Wtih the latest version of transformers you can now use any timm model with the familiar transformers API.
Blog Post: https://huggingface.co/blog/timm-transformers
Repository with examples: https://github.com/ariG23498/timm-wrapper-examples
Collection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1
cfahlgren1
posted
an
update
28 days ago
Post
1751
Wow, I just added Langfuse tracing to the Deepseek Artifacts app and it's really nice 🔥
It allows me to visualize and track more things along with the cfahlgren1/react-code-instructions dataset.
It was just added as a one click Docker Space template, so it's super easy to self host 💪
It allows me to visualize and track more things along with the cfahlgren1/react-code-instructions dataset.
It was just added as a one click Docker Space template, so it's super easy to self host 💪
cfahlgren1
posted
an
update
about 1 month ago
Post
2242
You'll notice the AI in the SQL Console is much better at working with chatml conversations:
Here's example of unnesting the cfahlgren1/react-code-instructions in less than 10 seconds by asking it. Check it out here: cfahlgren1/react-code-instructions
- "show me the average assistant response length"
- "extract user, system, and assistant messages into separate columns"
It's super easy to work with conversational datasets now with natural language 🗣️
Here's example of unnesting the cfahlgren1/react-code-instructions in less than 10 seconds by asking it. Check it out here: cfahlgren1/react-code-instructions
- "show me the average assistant response length"
- "extract user, system, and assistant messages into separate columns"
It's super easy to work with conversational datasets now with natural language 🗣️
-
- 2 replies
cfahlgren1
posted
an
update
about 1 month ago
Post
3328
The
deepseek-ai/DeepSeek-V3 is very good! I have been playing with it and found it is really good at one-shotting a pretty good landing page.
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub 💪
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub 💪
Post
4754
VLMs are going through quite an open revolution AND on-device friendly sizes:
1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c
3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d
4. Microsoft w/ FlorenceVL - 3B & 8B: https://huggingface.co/jiuhai
5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/
What a time to be alive! 🔥
1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c
3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d
4. Microsoft w/ FlorenceVL - 3B & 8B: https://huggingface.co/jiuhai
5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/
What a time to be alive! 🔥
Post
1409
We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2.
google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
merve/paligemma2-vqav2
google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
merve/paligemma2-vqav2
cfahlgren1
posted
an
update
2 months ago
Post
1937
You can just ask things 🗣️
"show me messages in the coding category that are in the top 10% of reward model scores"
Download really high quality instructions from the Llama3.1 405B synthetic dataset 🔥
argilla/magpie-ultra-v1.0
"show me messages in the coding category that are in the top 10% of reward model scores"
Download really high quality instructions from the Llama3.1 405B synthetic dataset 🔥
argilla/magpie-ultra-v1.0
cfahlgren1
posted
an
update
2 months ago
Post
3028
We just dropped an LLM inside the SQL Console 🤯
The amazing, new Qwen/Qwen2.5-Coder-32B-Instruct model can now write SQL for any Hugging Face dataset ✨
It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think 🤗
The amazing, new Qwen/Qwen2.5-Coder-32B-Instruct model can now write SQL for any Hugging Face dataset ✨
It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think 🤗
Post
4572
Massive week for Open AI/ ML:
Mistral Pixtral & Instruct Large - ~123B, 128K context, multilingual, json + function calling & open weights
mistralai/Pixtral-Large-Instruct-2411
mistralai/Mistral-Large-Instruct-2411
Allen AI Tülu 70B & 8B - competive with claude 3.5 haiku, beats all major open models like llama 3.1 70B, qwen 2.5 and nemotron
allenai/tulu-3-models-673b8e0dc3512e30e7dc54f5
allenai/tulu-3-datasets-673b8df14442393f7213f372
Llava o1 - vlm capable of spontaneous, systematic reasoning, similar to GPT-o1, 11B model outperforms gemini-1.5-pro, gpt-4o-mini, and llama-3.2-90B-vision
Xkev/Llama-3.2V-11B-cot
Black Forest Labs Flux.1 tools - four new state of the art model checkpoints & 2 adapters for fill, depth, canny & redux, open weights
reach-vb/black-forest-labs-flux1-6743847bde9997dd26609817
Jina AI Jina CLIP v2 - general purpose multilingual and multimodal (text & image) embedding model, 900M params, 512 x 512 resolution, matroyoshka representations (1024 to 64)
jinaai/jina-clip-v2
Apple AIM v2 & CoreML MobileCLIP - large scale vision encoders outperform CLIP and SigLIP. CoreML optimised MobileCLIP models
apple/aimv2-6720fe1558d94c7805f7688c
apple/coreml-mobileclip
A lot more got released like, OpenScholar (https://huggingface.co/collections/OpenScholar/openscholar-v1-67376a89f6a80f448da411a6), smoltalk ( HuggingFaceTB/smoltalk), Hymba ( nvidia/hymba-673c35516c12c4b98b5e845f), Open ASR Leaderboard ( hf-audio/open_asr_leaderboard) and much more..
