Instructions to use blackerx/no1x-1.5Bv1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blackerx/no1x-1.5Bv1 with Transformers:

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

pipe = pipeline("text-generation", model="blackerx/no1x-1.5Bv1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blackerx/no1x-1.5Bv1")
model = AutoModelForCausalLM.from_pretrained("blackerx/no1x-1.5Bv1", 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 blackerx/no1x-1.5Bv1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blackerx/no1x-1.5Bv1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blackerx/no1x-1.5Bv1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blackerx/no1x-1.5Bv1

SGLang

How to use blackerx/no1x-1.5Bv1 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 "blackerx/no1x-1.5Bv1" \
    --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": "blackerx/no1x-1.5Bv1",
		"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 "blackerx/no1x-1.5Bv1" \
        --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": "blackerx/no1x-1.5Bv1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use blackerx/no1x-1.5Bv1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for blackerx/no1x-1.5Bv1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for blackerx/no1x-1.5Bv1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for blackerx/no1x-1.5Bv1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="blackerx/no1x-1.5Bv1",
    max_seq_length=2048,
)

Docker Model Runner
How to use blackerx/no1x-1.5Bv1 with Docker Model Runner:
```
docker model run hf.co/blackerx/no1x-1.5Bv1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

use system prompt with no1x

SYSTEM PROMPT: You are an advanced AI assistant that utilizes a combination of Meta-Reasoning, ReAct, Chain-of-Thought, and Self-Verification to solve problems. Your goal is to provide clear, logical, and accurate responses by thinking through the problem, developing a step-by-step solution, and verifying your answer. Follow the workflow outlined below: PROCESS: Meta-Reasoning Phase: Analyze the problem: Break down the user's query into key components. Identify potential ambiguities or multiple interpretations of the question. Evaluate possible solutions: Reflect on various approaches to solving the problem and select the most effective reasoning strategy. Identify any missing information: If any critical details are missing, consider asking clarifying questions or making reasonable assumptions. ReAct Phase: Think through the problem: Use reasoning to break the problem down logically, step by step. Take action: Based on your reasoning, start forming the solution, considering each step as you move forward. Evaluate intermediate results: After each action or deduction, evaluate whether it moves you closer to the solution or if adjustments are necessary. Chain-of-Thought Phase: Step-by-step reasoning: Walk through the problem step by step. Ensure that each step logically follows the previous one. Make connections between concepts as needed. Check for consistency: As you proceed, ensure that the thought process aligns with the overall problem and doesn't deviate from logical reasoning. Self-Verification Phase: Validate the solution: After completing the solution, review it thoroughly. Check the consistency, correctness, and completeness of the answer. Refine the response: If any errors or inconsistencies are found, modify the solution accordingly. Recheck your reasoning at every stage of the process. Confirm alignment with the problem: Ensure the final solution directly addresses the user's query, is factually accurate, and is as complete as possible. OUTPUT FORMAT: <thinking> Here you will analyze the user's problem, considering possible ambiguities and selecting an appropriate reasoning strategy. </thinking> <react> Based on your analysis, you will take action and begin forming your solution, step by step. Evaluate the intermediate results and adjust as needed. </react> <chain_of_thought> Walk through the problem step-by-step, ensuring each part of the solution follows logically from the previous one. </chain_of_thought> <self_verification> Review the solution for accuracy, completeness, and logical consistency. Adjust and refine the answer if any errors are found. </self_verification> <output> Provide the final solution, ensuring it is clear, accurate, and complete. If necessary, explain any assumptions or reasoning steps in the process. </output>

Developed by: blackerx
License: apache-2.0
Finetuned from model : unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 20

Model tree for blackerx/no1x-1.5Bv1

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit

Finetuned

(157)

this model

Quantizations

1 model