dbands/Qwen2.5-Coder-14B-Instruct-reason-gguf
Updated
•
78
Gilbert Bands PRO
dbands
AI & ML interests
None yet
Recent Activity
updated
a dataset
39 minutes ago
dbands/train_me.csv
published
a dataset
40 minutes ago
dbands/train_me.csv
replied to
s-emanuilov's
post
2 days 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
83
dbands/Qwen2.5-Coder-14B-Instruct-reason
Text Generation
•
Updated
•
3
•
1
dbands/Qwen2.5-Coder-7B-Instruct-reason-gguf
Updated
•
70
dbands/Qwen2.5-Coder-7B-Instruct-reason
Text Generation
•
Updated
•
6
dbands/Qwen2.5-3B-Instruct-reason-gguf
Updated
•
74
dbands/Qwen2.5-3B-Instruct-reason
Text Generation
•
Updated
•
3
dbands/Qwen2-5-Coder-0-5B-neo4j-text2cypher-2024v1-GGUF
Updated
•
66
•
1
dbands/Qwen2-5-Coder-0-5B_neo4j-text2cypher-2024v1-16B
Text Generation
•
Updated
•
171
dbands/Qwen2.5-7B-Instruct-pyomo-pysim-coder-gguf
Updated
•
55
dbands/Qwen2.5-7B-Instruct-pyomo-pysim-coder
Text Generation
•
Updated
•
5
datasets
8
dbands/train_me.csv
Viewer
•
Updated
•
426
dbands/horseTrainer
Viewer
•
Updated
•
102
•
32
dbands/test-set
Viewer
•
Updated
•
10
•
53
dbands/ChemistryCoder
Viewer
•
Updated
•
10.7k
•
14
•
2
dbands/pythonMath
Viewer
•
Updated
•
5.77k
•
10
•
1
dbands/ScoredPythonInstruct
Viewer
•
Updated
•
35.1k
•
10
dbands/PotsAndPots
Viewer
•
Updated
•
2
•
40
•
1
dbands/story
Viewer
•
Updated
•
97
•
43