Instructions to use stech2333/brainalign-qwen2.5-1.5b-B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stech2333/brainalign-qwen2.5-1.5b-B with Transformers:

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

pipe = pipeline("text-generation", model="stech2333/brainalign-qwen2.5-1.5b-B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stech2333/brainalign-qwen2.5-1.5b-B")
model = AutoModelForCausalLM.from_pretrained("stech2333/brainalign-qwen2.5-1.5b-B")
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 stech2333/brainalign-qwen2.5-1.5b-B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stech2333/brainalign-qwen2.5-1.5b-B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stech2333/brainalign-qwen2.5-1.5b-B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stech2333/brainalign-qwen2.5-1.5b-B

SGLang

How to use stech2333/brainalign-qwen2.5-1.5b-B 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 "stech2333/brainalign-qwen2.5-1.5b-B" \
    --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": "stech2333/brainalign-qwen2.5-1.5b-B",
		"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 "stech2333/brainalign-qwen2.5-1.5b-B" \
        --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": "stech2333/brainalign-qwen2.5-1.5b-B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stech2333/brainalign-qwen2.5-1.5b-B with Docker Model Runner:
```
docker model run hf.co/stech2333/brainalign-qwen2.5-1.5b-B
```

B

Summary

This model is the B BrainAlign stage-2 LoRA checkpoint (best_by_retrieval) merged into the full base model Qwen/Qwen2.5-1.5B-Instruct.

The folder is saved in standard Hugging Face format so it can be uploaded directly for Open LLM Leaderboard v2 evaluation.

Export Metadata

Export time: 2026-05-14T19:54:54
Model kind: merged_lora
Base model: Qwen/Qwen2.5-1.5B-Instruct
Checkpoint choice: best_by_retrieval
Projector branch: B
Stage-1 head: mean5_pca1024_standardized_mse_contrastive_rawpca_normmse_rerun

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("B")
tokenizer = AutoTokenizer.from_pretrained("B")

Downloads last month: 29

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for stech2333/brainalign-qwen2.5-1.5b-B

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(983)

this model