Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Paper โข 2606.29331 โข Published
AI & ML interests
Building interactive demos to scikit-learn examples ๐งก
Recent Activity
View all activity
suayptalhaย
authored a
paper 29 days ago
pankajpandey-devย
posted an update about 1 month ago
Post
4120
๐ฎ๐ณ Qwen3.5-9B Hindi Instruct โ it stops thinking in English
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
- 4 replies
pankajpandey-devย
posted an update about 1 month ago
Post
7838
๐ฎ๐ณ New in my Hindi LLM Series: Gemma-4 E4B, fine-tuned for Hindi โ and it runs on your laptop's CPU.
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting ๐
โ My fine-tune is more concise โ ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
โ Pure native Hindi โ base keeps slipping into English ("เคธเคเคคเฅเคฒเคฟเคค เคเคนเคพเคฐ (Eat a Balanced Diet)", "เคคเคพเคฐเคพ (Star)"). My fine-tune stays in clean Hindi.
โ Tighter instruction-following โ ask for a "short message" and it gives one, not a menu of options.
โ๏ธ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model โ I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
๐ Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth ยท Data by @ai4bharat ๐
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting ๐
โ My fine-tune is more concise โ ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
โ Pure native Hindi โ base keeps slipping into English ("เคธเคเคคเฅเคฒเคฟเคค เคเคนเคพเคฐ (Eat a Balanced Diet)", "เคคเคพเคฐเคพ (Star)"). My fine-tune stays in clean Hindi.
โ Tighter instruction-following โ ask for a "short message" and it gives one, not a menu of options.
โ๏ธ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model โ I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
๐ Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth ยท Data by @ai4bharat ๐
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
- 12 replies
eienmojikiย
posted an update about 1 month ago
Post
229
Hi everyone,
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
pankajpandey-devย
posted an update about 2 months ago
Post
920
๐ฎ๐ณ Gemma-3-1B Hindi Instruct โ a Hindi LLM that runs fully offline, anywhere.
Last week I shipped Qwen3-4B Hindi. This week I went the other direction: how tiny can a useful Hindi model get? So I fine-tuned Gemma-3-1B on quality-filtered Hindi instruction data and shipped the full GGUF ladder.
โ Fine-tune (16-bit): pankajpandey-dev/gemma-3-1b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/gemma-3-1b-hindi-instruct-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 806 MB โ runs on CPU, a cheap laptop, even a Raspberry Pi.
What I tried this round: chrF-filtered the training data to drop weak translations, and used response-only loss so the model learns how to answer, not how to repeat prompts.
Honest note: at 1B, Hindi fluency is strong but coherence is bounded by size โ it's a lightweight/edge experiment, not a 4B replacement. Gemma-3-4B Hindi is next.
Part of my Hindi LLM Series โ openly-licensed Indic models for local & edge use. Feedback welcome ๐
#Hindi #IndicNLP #GGUF #LocalLLM #Gemma #EdgeAI
Last week I shipped Qwen3-4B Hindi. This week I went the other direction: how tiny can a useful Hindi model get? So I fine-tuned Gemma-3-1B on quality-filtered Hindi instruction data and shipped the full GGUF ladder.
โ Fine-tune (16-bit): pankajpandey-dev/gemma-3-1b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/gemma-3-1b-hindi-instruct-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 806 MB โ runs on CPU, a cheap laptop, even a Raspberry Pi.
What I tried this round: chrF-filtered the training data to drop weak translations, and used response-only loss so the model learns how to answer, not how to repeat prompts.
Honest note: at 1B, Hindi fluency is strong but coherence is bounded by size โ it's a lightweight/edge experiment, not a 4B replacement. Gemma-3-4B Hindi is next.
Part of my Hindi LLM Series โ openly-licensed Indic models for local & edge use. Feedback welcome ๐
#Hindi #IndicNLP #GGUF #LocalLLM #Gemma #EdgeAI
EduardoPachecoย
authored a
paper about 2 months ago
EduardoPachecoย
authored 2
papers 2 months ago
pankajpandey-devย
posted an update 2 months ago
Post
14995
๐ฎ๐ณ Qwen3-4B Hindi Instruct v2 โ a Hindi LLM that runs on your own machine
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi โ so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
โ Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
โ GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB โ fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series โ building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome ๐
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi โ so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
โ Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
โ GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB โ fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series โ building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome ๐
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
- 4 replies
pankajpandey-devย
posted an update 2 months ago
Post
698
๐ฎ๐ณ Just shipped: MiniCPM5-1B-Hindi-Instruct (+ GGUF quants)
First Hindi instruction-tuned fine-tune of OpenBMB's brand-new MiniCPM5-1B (released this week).
Trained with Unsloth + LoRA (r=32) on AI4Bharat's anudesh + dolly Hindi splits โ ~4k high-quality examples, 2 epochs on a single T4 in 60 minutes.
