Instructions to use OpenOneRec/KSA-V2-4B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenOneRec/KSA-V2-4B-base with Transformers:

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

pipe = pipeline("text-generation", model="OpenOneRec/KSA-V2-4B-base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenOneRec/KSA-V2-4B-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenOneRec/KSA-V2-4B-base", trust_remote_code=True, 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenOneRec/KSA-V2-4B-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenOneRec/KSA-V2-4B-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenOneRec/KSA-V2-4B-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenOneRec/KSA-V2-4B-base

SGLang

How to use OpenOneRec/KSA-V2-4B-base 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 "OpenOneRec/KSA-V2-4B-base" \
    --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": "OpenOneRec/KSA-V2-4B-base",
		"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 "OpenOneRec/KSA-V2-4B-base" \
        --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": "OpenOneRec/KSA-V2-4B-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenOneRec/KSA-V2-4B-base with Docker Model Runner:
```
docker model run hf.co/OpenOneRec/KSA-V2-4B-base
```

KSA-V2-4B-base

File size: 867 Bytes

a1111f3

from __future__ import annotations

from dataclasses import dataclass

import torch

__all__ = [
    "SummaryBatchContext",
    "build_summary_sliding_context",
]


@dataclass
class SummaryBatchContext:
    position_ids: torch.Tensor
    summary_mask: torch.Tensor
    text_positions: torch.Tensor | None = None
    summary_positions: torch.Tensor | None = None

    @property
    def enabled(self) -> bool:
        return self.summary_mask.numel() > 0


def build_summary_sliding_context(
    input_ids: torch.Tensor,
    position_ids: torch.Tensor,
    summary_token_num: int,
    summary_token_begin: int,
) -> SummaryBatchContext:
    summary_mask = (input_ids >= summary_token_begin) & (
        input_ids < summary_token_begin + summary_token_num
    )
    return SummaryBatchContext(
        position_ids=position_ids,
        summary_mask=summary_mask,
    )