Instructions to use prodigyhuh/atomicvision-medium-fidelity-boost-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prodigyhuh/atomicvision-medium-fidelity-boost-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
model = PeftModel.from_pretrained(base_model, "prodigyhuh/atomicvision-medium-fidelity-boost-lora")

Transformers

How to use prodigyhuh/atomicvision-medium-fidelity-boost-lora with Transformers:

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

pipe = pipeline("text-generation", model="prodigyhuh/atomicvision-medium-fidelity-boost-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prodigyhuh/atomicvision-medium-fidelity-boost-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prodigyhuh/atomicvision-medium-fidelity-boost-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prodigyhuh/atomicvision-medium-fidelity-boost-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": "prodigyhuh/atomicvision-medium-fidelity-boost-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prodigyhuh/atomicvision-medium-fidelity-boost-lora

SGLang

How to use prodigyhuh/atomicvision-medium-fidelity-boost-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 "prodigyhuh/atomicvision-medium-fidelity-boost-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": "prodigyhuh/atomicvision-medium-fidelity-boost-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 "prodigyhuh/atomicvision-medium-fidelity-boost-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": "prodigyhuh/atomicvision-medium-fidelity-boost-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prodigyhuh/atomicvision-medium-fidelity-boost-lora with Docker Model Runner:
```
docker model run hf.co/prodigyhuh/atomicvision-medium-fidelity-boost-lora
```

atomicvision-medium-fidelity-boost-lora / safe_sft_report.json

prodigyhuh

Upload AtomicVision PEFT adapter

2f65e0a verified about 2 months ago

Raw

History Blame Contribute Delete

995 Bytes

	{
	"dataset_jsonl": "/kaggle/working/AtomicVision/outputs/sft/atomicvision_medium_prior_fidelity_sft.jsonl",
	"final_mean_loss": 0.0018379708199063316,
	"grad_accum": 8,
	"init_adapter_dir": "/kaggle/working/atomicvision-format-submit-merged-lora",
	"learning_rate": 5e-06,
	"lora_alpha": 32,
	"lora_dropout": 0.05,
	"lora_r": 16,
	"mask_stats": {
	"examples": 256,
	"max_label_tokens": 73,
	"max_length": 1536,
	"mean_label_tokens": 52.64453125,
	"min_label_tokens": 13,
	"truncated_examples": 248
	},
	"max_updates": 12,
	"model": "Qwen/Qwen3-1.7B",
	"output_dir": "/kaggle/working/atomicvision-medium-fidelity-boost-lora",
	"row_stats": {
	"final_tool_counts": {
	"ask_prior": 8,
	"submit_defect_map": 248
	},
	"rows": 256,
	"sample_counts": {
	"ask_prior": 8,
	"submit_after_reference": 5,
	"submit_prior": 243
	}
	},
	"status": "success",
	"zip_path": "/kaggle/working/atomicvision-medium-fidelity-boost-lora.zip"
	}