Etherll/Qwen2.5-CodeFIM-1.5B-v2
Text Generation
•
Updated
•
34
•
3
ll PRO
Etherll
AI & ML interests
None yet
Recent Activity
liked
a model
5 days ago
open-r1/OlympicCoder-7B
liked
a Space
26 days ago
Reality123b/XylariaDeepReason
reacted
to
s-emanuilov's
post
with 🔥
about 1 month ago
Tutorial 💥 Training a non-English reasoning model with GRPO and Unsloth
I wanted to share my experiment with training reasoning models in languages other than English/Chinese.
Using Llama 3.1 8B as base, GRPO trainer from trl, and Unsloth optimizations, I got a working prototype in Bulgarian after ~5 hours on an L40S GPU. The approach should work for any language where the base model has some pre-training coverage.
Full code and tutorial here: https://unfoldai.com/reasoning-in-a-non-english-language/
The model itself: https://huggingface.co/s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1
I hope this helps anyone looking to build reasoning models in their language.
Organizations
models
24
Etherll/Qwen2.5-CodeFIM-1.5B-v2-Q8_0-GGUF
Updated
•
6
Etherll/Qwen2.5-7B-della-test
Text Generation
•
Updated
•
49
•
1
Etherll/SuperHermes
Text Generation
•
Updated
•
7
•
1
Etherll/Herplete-LLM-Llama-3.1-8b-Ties-Q5_K_M-GGUF
Updated
•
9
Etherll/Qwen2.5-Coder-1.5B-CodeFIM
Text Generation
•
Updated
•
52
•
3
Etherll/Qwen2.5-Coder-1.5B-CodeFIM-Q8_0-GGUF
Updated
•
2
Etherll/Herplete-LLM-Llama-3.1-8b-Ties
Text Generation
•
Updated
•
6
Etherll/Qwen2.5-Coder-7B-Instruct-Ties
Text Generation
•
Updated
•
12
•
1
Etherll/Qwen2.5-14b-web-Q6_K-GGUF
Updated
•
5
•
1
datasets
7
Etherll/code-fim-v2
Viewer
•
Updated
•
64k
•
73
•
3
Etherll/python-code-infill-test
Viewer
•
Updated
•
25.5k
•
57
Etherll/jokes
Viewer
•
Updated
•
244
•
11
•
3
Etherll/GatedLinearAttention_Transformers_Q_and_A
Viewer
•
Updated
•
149
•
28
•
1
Etherll/code-FIM-test4
Viewer
•
Updated
•
69.5k
•
53
Etherll/lady_nagant_v2
Updated
•
2
Etherll/lady_nagant
Updated
•
1