Instructions to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337")

Transformers

How to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 with Transformers:

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

pipe = pipeline("text-generation", model="runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337

SGLang

How to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 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 "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337" \
    --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": "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337",
		"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 "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337" \
        --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": "runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337 with Docker Model Runner:
```
docker model run hf.co/runtime-contracts/qwen3-8b-knapsack-lora-persistent-seed1337
```

qwen3-8b-knapsack-lora-persistent-seed1337 / README.md

TieuDaoChanNhan

Update card: license, paper reference

f4dc4ca verified 24 days ago

preview code

Raw History Blame Contribute Delete

1.74 kB

	---
	license: apache-2.0
	library_name: peft
	base_model: Qwen/Qwen3-8B
	tags:
	- lora
	- transformers
	pipeline_tag: text-generation
	---

	# qwen3-8b-knapsack-lora-persistent-seed1337

	Supplementary release for the paper Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality (IAEval 2026, the NeurIPS 2026 Workshop on Evaluation of Interactive Agents). This is
	one of six LoRA adapters (persistent/stateless training regime x 3 seeds)
	fine-tuned on the Opaque Knapsack agentic task.

	- Base model: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
	- Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
	- Seed: 1337

	## Training configuration

	Fine-tuned with [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) 0.13.2,
	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 \| 1337 \|
	\| training data \| paired traces for the "persistent" regime (see paper Appendix for pairing/filtering procedure) \|

	## Provenance

	Released alongside the paper Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality (IAEval 2026, the NeurIPS 2026 Workshop on Evaluation of Interactive Agents), to reproduce its reported results.

	## License

	Apache License 2.0. The base model (Qwen3-8B) is also released under Apache 2.0.

	---
	license: apache-2.0
	library_name: peft
	base_model: Qwen/Qwen3-8B
	tags:
	- lora
	- transformers
	pipeline_tag: text-generation
	---

	# qwen3-8b-knapsack-lora-persistent-seed1337

	Supplementary release for the paper Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality (IAEval 2026, the NeurIPS 2026 Workshop on Evaluation of Interactive Agents). This is
	one of six LoRA adapters (persistent/stateless training regime x 3 seeds)
	fine-tuned on the Opaque Knapsack agentic task.

	- Base model: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
	- Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
	- Seed: 1337

	## Training configuration

	Fine-tuned with [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) 0.13.2,
	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 \| 1337 \|
	\| training data \| paired traces for the "persistent" regime (see paper Appendix for pairing/filtering procedure) \|

	## Provenance

	Released alongside the paper Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality (IAEval 2026, the NeurIPS 2026 Workshop on Evaluation of Interactive Agents), to reproduce its reported results.

	## License

	Apache License 2.0. The base model (Qwen3-8B) is also released under Apache 2.0.