Downloads · 30 days
0
kuririrn/qwen3-4b-agent-trajectory-SFT_alfadm-prmcons_alformat3
qwen3-4b-agent-trajectory-SFT_alfadm-prmcons_alformat3 is a text generation model from kuririrn. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth.
Downloads · 30 days
0
Access
Public
Updated Feb 26, 2026
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth.
This repository contains LoRA adapter weights only. The base model must be loaded separately.
This adapter is trained on a single trajectory-style SFT dataset:
THOUGHT: / ACTION: style reasoning traces.This adapter is trained to improve multi-turn agent task performance on ALFWorld (household tasks).
Loss is applied to all assistant turns in the trajectory, so the model learns environment observation, action selection, tool use, and recovery from errors in ALFWorld.
In addition, user prompts are augmented to:
Your goal: ...),Previous Action: ...),Previous Result: ... when applicable),task succeeded outputs before the goal is reached.For ALFWorld trajectories, user messages that already contain an admissible actions/commands list are augmented during training with an additional constraint prompt:
[Important Instruction]
You must choose exactly one action from the admissible commands list.
Do not generate any action that is not explicitly included in that list.
The action you output must exactly match one item in the
admissible commands list.
## Intended Use
This adapter is intended to be used as a tool-using agent
for ALFWorld and/or DBBench-style tasks, depending on the
training configuration:
- When trained only on ALFWorld, it focuses on household tasks.
- When trained only on DBBench, it focuses on database operations.
- When trained on both, it aims to balance both domains.
## How to Load
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen3-4B-Instruct-2507",
torch_dtype="auto",
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(
base_model,
"/content/lora_agentbench_qwen3_4b",
)
model.eval()
## Limitations and Bias
This adapter is trained on synthetic and task-specific trajectories
for ALFWorld and/or DBBench. It may:
- Overfit to the style of prompts and environments in these datasets.
- Hallucinate actions or SQL queries outside the training distribution.
- Fail on tasks that are very different from ALFWorld/DBBench.
Always validate the model's outputs, especially when using it for
real-world decision making or database operations.