Can't wait for the next week! 🤗
Mistral Pixtral & Instruct Large - ~123B, 128K context, multilingual, json + function calling & open weights
mistralai/Pixtral-Large-Instruct-2411
mistralai/Mistral-Large-Instruct-2411
Allen AI Tülu 70B & 8B - competive with claude 3.5 haiku, beats all major open models like llama 3.1 70B, qwen 2.5 and nemotron
allenai/tulu-3-models-673b8e0dc3512e30e7dc54f5
allenai/tulu-3-datasets-673b8df14442393f7213f372
Llava o1 - vlm capable of spontaneous, systematic reasoning, similar to GPT-o1, 11B model outperforms gemini-1.5-pro, gpt-4o-mini, and llama-3.2-90B-vision
Xkev/Llama-3.2V-11B-cot
Black Forest Labs Flux.1 tools - four new state of the art model checkpoints & 2 adapters for fill, depth, canny & redux, open weights
reach-vb/black-forest-labs-flux1-6743847bde9997dd26609817
Jina AI Jina CLIP v2 - general purpose multilingual and multimodal (text & image) embedding model, 900M params, 512 x 512 resolution, matroyoshka representations (1024 to 64)
jinaai/jina-clip-v2
Apple AIM v2 & CoreML MobileCLIP - large scale vision encoders outperform CLIP and SigLIP. CoreML optimised MobileCLIP models
apple/aimv2-6720fe1558d94c7805f7688c
apple/coreml-mobileclip
A lot more got released like, OpenScholar (https://huggingface.co/collections/OpenScholar/openscholar-v1-67376a89f6a80f448da411a6), smoltalk ( HuggingFaceTB/smoltalk), Hymba ( nvidia/hymba-673c35516c12c4b98b5e845f), Open ASR Leaderboard ( hf-audio/open_asr_leaderboard) and much more..
Can't wait for the next week! 🤗
cfahlgren1
posted
an
update
3 months ago
Post
923
observers 🔭 - automatically log all OpenAI compatible requests to a dataset💽
• supports any OpenAI compatible endpoint 💪
• supports DuckDB, Hugging Face Datasets, and Argilla as stores
> pip install observers
No complex framework. Just a few lines of code to start sending your traces somewhere. Let us know what you think! @davidberenstein1957 and I will continue iterating!
Here's an example dataset that was logged to Hugging Face from Ollama: cfahlgren1/llama-3.1-awesome-chatgpt-prompts
• supports any OpenAI compatible endpoint 💪
• supports DuckDB, Hugging Face Datasets, and Argilla as stores
> pip install observers
No complex framework. Just a few lines of code to start sending your traces somewhere. Let us know what you think! @davidberenstein1957 and I will continue iterating!
