kavirubc

weave-ccwm-qwen2.5-coder-7b-ablation-1step-traj

README

License: apache-2.0

What this model does

Given a concurrent Go program and a partial execution trace (goroutine scheduler events), predict the next scheduler event:

text

Input:  Go program source + partial trace (GoStart, GoBlock, GoUnblock, GoCreate, GoEnd, GoSched events)Output: {"event_type": "GoBlock", "goroutine_id": 3, "reasoning": "...", "confidence": "high"}

Training

Table with columns: Setting, Value
Setting	Value
Base model	`Qwen/Qwen2.5-Coder-7B-Instruct`
Method	Unsloth + QLoRA
Dataset	kavirubc/weave-bench

Results (Phase 13)

Table with columns: Model, Accuracy, Notes
Model	Accuracy	Notes
Qwen2.5-Coder-7B fine-tuned (this model)	36.2%	Phase 13 on GoKer held-out set
Qwen2.5-Coder-1.5B fine-tuned	40.2%	Phase 12 (in-distribution evaluation)

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base = AutoModelForCausalLM.from_pretrained(    "Qwen/Qwen2.5-Coder-7B-Instruct",    torch_dtype=torch.bfloat16,    device_map="auto",)model = PeftModel.from_pretrained(base, "kavirubc/weave-ccwm-qwen2.5-coder-7b-lora")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-7B-Instruct")

Or use the eval script from the repo:

bash

uv run python scripts/run_eval_unsloth.py \    --adapter kavirubc/weave-ccwm-qwen2.5-coder-7b-lora \    --val_file dataset/output/kaggle_upload/val_point_dups.jsonl

Citation

bibtex

@misc{weave2026,  author = {Hapuarachchi, Kaviru},  title  = {Weave: Concurrent Code World Models},  year   = {2026},  url    = {https://github.com/kaviru2/Weave}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

kavirubc

Model Tree

Base

Qwen/Qwen2.5-Coder-7B-Instruct

Adapter

this model

Input Modalities

Text

Output Modalities