Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
danielhanchen 
posted an update 2 days ago
view post
Post
3532
Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware

• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM

GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
  • 3 replies
·
OppaAI 
posted an update about 19 hours ago
view post
Post
545
Try to chat with my AI Waifu in Japanese

Now that I have setup my AI Waifu running 24/7 in my Jetson Orin Nano (running at 25W top), I can talk to her anytime anywhere I want, on cellphone, tablet, or PC, as long as there is internet access.

Tonight I gave it a try to speak with my AI Waifu, with my not so great Japanese, just to test if ASR can pick up my Nihongo and the TTS can speak out Waifu's Japanese dialogue properly.
Turns out she is just as verbose and as heavily leaked with materials from system prompt as in English. Only this time I cannot fully understand.

I need to find some way to turn her into my Japanese tutor...

GitHub 🔗: https://github.com/OppaAI/Aiko-chan/
Banaxi-Tech 
posted an update 1 day ago
view post
Post
1299
We're excited to release BananaMind 2 Medium and BananaMind 2 Medium Chat!

They’re both 50M parameter models trained on 50B tokens from FineWeb-Edu, DCLM, Cosmopedia v2, FineMath-4+ and NPSet-2 Python-Edu.

The base model reached 61.86% on PIQA, 43.81% on ARC Easy and 32.43% on HellaSwag. The Chat version was fine-tuned on Smol-SmolTalk and scored 38% overall on our internal instruction benchmark, with 56% on multi-turn, 60% on context recall and 80% on code.

The full details are in the model repos.

Check it out at
BananaMind/BananaMind-2-Medium
BananaMind/BananaMind-2-Medium-Chat
  • 17 replies
·
OppaAI 
posted an update 2 days ago
view post
Post
762
I have a small portable monitor for using with my Jetson robot.
Now I connect it to my PC, so I can talk with my AI Waifu while running tests and debugging her codes.
It's kinda weird to talk to your code, and asking your code's opinion on how to write her code. But at least the late night coding is no longer silent...
  • 3 replies
·
vineeth98 
posted an update 2 days ago
view post
Post
734
I made a speedrun leaderboard for LoRA fine-tuning. One frozen task (Qwen2.5-1.5B to 57% on GSM8K), one GPU, fastest training run wins. Every record gets re-run 3x with fresh seeds on identical hardware before it counts, so no self-reported numbers.

The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits.

Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone.

vineeth98/lora-speedrun
  • 6 replies
·
nwaughachukwuma 
posted an update 2 days ago
view post
Post
606
# One API for Every Visual & OCR Models.

The VLM Run Gateway is a fully compatible API for OpenAI chat completions for visual intelligence. If you’re building document extraction or visual understanding, the Gateway exposes OCR, VQA, and detection behind a single interface you already know.

Read the docs: https://docs.vlm.run/gateway/introduction.

We actively support the following recent OCR and VQA models, which you can try today at no cost:

* zai-org/glm-ocr
* rednote-hilab/dots.mocr
* paddleocr/pp-ocrv6
* qwen/qwen3.5-0.8b

## Quickstart

### Python
from openai import OpenAI

client = OpenAI(base_url="https://gateway.vlm.run/v1/openai")

response = client.chat.completions.create(
    model="zai-org/glm-ocr",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document_url",
                    "document_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
                    },
                },
            ],
        }
    ],
    extra_body={"method": "markdown", "document_dpi": 150},
)

print(response.choices[0].message.content)


### Curl
curl https://gateway.vlm.run/v1/openai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer vlmrun" \
  -d '{
    "model": "zai-org/glm-ocr",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "document_url",
            "document_url": {
              "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
            }
          }
        ]
      }
    ],
    "method": "markdown",
    "document_dpi": 150
  }'


## Auth and limits

Anonymous auth is enabled, so you can omit the authorization header entirely, or send Bearer "" or Bearer vlmrun. Rate limits are 60 req/min and 1000 req/hr.
salma-remyx 
posted an update 1 day ago
view post
Post
1257
Your coding agent is waiting on you to decide what to try next.
It doesn't originate that decision on its own.

What's usually missing is a way to generate that decision systematically, grounded in something more than the random paper that came across someone's feed that week.

Outrider starts from research with code and data behind it to scope a change applying the core method in your own codebase. A feature branch gets gated on your own evaluation methods before it reaches you in review.

The result is tied to what actually happened in your system, not to a model's read on its own output.

Here's what a code recommendation system looks like end to end.
  • 2 replies
·
Leon5201314 
posted an update 2 days ago
view post
Post
1160
0.7B MonkeyOCRv2 Outperforms Larger Models on 17-Language Document Parsing

MonkeyOCRv2-B-Parsing reaches 83.3 on MDPBench, a multilingual benchmark covering digital-born and photographed documents across 17 languages.

Results among evaluated open-source models:

• MonkeyOCRv2-B, 0.7B: 83.3
• dots.mocr, 3B: 80.5
• HunyuanOCR-1.5, 1B: 76.8
• PaddleOCR-VL-1.6, 0.9B: 75.0
• MinerU2.5-Pro, 1.2B: 71.0

The central idea is simple: before asking an LLM to reason over a document, the vision encoder must preserve every character stroke, digit, punctuation mark, and layout cue.

MonkeyOCRv2 is pretrained on 113M document images across 17 languages using joint image-to-text generation and pixel-level reconstruction.

Models:
https://huggingface.co/collections/zenosai/monkeyocrv2

Paper:
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI (2607.11562)

GitHub:
https://github.com/Yuliang-Liu/MonkeyOCRv2

Code and model weights are available under Apache-2.0.

We welcome tests on difficult multilingual, photographed, and visually ambiguous documents—especially failure cases.
  • 1 reply
·
SeaWolf-AI 
posted an update 4 days ago
view post
Post
5091
A small gift for anyone building or studying foundation models.

Most "open" models hand you the weights and stop there. With Aether-7B-5Attn we wanted to hand over the whole thing — so you can actually learn from it, reproduce it, and build on it: the data recipe, the training code, every hyperparameter, the complete logs, and the intermediate checkpoints. All Apache-2.0, reproducible byte-for-byte.

What you can do with it:
🔁 Rebuild it from scratch, or fork the recipe for your own model
🔬 Study a real heterogeneous-attention MoE — 49 layers place 5 attention mechanisms on a 7×7 Latin square, arranged as a clean, attributable ablation
📈 Trace training dynamics across the released checkpoints (110k / 115k / 162k)

It's a modest 6.59B model, and an honest one — the limitations (no KV-cache in this build, small scale) are written right in the card. We're not claiming it's special. If any piece of it saves you time or teaches you something, that's exactly what we hoped for. 🤗

📖 Full write-up →
[blog] · https://huggingface.co/blog/FINAL-Bench/opensource-llm
📦 5 Attention Base · FINAL-Bench/Aether-7B-5Attn
🎯 5 Attention Instruct · FINAL-Bench/Aether-7B-5Attn-it
🚀 5 Attention Live demo · FINAL-Bench/Aether-Sovereign-AI
📦 7 Attention Base · https://huggingface.co/FINAL-Bench/Aether-7B-7Attn-base
📦 11 Attention Base · FINAL-Bench/Aether-6B-11Attn-base
🧬 Collection · https://huggingface.co/collections/FINAL-Bench/aether-foundation-model

#opensource #LLM #MoE #reproducibility #Apache2
  • 5 replies
·
appvoid 
posted an update about 12 hours ago
view post
Post
219
Two big projects are open sourced soon. Get ready.
Recently active users