HF中国镜像站 Party @ PyTorch Conference

community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Skylion007 authored a paper about 4 hours ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

sarahooker authored a paper about 2 months ago

Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress

sarahooker authored a paper about 2 months ago

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning

View all activity

HF-Party's activity

julien-c

posted an update 3 days ago

Post

2115

Important notice 🚨

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference – with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.

danielhanchen

posted an update about 2 months ago

Post

2885

I uploaded DeepSeek R1 GGUFs!

unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF
2bit for MoE: unsloth/DeepSeek-R1-GGUF
unsloth/DeepSeek-R1-Zero-GGUF

More at unsloth/deepseek-r1-all-versions-678e1c48f5d2fce87892ace5

danielhanchen

posted an update 2 months ago

Post

4672

We fixed many bugs in Phi-4 & uploaded fixed GGUF + 4-bit versions! ✨

Our fixed versions are even higher on the Open LLM Leaderboard than Microsoft's!

GGUFs: unsloth/phi-4-GGUF
Dynamic 4-bit: unsloth/phi-4-unsloth-bnb-4bit

You can also now finetune Phi-4 for free on Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb

Read our blogpost for more details on bug fixes etc: https://unsloth.ai/blog/phi4

danielhanchen

posted an update 2 months ago

Post

3171

Deepseek V3, including GGUF + bf16 versions are now uploaded!

Includes 2, 3, 4, 5, 6 and 8-bit quantized versions.

GGUFs: unsloth/DeepSeek-V3-GGUF
bf16: unsloth/DeepSeek-V3-bf16

Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit.

See how to run them with examples and the full collection: unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c

Johannes

authored a paper 2 months ago

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring

Paper • 2501.02045 • Published Jan 3 • 21

Jackmin108

authored 2 papers 2 months ago

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

Paper • 2407.07852 • Published Jul 10, 2024

INTELLECT-1 Technical Report

Paper • 2412.01152 • Published Dec 2, 2024 • 1

julien-c

posted an update 3 months ago

Post

10350

After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

danielhanchen

posted an update 3 months ago

Post

1548

I uploaded GGUFs, 4bit bitsandbytes and full 16bit precision weights for Llama 3.3 70B Instruct are here: unsloth/llama-33-all-versions-67535d7d994794b9d7cf5e9f

You can also finetune Llama 3.3 70B in under 48GB of VRAM with Unsloth!
GGUFs: unsloth/Llama-3.3-70B-Instruct-GGUF
BnB 4bit: unsloth/Llama-3.3-70B-Instruct-bnb-4bit
16bit: unsloth/Llama-3.3-70B-Instruct

1 reply

Siddartha10

authored a paper 3 months ago

1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs

Paper • 2411.06850 • Published Nov 11, 2024 • 4

julien-c

posted an update 3 months ago

Post

3197

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

samsja

authored a paper 4 months ago

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

Paper • 2407.07852 • Published Jul 10, 2024

danielhanchen

posted an update 4 months ago

Post

1436

Vision finetuning is in 🦥Unsloth! You can now finetune Llama 3.2, Qwen2 VL, Pixtral and all Llava variants up to 2x faster and with up to 70% less VRAM usage! Colab to finetune Llama 3.2: https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing

1 reply

ArthurZ

posted an update 4 months ago

Post

3504

Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!

Contributions are welcome to support more models! 🔥