Text Generation
PEFT
Safetensors
English
lora
grpo
chain-of-thought
reasoning
compression
gsm8k
conversational
Eval Results (legacy)
Instructions to use ssurface/cot-dialect-olmo3-7b-think-grpo-reward-diff-l5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ssurface/cot-dialect-olmo3-7b-think-grpo-reward-diff-l5 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("merged_olmo/l5") model = PeftModel.from_pretrained(base_model, "ssurface/cot-dialect-olmo3-7b-think-grpo-reward-diff-l5") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload training_config.json with huggingface_hub
Verified signature10fb495 -
Upload training_log.jsonl with huggingface_hub
Verified signature69b2632 -
Upload README.md with huggingface_hub
Verified signature79d87c2 -
Upload chat_template.jinja with huggingface_hub
Verified signature0237c8c -
Upload tokenizer_config.json with huggingface_hub
Verified signaturef4db72a -
Upload tokenizer.json with huggingface_hub
Verified signature8109c43 -
Upload adapter_config.json with huggingface_hub
Verified signature708f32d -
Upload adapter_model.safetensors with huggingface_hub
Verified signature6ecf7c3 -
initial commit
Verified signature2348761