gi111f11cb7f354a74a8c123f5b155498e
/
Art-v0-3B
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Art-v0-3B
4 Commits 1 Branch 0 Tags 5.8 GiB
Go to file
xxl 6bb4db91f9 first commit 2025-01-23 14:55:09 +08:00
.gitattributes Add .gitattributes 2025-01-23 13:57:51 +08:00
LICENSE first commit 2025-01-23 14:30:47 +08:00
README.md first commit 2025-01-23 14:30:47 +08:00
added_tokens.json first commit 2025-01-23 14:30:47 +08:00
config.json first commit 2025-01-23 14:30:47 +08:00
generation_config.json first commit 2025-01-23 14:30:47 +08:00
merges.txt first commit 2025-01-23 14:30:47 +08:00
model-00001-of-00002.safetensors first commit 2025-01-23 14:55:09 +08:00
model-00002-of-00002.safetensors first commit 2025-01-23 14:55:09 +08:00
model.safetensors.index.json first commit 2025-01-23 14:30:47 +08:00
special_tokens_map.json first commit 2025-01-23 14:30:47 +08:00
tokenizer.json first commit 2025-01-23 14:30:47 +08:00
tokenizer_config.json first commit 2025-01-23 14:30:47 +08:00
vocab.json first commit 2025-01-23 14:30:47 +08:00

README.md

license
other

Auto Regressive Thinker (Art) v0 3B

Art v0 3B is our inaugural model in the Art series, fine-tuned from Qwen/Qwen2.5-3B-Instruct using a specialized dataset generated with Gemini 2.0 Flash Thinking. Read more about the Art series

Model Details

  • Base Model: Qwen2.5-3B-Instruct
  • Architecture: Transformer
  • Size: 3B parameters

Usage

The model incorporates a reasoning mechanism using specific tags:

<|start_reasoning|> model's reasoning process <|end_reasoning|> model's response

Recommendations

  • Use the model without quantization
  • Use the tokenizer chat template
  • Use a low temperature 0.1-0.3 and repetition_penalty of 1.1

Training Details

This experimental model was trained on a curated dataset generated using Gemini 2.0 Flash Thinking. Detailed training methodology, dataset, and code are available exclusively to our community members.

About Us

We are a community-funded AI research lab focused on advancing open-source AGI development. Our community members support us through Patreon donations.

Community Access

Our supporters get exclusive access to:

  • Training dataset
  • Training code and methodology
  • Behind-the-scenes development insights
  • Future model previews

Join Our Community