Instructions to use RinnRinnmini/qwen3-4b-agent-trajectory-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RinnRinnmini/qwen3-4b-agent-trajectory-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RinnRinnmini/qwen3-4b-agent-trajectory-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RinnRinnmini/qwen3-4b-agent-trajectory-lora")
model = AutoModelForCausalLM.from_pretrained("RinnRinnmini/qwen3-4b-agent-trajectory-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RinnRinnmini/qwen3-4b-agent-trajectory-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RinnRinnmini/qwen3-4b-agent-trajectory-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RinnRinnmini/qwen3-4b-agent-trajectory-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RinnRinnmini/qwen3-4b-agent-trajectory-lora

SGLang

How to use RinnRinnmini/qwen3-4b-agent-trajectory-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RinnRinnmini/qwen3-4b-agent-trajectory-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RinnRinnmini/qwen3-4b-agent-trajectory-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RinnRinnmini/qwen3-4b-agent-trajectory-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RinnRinnmini/qwen3-4b-agent-trajectory-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RinnRinnmini/qwen3-4b-agent-trajectory-lora with Docker Model Runner:
```
docker model run hf.co/RinnRinnmini/qwen3-4b-agent-trajectory-lora
```

qwen3-4b-agent-trajectory-merged

This repository provides a MERGED (fully materialized) model created by merging a LoRA adapter into the base model:

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: LoRA + Unsloth, then merge_and_unload() into full weights

✅ This repo contains the merged model weights.
You do NOT need PEFT / LoRA adapters at inference time.

Note: This is a derivative of the base model. Usage must comply with the base model's original terms.

What is included

Full merged model weights (the LoRA adapter is already merged)
Tokenizer / config files needed for inference

Training Objective

This model is trained to improve multi-turn agent task performance on agent-trajectory style data (e.g., ALFWorld household tasks and DBBench database operations, depending on the datasets listed below).

Loss is applied to all assistant turns in the multi-turn trajectories so the model learns: environment observation, action selection, tool use, and recovery from errors.

Training Configuration (summary)

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: LoRA training (base loaded without 4-bit quantization), then merged into full weights
Max sequence length: 2048
Epochs: 2
Learning rate: 1e-06
LoRA: r=64, alpha=128

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "your_id/your-merged-repo"

tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)

# (optional) generation example
inputs = tokenizer("Hello! What should I do next?", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(out[0], skip_special_tokens=True))

Downloads last month: 1

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for RinnRinnmini/qwen3-4b-agent-trajectory-lora

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5498)

this model

RinnRinnmini
/

qwen3-4b-agent-trajectory-lora