swesmith_8b_rope_65k-step37

RL-trained Qwen3-8B on SWEsmith tasks (65k context with YaRN rope, 37 steps, LR=2e-5, Dr.GRPO with sequence_mean loss, eps_clip_high=0.28).

Training Details

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("laion/swesmith_8b_rope_65k-step37")
tokenizer = AutoTokenizer.from_pretrained("laion/swesmith_8b_rope_65k-step37")
Downloads last month
25
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for laion/swesmith_8b_rope_65k-step37

Finetuned
Qwen/Qwen3-8B
Finetuned
(2)
this model