2.2 KiB
base_model, datasets, language, license, library_name, pipeline_tag, tags
| base_model | datasets | language | license | library_name | pipeline_tag | tags | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-4B-Instruct-2507 |
|
|
apache-2.0 | transformers | text-generation |
|
Qwen3-4B-Agent-ALFWorld-Specialist
This repository provides a merged full-parameter model (bfloat16) fine-tuned from Qwen/Qwen3-4B-Instruct-2507.
Instead of a standalone LoRA adapter, this model has been created by merging LoRA weights back into the base model using Unsloth's merge_and_unload method. This ensures high-speed inference and easy deployment.
Training Objective
This model is specialized for ALFWorld trajectory tasks, trained to handle multi-turn environment observations and action selections.
Training Configuration
- Base model: Qwen/Qwen3-4B-Instruct-2507
- Format: Merged Full Weights (bfloat16)
- Method: LoRA fine-tuning (Merged via Unsloth
merge_and_unload) - Max sequence length: 4096
- Steps: 600
- Learning rate: 5e-07
- LoRA Parameters during training: r=64, alpha=128
- Platform: Trained with Unsloth
Usage
Since this is a merged model, you can load it directly like any other Qwen3 model:
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "moushi21/agent-bench-alfworld-merged3"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
Sources & Terms (IMPORTANT)
Training data:
- u-10bei/sft_alfworld_trajectory_dataset
- u-10bei/sft_alfworld_trajectory_dataset_v2
- u-10bei/sft_alfworld_trajectory_dataset_v3
- u-10bei/sft_alfworld_trajectory_dataset_v4
- u-10bei/sft_alfworld_trajectory_dataset_v5
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.