Instructions to use runtime-contracts/mistral-7b-knapsack-lora-persistent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use runtime-contracts/mistral-7b-knapsack-lora-persistent with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.3")
model = PeftModel.from_pretrained(base_model, "runtime-contracts/mistral-7b-knapsack-lora-persistent")

Transformers

How to use runtime-contracts/mistral-7b-knapsack-lora-persistent with Transformers:

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

pipe = pipeline("text-generation", model="runtime-contracts/mistral-7b-knapsack-lora-persistent")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("runtime-contracts/mistral-7b-knapsack-lora-persistent", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use runtime-contracts/mistral-7b-knapsack-lora-persistent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "runtime-contracts/mistral-7b-knapsack-lora-persistent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "runtime-contracts/mistral-7b-knapsack-lora-persistent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/runtime-contracts/mistral-7b-knapsack-lora-persistent

SGLang

How to use runtime-contracts/mistral-7b-knapsack-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 "runtime-contracts/mistral-7b-knapsack-lora-persistent" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "runtime-contracts/mistral-7b-knapsack-lora-persistent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/mistral-7b-knapsack-lora-persistent" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "runtime-contracts/mistral-7b-knapsack-lora-persistent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use runtime-contracts/mistral-7b-knapsack-lora-persistent with Docker Model Runner:
```
docker model run hf.co/runtime-contracts/mistral-7b-knapsack-lora-persistent
```

mistral-7b-knapsack-lora-persistent / README.md

TieuDaoChanNhan

Update card: license, paper reference

cf14e8e verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.2 kB

---
license: apache-2.0
library_name: peft
base_model: mistralai/Mistral-7B-v0.3
tags:
- lora
- transformers
pipeline_tag: text-generation
---
# mistral-7b-knapsack-lora-persistent

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 four LoRA adapters (Mistral-7B-v0.3 / Llama-3.1-8B base model x
persistent/stateless training regime) fine-tuned on the Opaque Knapsack
agentic task, extending a prior single-base-model result (see the sibling
Qwen3-8B release) to a second base model family for the same paper.

- **Base model:** [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
- **Training regime:** persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
- **Seed:** 3407

## Training configuration

Fine-tuned with [Axolotl](https://github.com/axolotl-ai-cloud/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 (see paper Appendix for pairing/filtering procedure) |
Mistral-7B-v0.3 ships no chat_template -- trained with Axolotl's built-in `mistral_v2v3` template; serving/eval uses a hand-written template extending it with system-role support (folded into the next user turn, since `mistral_v2v3` only accepts user/assistant).

## 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 (Mistral-7B-v0.3) is also released under Apache 2.0.

	---
	license: apache-2.0
	library_name: peft
	base_model: mistralai/Mistral-7B-v0.3
	tags:
	- lora
	- transformers
	pipeline_tag: text-generation
	---

	# mistral-7b-knapsack-lora-persistent

	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 four LoRA adapters (Mistral-7B-v0.3 / Llama-3.1-8B base model x
	persistent/stateless training regime) fine-tuned on the Opaque Knapsack
	agentic task, extending a prior single-base-model result (see the sibling
	Qwen3-8B release) to a second base model family for the same paper.

	- Base model: [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
	- Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
	- Seed: 3407

	## Training configuration

	Fine-tuned with [Axolotl](https://github.com/axolotl-ai-cloud/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 (see paper Appendix for pairing/filtering procedure) \|

	Mistral-7B-v0.3 ships no chat_template -- trained with Axolotl's built-in `mistral_v2v3` template; serving/eval uses a hand-written template extending it with system-role support (folded into the next user turn, since `mistral_v2v3` only accepts user/assistant).

	## 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 (Mistral-7B-v0.3) is also released under Apache 2.0.