Instructions to use sunbaby/BrainCog-8B-0.1-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunbaby/BrainCog-8B-0.1-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="sunbaby/BrainCog-8B-0.1-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sunbaby/BrainCog-8B-0.1-Instruct")
model = AutoModelForCausalLM.from_pretrained("sunbaby/BrainCog-8B-0.1-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 sunbaby/BrainCog-8B-0.1-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunbaby/BrainCog-8B-0.1-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": "sunbaby/BrainCog-8B-0.1-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sunbaby/BrainCog-8B-0.1-Instruct

SGLang

How to use sunbaby/BrainCog-8B-0.1-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 "sunbaby/BrainCog-8B-0.1-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": "sunbaby/BrainCog-8B-0.1-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 "sunbaby/BrainCog-8B-0.1-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": "sunbaby/BrainCog-8B-0.1-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sunbaby/BrainCog-8B-0.1-Instruct with Docker Model Runner:
```
docker model run hf.co/sunbaby/BrainCog-8B-0.1-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Information

BrainCog is developed by BrainCog group.

Current version is BrainCog-8B-0.1-Instruct.

Use with transformers

import torch
import transformers

model_id = "sunbaby/BrainCog-8B-0.1-Instruct"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
      "torch_dtype": torch.bfloat16
    },
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a useful chatbot or assistant to help people."},
    {"role": "user", "content": "How are you?"},
]
outputs = pipeline(
    messages,
    max_new_tokens=2048,
)
print(outputs[0]["generated_text"][-1])

Responsibility

The output of the model is uncontrollable, and its output does not represent our opinion

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for sunbaby/BrainCog-8B-0.1-Instruct

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(597)

this model

Quantizations

1 model

sunbaby
/

BrainCog-8B-0.1-Instruct

Model Information

Use with transformers

Responsibility

Model tree for sunbaby/BrainCog-8B-0.1-Instruct

Dataset used to train sunbaby/BrainCog-8B-0.1-Instruct