Here's an example dataset that was logged to Hugging Face from Ollama: cfahlgren1/llama-3.1-awesome-chatgpt-prompts
cfahlgren1
posted
an
update
3 months ago
Post
878
You can create charts, leaderboards, and filters on top of any Hugging Face dataset in less than a minute
• ASCII Bar Charts 📊
• Powered by DuckDB WASM ⚡
• Download results to Parquet 💽
• Embed and Share results with friends 📬
Do you have any interesting queries?
• ASCII Bar Charts 📊
• Powered by DuckDB WASM ⚡
• Download results to Parquet 💽
• Embed and Share results with friends 📬
Do you have any interesting queries?
cfahlgren1
posted
an
update
3 months ago
Post
751
What rank are you on Hugging Face Top Yappers? 🗣️
Find your rank here with this link: cfahlgren1/hub-stats
The Top 3:
- @fdaudens
- @singhsidhukuldeep
- @akhaliq
I am at #71 and need to get my numbers up! 📈
Find your rank here with this link: cfahlgren1/hub-stats
The Top 3:
- @fdaudens
- @singhsidhukuldeep
- @akhaliq
I am at #71 and need to get my numbers up! 📈
-
- 4 replies
cfahlgren1
posted
an
update
3 months ago
Post
3171
You can clean and format datasets entirely in the browser with a few lines of SQL.
In this post, I replicate the process @mlabonne used to clean the new microsoft/orca-agentinstruct-1M-v1 dataset.
The cleaning process consists of:
- Joining the separate splits together / add split column
- Converting string messages into list of structs
- Removing empty system prompts
https://huggingface.co/blog/cfahlgren1/the-beginners-guide-to-cleaning-a-dataset
Here's his new cleaned dataset: mlabonne/orca-agentinstruct-1M-v1-cleaned
In this post, I replicate the process @mlabonne used to clean the new microsoft/orca-agentinstruct-1M-v1 dataset.
The cleaning process consists of:
- Joining the separate splits together / add split column
- Converting string messages into list of structs
- Removing empty system prompts
https://huggingface.co/blog/cfahlgren1/the-beginners-guide-to-cleaning-a-dataset
Here's his new cleaned dataset: mlabonne/orca-agentinstruct-1M-v1-cleaned
- 1 reply
Post
4424
What a brilliant week for Open Source AI!
Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17%
microsoft/llm2clip-672323a266173cfa40b32d4c
Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents
Nexusflow/athene-v2-6735b85e505981a794fb02cc
Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed
microsoft/orca-agentinstruct-1M-v1
Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder
reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71
JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow
deepseek-ai/JanusFlow-1.3B
Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens!
PleIAs/common_corpus
I'm sure I missed a lot, can't wait for the next week!
Put down in comments what I missed! 🤗
Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17%
microsoft/llm2clip-672323a266173cfa40b32d4c
Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents
Nexusflow/athene-v2-6735b85e505981a794fb02cc
Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed
microsoft/orca-agentinstruct-1M-v1
Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder
reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71
JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow
deepseek-ai/JanusFlow-1.3B
Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens!
PleIAs/common_corpus
I'm sure I missed a lot, can't wait for the next week!
Put down in comments what I missed! 🤗
cfahlgren1
posted
an
update
3 months ago
Post
2241
Why use Google Drive when you can have:
• Free storage with generous limits🆓
• Dataset Viewer (Sorting, Filtering, FTS) 🔍
• Third Party Library Support
• SQL Console 🟧
• Security 🔒
• Community, Reach, and Visibility 📈
It's a no brainer!
Check out our post on what you get instantly out of the box when you create a dataset.
https://huggingface.co/blog/researcher-dataset-sharing
• Free storage with generous limits🆓
• Dataset Viewer (Sorting, Filtering, FTS) 🔍
• Third Party Library Support
• SQL Console 🟧
• Security 🔒
• Community, Reach, and Visibility 📈
It's a no brainer!
Check out our post on what you get instantly out of the box when you create a dataset.
https://huggingface.co/blog/researcher-dataset-sharing
- 1 reply