Instructions to use streamerbtw1002/Nexuim-R1-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use streamerbtw1002/Nexuim-R1-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="streamerbtw1002/Nexuim-R1-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("streamerbtw1002/Nexuim-R1-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("streamerbtw1002/Nexuim-R1-7B-Instruct")
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

vLLM

How to use streamerbtw1002/Nexuim-R1-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "streamerbtw1002/Nexuim-R1-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "streamerbtw1002/Nexuim-R1-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/streamerbtw1002/Nexuim-R1-7B-Instruct

SGLang

How to use streamerbtw1002/Nexuim-R1-7B-Instruct 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 "streamerbtw1002/Nexuim-R1-7B-Instruct" \
    --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": "streamerbtw1002/Nexuim-R1-7B-Instruct",
		"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 "streamerbtw1002/Nexuim-R1-7B-Instruct" \
        --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": "streamerbtw1002/Nexuim-R1-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use streamerbtw1002/Nexuim-R1-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/streamerbtw1002/Nexuim-R1-7B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Details

Model Name: streamerbtw1002/Nexuim-R1-7B-Instruct

Developed by: James Phifer (NexusMind.tech)
Funded by: Tristian (Shuttle.ai)
License: Apache-2.0
Finetuned from: Qwen/Qwen2.5-VL-7B-Instruct
Architecture: Transformer-based LLM

Overview

This model is designed to handle complex mathematical questions efficiently using Chain of Thought (CoT) reasoning.

Capabilities:
- General-purpose LLM
- Strong performance on multi-step reasoning tasks
- Able to respond to requests ethically while preventing human harm
Limitations:
- Not evaluated extensively
- May generate incorrect or biased outputs in certain contexts

Training Details

Dataset: Trained on a 120k-line CoT dataset for mathematical reasoning.
Training Hardware: 1x A100 80GB GPU (Provided by Tristian at Shuttle.ai)

Evaluation

Status: Not formally tested yet.
Preliminary Results:

Provides detailed, well-structured answers
Performs well on long-form mathematical problems

Usage

from transformers import AutoConfig, AutoModel, AutoTokenizer

model_id = "streamerbtw1002/Nexuim-R1-7B-Instruct"

config = AutoConfig.from_pretrained(
  model_id,
  revision="main"
)
model = AutoModel.from_pretrained(
  model_id,
  revision="main"
)
tokenizer = AutoTokenizer.from_pretrained(
  model_id,
  revision="main"
)

Downloads last month: 18

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for streamerbtw1002/Nexuim-R1-7B-Instruct

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3288)

this model

Quantizations

1 model