slimfrikha commited on
Commit
663f8eb
·
verified ·
1 Parent(s): 9c22083

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -1,22 +1,24 @@
1
  ---
2
- library_name: transformers
 
3
  language:
4
  - en
5
- tags:
6
- - falcon-h1r
7
  license: other
8
  license_name: falcon-llm-license
9
  license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
10
- base_model:
11
- - tiiuae/Falcon-H1-7B-Base
12
  ---
13
 
14
  <img src="https://huggingface.co/datasets/tiiuae/reasoning-images/resolve/main/falcon-h1r-logo.png" alt="drawing" width="800"/>
15
 
16
  # Falcon-H1R-7B
17
 
18
- This repository presents **Falcon-H1R-7B**, a reasoning-specialized model built on top of [Falcon-H1-7B-Base](https://huggingface.co/tiiuae/Falcon-H1-7B-Base) and trained via cold-start supervised fine-tuning with
19
- long reasoning traces and further enhanced by scaling RL with GRPO. The model demonstrates outstanding performance across various benchmark evaluations, including mathematics, programming, instruction following, and general logic.
 
20
 
21
  ## Model Description
22
 
@@ -428,7 +430,7 @@ TTS represents test time scaling results on few of the benchmarks that we evalua
428
  # Useful links
429
 
430
  - View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1r-7b).
431
- - View [our technical report](https://arxiv.org/abs/2601.02346).
432
  - Feel free to join [our discord server](https://discord.gg/Cbek57PrZE) if you have any questions or to interact with our researchers and developers.
433
 
434
  # Citation
 
1
  ---
2
+ base_model:
3
+ - tiiuae/Falcon-H1-7B-Base
4
  language:
5
  - en
6
+ library_name: transformers
7
+ pipeline_tag: text-generation
8
  license: other
9
  license_name: falcon-llm-license
10
  license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
11
+ tags:
12
+ - falcon-h1r
13
  ---
14
 
15
  <img src="https://huggingface.co/datasets/tiiuae/reasoning-images/resolve/main/falcon-h1r-logo.png" alt="drawing" width="800"/>
16
 
17
  # Falcon-H1R-7B
18
 
19
+ This repository presents **Falcon-H1R-7B**, a reasoning-specialized model introduced in the paper [Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling](https://huggingface.co/papers/2601.02346).
20
+
21
+ Built on top of [Falcon-H1-7B-Base](https://huggingface.co/tiiuae/Falcon-H1-7B-Base), it was trained via cold-start supervised fine-tuning with long reasoning traces and further enhanced by scaling RL with GRPO. The model demonstrates outstanding performance across various benchmark evaluations, including mathematics, programming, instruction following, and general logic.
22
 
23
  ## Model Description
24
 
 
430
  # Useful links
431
 
432
  - View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1r-7b).
433
+ - View [our technical report](https://huggingface.co/papers/2601.02346).
434
  - Feel free to join [our discord server](https://discord.gg/Cbek57PrZE) if you have any questions or to interact with our researchers and developers.
435
 
436
  # Citation