๐ Model (16-bit + LoRA adapter):
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct
๐ฆ GGUF quants for llama.cpp / Ollama / LM Studio:
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct-v1-GGUF
5 quant levels โ from Q3_K_M (~560 MB, runs on a Raspberry Pi) to Q8_0 (~1.2 GB, near-lossless). Q4_K_M is the recommended default.
Part of my ongoing ๐ฎ๐ณ Hindi LLM Series โ bringing strong open-source LLMs to Indian languages.
#Hindi #IndicNLP #MiniCPM5 #LoRA #Unsloth #GGUF #llamacpp #Ollama #LocalLLM
First Hindi instruction-tuned fine-tune of OpenBMB's brand-new MiniCPM5-1B (released this week).
Trained with Unsloth + LoRA (r=32) on AI4Bharat's anudesh + dolly Hindi splits โ ~4k high-quality examples, 2 epochs on a single T4 in 60 minutes.
๐ Model (16-bit + LoRA adapter):
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct
๐ฆ GGUF quants for llama.cpp / Ollama / LM Studio:
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct-v1-GGUF
5 quant levels โ from Q3_K_M (~560 MB, runs on a Raspberry Pi) to Q8_0 (~1.2 GB, near-lossless). Q4_K_M is the recommended default.
Part of my ongoing ๐ฎ๐ณ Hindi LLM Series โ bringing strong open-source LLMs to Indian languages.
#Hindi #IndicNLP #MiniCPM5 #LoRA #Unsloth #GGUF #llamacpp #Ollama #LocalLLM
pankajpandey-devย
posted an update 2 months ago
Post
2705
๐งฌ Just uploaded K-quants of Carbon-3B for llama.cpp users!
@HuggingFaceBio released the original GGUF in bf16 only โ so I added the full quant ladder for CPU/edge inference:
โข Q2_K โ 1.4 GB
โข Q3_K_M โ 1.8 GB
โข Q4_K_M โ 2.1 GB โญ
โข Q5_K_M โ 2.4 GB
โข Q6_K โ 2.7 GB
โข Q8_0 โ 3.5 GB
๐ pankajpandey-dev/Carbon-3B-GGUF
Now you can generate DNA sequences on your laptop. Needs a llama.cpp build with PR #23410 (HybridDNATokenizer support).
Huge thanks to the HuggingFaceBio team for the original model ๐
#GGUF #llamacpp #genomics #DNA
@HuggingFaceBio released the original GGUF in bf16 only โ so I added the full quant ladder for CPU/edge inference:
โข Q2_K โ 1.4 GB
โข Q3_K_M โ 1.8 GB
โข Q4_K_M โ 2.1 GB โญ
โข Q5_K_M โ 2.4 GB
โข Q6_K โ 2.7 GB
โข Q8_0 โ 3.5 GB
๐ pankajpandey-dev/Carbon-3B-GGUF
Now you can generate DNA sequences on your laptop. Needs a llama.cpp build with PR #23410 (HybridDNATokenizer support).
Huge thanks to the HuggingFaceBio team for the original model ๐
#GGUF #llamacpp #genomics #DNA
pankajpandey-devย
posted an update 2 months ago
Post
281
Just released Qwen3-0.6B fine-tuned on Hindi instruction data ๐ฎ๐ณ
โ Full model: pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1
โ GGUF versions (Q2/Q4/Q5/Q8): pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1-GGUF
Smallest Hindi-capable GGUF โ runs on any laptop at 0.37GB.
Next: v2 with more data, better responses.
#Hindi #LLM #GGUF #OpenSource
โ Full model: pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1
โ GGUF versions (Q2/Q4/Q5/Q8): pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1-GGUF
Smallest Hindi-capable GGUF โ runs on any laptop at 0.37GB.
Next: v2 with more data, better responses.
#Hindi #LLM #GGUF #OpenSource
Post
191
One prompt, three answers - which model is from where?
johko/llm-blind-date
I built a little demo where you give three models (Apertus, Llama, Qwen3) the same prompt and in the end you have to guess which is which just based on their answers.
GIve it a try! ;)
johko/llm-blind-date
I built a little demo where you give three models (Apertus, Llama, Qwen3) the same prompt and in the end you have to guess which is which just based on their answers.
GIve it a try! ;)
Post
3136
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
Aurelien-Morganย
posted an update 3 months ago
Post
1105
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
- 1 reply
Post
4398
๐๐ปโโ๏ธ Hey there folks,
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
- 2 replies
Post
3708
๐๐ปโโ๏ธ Hey there folks ,
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
suayptalhaย
authored a
paper 3 months ago
Q-bertย
authored a
paper 3 months ago
awinmlย
authored a
paper 4 months ago