Instructions to use hfunknown/qwen3-8b-navigation-lora-persistent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hfunknown/qwen3-8b-navigation-lora-persistent with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "hfunknown/qwen3-8b-navigation-lora-persistent")

Transformers

How to use hfunknown/qwen3-8b-navigation-lora-persistent with Transformers:

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

pipe = pipeline("text-generation", model="hfunknown/qwen3-8b-navigation-lora-persistent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hfunknown/qwen3-8b-navigation-lora-persistent", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hfunknown/qwen3-8b-navigation-lora-persistent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hfunknown/qwen3-8b-navigation-lora-persistent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hfunknown/qwen3-8b-navigation-lora-persistent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hfunknown/qwen3-8b-navigation-lora-persistent

SGLang

How to use hfunknown/qwen3-8b-navigation-lora-persistent 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 "hfunknown/qwen3-8b-navigation-lora-persistent" \
    --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": "hfunknown/qwen3-8b-navigation-lora-persistent",
		"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 "hfunknown/qwen3-8b-navigation-lora-persistent" \
        --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": "hfunknown/qwen3-8b-navigation-lora-persistent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hfunknown/qwen3-8b-navigation-lora-persistent with Docker Model Runner:
```
docker model run hf.co/hfunknown/qwen3-8b-navigation-lora-persistent
```

qwen3-8b-navigation-lora-persistent / README.md

hfunknown

Upload README.md with huggingface_hub

c93f7a4 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

1.69 kB

metadata

library_name: peft
base_model: Qwen/Qwen3-8B
tags:
  - lora
  - transformers
pipeline_tag: text-generation

qwen3-8b-navigation-lora-persistent

Anonymous supplementary release for a double-blind workshop submission. This is one of four LoRA adapters (rule_diagnosis / navigation task family x persistent/stateless training regime), fine-tuned on the navigation agentic task (graph exploration with a per-turn tool-call budget). It is the second-family generalization arm alongside the primary Opaque Knapsack result (see the sibling Qwen3-8B knapsack release).

Base model: Qwen/Qwen3-8B
Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
Seed: 3407

Training configuration

Fine-tuned with Axolotl, LoRA adapter, 4-bit NF4 quantized base:

Hyperparameter	Value
lora_r	64
lora_alpha	128
lora_dropout	0.05
lora_target_modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
learning_rate	1e-4
lr_scheduler	cosine
optimizer	adamw_torch
epochs	3.0
micro_batch_size	1
gradient_accumulation_steps	16
sequence_len	16384
sample_packing	false
seed	3407
training data	paired traces for the "persistent" regime on navigation, see paper Appendix for pairing/filtering procedure

Provenance

Released anonymously alongside a NeurIPS workshop submission for reproducibility review. Non-anonymous release (paper citation, full code, full training traces) will follow after the review process concludes.