Instructions to use willamazon1/sdft-search-lora-iter20 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use willamazon1/sdft-search-lora-iter20 with Transformers:

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

pipe = pipeline("text-generation", model="willamazon1/sdft-search-lora-iter20")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("willamazon1/sdft-search-lora-iter20")
model = AutoModelForCausalLM.from_pretrained("willamazon1/sdft-search-lora-iter20", device_map="auto")
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 willamazon1/sdft-search-lora-iter20 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "willamazon1/sdft-search-lora-iter20"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "willamazon1/sdft-search-lora-iter20",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/willamazon1/sdft-search-lora-iter20

SGLang

How to use willamazon1/sdft-search-lora-iter20 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 "willamazon1/sdft-search-lora-iter20" \
    --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": "willamazon1/sdft-search-lora-iter20",
		"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 "willamazon1/sdft-search-lora-iter20" \
        --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": "willamazon1/sdft-search-lora-iter20",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use willamazon1/sdft-search-lora-iter20 with Docker Model Runner:
```
docker model run hf.co/willamazon1/sdft-search-lora-iter20
```

sdft-search-lora-iter20

A Qwen3-8B model fine-tuned for retrieval-augmented (search-R1 style) multi-turn reasoning. This is a LoRA adapter merged back into the full model and exported as standard HuggingFace safetensors.

Training

Base / init: Qwen3-8B-Base after a supervised fine-tuning (SDFT) cold-start (oracle-mix SFT), then RL.
Method: Search-R1 style RL (GRPO/GSPO) in the slime framework, with a co-located GPU-faiss retriever over a Wikipedia-2018 index.
Parameter-efficient: LoRA, rank r=16, alpha=32 (scaling alpha/r = 2.0), applied to linear_qkv, linear_proj, linear_fc1, linear_fc2 in every layer.
Checkpoint: RL iteration 20. The adapter (all 144 lora_B factors nonzero) is merged into the base weights: W ← W + (alpha/r) · B @ A per target module.

Note: This is an early checkpoint (20 RL steps). The merged delta over the SDFT base is small (relative Frobenius norm ~1e-2 per projection matrix), so the model behaves very close to the SDFT base with an initial RL update applied.

Architecture

Qwen3, 36 layers, hidden 4096, 32 attn heads / 8 KV heads (GQA), intermediate 12288, vocab 151936, bf16. Identical arch to Qwen3-8B-Base.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("willamazon1/sdft-search-lora-iter20")
model = AutoModelForCausalLM.from_pretrained(
    "willamazon1/sdft-search-lora-iter20", dtype=torch.bfloat16, device_map="cuda"
)
ids = tok("The capital of France is", return_tensors="pt").input_ids.cuda()
print(tok.decode(model.generate(ids, max_new_tokens=16)[0]))

Downloads last month: 19

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for willamazon1/sdft-search-lora-iter20

Base model

Qwen/Qwen3-8B-Base

Adapter

(82)

this model