Instructions to use dfdu233/OneReason-0.8B-lora-expA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dfdu233/OneReason-0.8B-lora-expA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/root/autodl-tmp/LLM/model_cache/OneReason-0.8B-pretrain-competition")
model = PeftModel.from_pretrained(base_model, "dfdu233/OneReason-0.8B-lora-expA")

Transformers

How to use dfdu233/OneReason-0.8B-lora-expA with Transformers:

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

pipe = pipeline("text-generation", model="dfdu233/OneReason-0.8B-lora-expA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dfdu233/OneReason-0.8B-lora-expA", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dfdu233/OneReason-0.8B-lora-expA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dfdu233/OneReason-0.8B-lora-expA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dfdu233/OneReason-0.8B-lora-expA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dfdu233/OneReason-0.8B-lora-expA

SGLang

How to use dfdu233/OneReason-0.8B-lora-expA 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 "dfdu233/OneReason-0.8B-lora-expA" \
    --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": "dfdu233/OneReason-0.8B-lora-expA",
		"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 "dfdu233/OneReason-0.8B-lora-expA" \
        --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": "dfdu233/OneReason-0.8B-lora-expA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dfdu233/OneReason-0.8B-lora-expA with Docker Model Runner:
```
docker model run hf.co/dfdu233/OneReason-0.8B-lora-expA
```

OneReason-0.8B-LoRA-ExpA

LoRA adapter fine-tuned from OpenOneRec/OneReason-0.8B-pretrain-competition on the Kuaishou Explorer LLM-Rec Challenge dataset.

Model Details

Base Model: OpenOneRec/OneReason-0.8B-pretrain-competition (Qwen3-0.8B)
Fine-tuning Method: LoRA (rank=16, alpha=32)
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Training Data: Kuaishou LLM-Rec Challenge competition dataset (32K samples)
Training Steps: 4,660 / 11,571 (~40% of 3 epochs)
Hardware: NVIDIA RTX 4090 (47GB VRAM)
Training Time: ~2h 41min

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "OpenOneRec/OneReason-0.8B-pretrain-competition"
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    trust_remote_code=True,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)

# Load LoRA adapter
model = PeftModel.from_pretrained(model, "dfdu233/OneReason-0.8B-lora-expA")

# Example inference
prompt = "<|prod_begin|><s_a_1183><s_b_746><s_c_5290>，这个商品卖的是什么？ /no_think"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_p=0.95, temperature=0.7)
print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))

Training Details

Loss: 3.023 → 1.337 (56% reduction over 4660 steps)
Validation Loss: 1.373 (decreasing, no overfitting)
Cutoff Length: 8192
Batch Size: 1 (gradient accumulation 8 = effective batch 8)
Learning Rate: 3e-5 (cosine schedule)
Optimizer: paged_adamw_8bit
Context Length: 8192 tokens
Flash Attention: fa2

Training Data Distribution

Task	Samples
Recommendation (懂推荐)	21,885
Item Understanding (懂物料)	5,807
User Prediction (懂用户)	4,788
Total	32,480

Framework versions

PEFT 0.18.1
PyTorch 2.4.0
Transformers 5.6.0
Flash-Attn 2.6.3

Downloads last month: 27

Model tree for dfdu233/OneReason-0.8B-lora-expA

Base model

OpenOneRec/OneReason-0.8B-pretrain-competition

Adapter

(10)

this model