Instructions to use imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout", max_seq_length=2048, )
Qwen3-4B SWE-Gym Hard-Anchor Process-Local Epsilon Adapter
This repository contains the best_holdout PEFT LoRA adapter from the Qwen3 SWE-Gym patch-repair investigation.
This checkpoint is not a general instruction model. It is an experimental adapter for search/replace patch generation on the held-out SWE-Gym style code-repair harness used in the project.
Base Model
- Base:
unsloth/Qwen3-4B-Instruct-2507 - Adapter type: LoRA
- PEFT version recorded in config:
0.19.1 - Local source checkpoint:
/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260606_123149_swegym_q4b-kl02-sft20k-hardanchor-processlocal-eps-v1-lr5e7_9a576cd/checkpoints/best_holdout
Training Context
This adapter started from the 4B hard-multi frontier adapter and received a tiny process-local SFT epsilon update while preserving the hard-multi anchor rows.
Run details:
- Run tag:
20260606_123149_swegym_q4b-kl02-sft20k-hardanchor-processlocal-eps-v1-lr5e7_9a576cd - Stage:
post_sft - Examples: 40
- Optimizer steps: 20
- Learning rate:
5e-7 - Built-in first-sample held-out pass@1:
7/35 - Built-in mean reward:
0.3497 - Built-in patch-applied rate:
0.6857
The interrupted seed9012 pass@8 validation did not complete, so this adapter should not be treated as a promoted replacement for the hard-multi frontier without a completed resample.
Loading
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_id = "unsloth/Qwen3-4B-Instruct-2507"
adapter_id = "imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout"
tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto", torch_dtype="auto")
model = PeftModel.from_pretrained(base, adapter_id)
Caveats
This is an experimental research checkpoint. The training and evaluation setup used a specific retrieval and search/replace editing contract. Results are not directly comparable to general coding benchmarks without reproducing that harness.
- Downloads last month
- -
Model tree for imdatta0/qwen3-4b-swegym-hardanchor-processlocal-eps-v1-best-holdout
Base model
Qwen/Qwen3-4B-Instruct-2507