Instructions to use Local-Novel-LLM-project/RAI-3.0-R1-VECTOR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Local-Novel-LLM-project/RAI-3.0-R1-VECTOR with Transformers:

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

pipe = pipeline("text-generation", model="Local-Novel-LLM-project/RAI-3.0-R1-VECTOR", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Local-Novel-LLM-project/RAI-3.0-R1-VECTOR", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Local-Novel-LLM-project/RAI-3.0-R1-VECTOR", trust_remote_code=True)
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 Local-Novel-LLM-project/RAI-3.0-R1-VECTOR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Local-Novel-LLM-project/RAI-3.0-R1-VECTOR

SGLang

How to use Local-Novel-LLM-project/RAI-3.0-R1-VECTOR 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 "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR" \
    --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": "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR",
		"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 "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR" \
        --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": "Local-Novel-LLM-project/RAI-3.0-R1-VECTOR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Local-Novel-LLM-project/RAI-3.0-R1-VECTOR with Docker Model Runner:
```
docker model run hf.co/Local-Novel-LLM-project/RAI-3.0-R1-VECTOR
```

TylorShine commited on Mar 30

Commit

39c3dd5

verified ·

1 Parent(s): 327a7bc

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ language:
 - en
 pipeline_tag: text-generation
 ---
-# RAI-R1-VECTOR
 <a href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank" style="margin: 2px;">
   <img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-4caf50?&color=4caf50" style="display: inline-block; vertical-align: middle;"/>
 </a>
@@ -20,7 +20,7 @@ pipeline_tag: text-generation
 ---
 ## Model Overview
-**RAI-R1-VECTOR** is a task-vector merged model created using the following formula:
 ```
 DeepSeek-R1-0528 + (RakutenAI-3.0 - DeepSeek-V3-0324)
 ```
@@ -46,8 +46,8 @@ This architecture combines the advanced reasoning capabilities of `DeepSeek-R1-0
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("Local-Novel-LLM-project/RAI-R1-VECTOR", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("Local-Novel-LLM-project/RAI-R1-VECTOR")
 inputs = tokenizer("日本の文化で重要な要素は", return_tensors="pt")
 outputs = model.generate(**inputs, max_length=100)
@@ -62,11 +62,11 @@ print(tokenizer.decode(outputs[0]))
 ## Citation
 ```bibtex
 @misc{RAIR1VECTOR2026,
-  title = {RAI-R1-VECTOR: Task-Vector Merged Model},
   author = {LocalNovelLLM-project},
   year = {2026},
   publisher = {LocalNovelLLM-project},
-  url = {https://huggingface.co/Local-Novel-LLM-project/RAI-R1-VECTOR}
 }
 ```

 - en
 pipeline_tag: text-generation
 ---
+# RAI-3.0-R1-VECTOR
 <a href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank" style="margin: 2px;">
   <img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-4caf50?&color=4caf50" style="display: inline-block; vertical-align: middle;"/>
 </a>
 ---
 ## Model Overview
+**RAI-3.0-R1-VECTOR** is a task-vector merged model created using the following formula:
 ```
 DeepSeek-R1-0528 + (RakutenAI-3.0 - DeepSeek-V3-0324)
 ```
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("Local-Novel-LLM-project/RAI-3.0-R1-VECTOR", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("Local-Novel-LLM-project/RAI-3.0-R1-VECTOR")
 inputs = tokenizer("日本の文化で重要な要素は", return_tensors="pt")
 outputs = model.generate(**inputs, max_length=100)
 ## Citation
 ```bibtex
 @misc{RAIR1VECTOR2026,
+  title = {RAI-3.0-R1-VECTOR: Task-Vector Merged Model},
   author = {LocalNovelLLM-project},
   year = {2026},
   publisher = {LocalNovelLLM-project},
+  url = {https://huggingface.co/Local-Novel-LLM-project/RAI-3.0-R1-VECTOR}
 }
 ```