Instructions to use BlossomsAI/BloomVN-8B-Chat-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlossomsAI/BloomVN-8B-Chat-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="BlossomsAI/BloomVN-8B-Chat-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BlossomsAI/BloomVN-8B-Chat-Reasoning")
model = AutoModelForCausalLM.from_pretrained("BlossomsAI/BloomVN-8B-Chat-Reasoning", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BlossomsAI/BloomVN-8B-Chat-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BlossomsAI/BloomVN-8B-Chat-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BlossomsAI/BloomVN-8B-Chat-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BlossomsAI/BloomVN-8B-Chat-Reasoning

SGLang

How to use BlossomsAI/BloomVN-8B-Chat-Reasoning 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 "BlossomsAI/BloomVN-8B-Chat-Reasoning" \
    --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": "BlossomsAI/BloomVN-8B-Chat-Reasoning",
		"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 "BlossomsAI/BloomVN-8B-Chat-Reasoning" \
        --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": "BlossomsAI/BloomVN-8B-Chat-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BlossomsAI/BloomVN-8B-Chat-Reasoning with Docker Model Runner:
```
docker model run hf.co/BlossomsAI/BloomVN-8B-Chat-Reasoning
```

MRAGU commited on Mar 6, 2025

Commit

10dd4fb

verified ·

1 Parent(s): 9199281

Create README.md

Browse files

Files changed (1) hide show

README.md +45 -0

README.md ADDED Viewed

	@@ -0,0 +1,45 @@

+---
+license: mit
+language:
+- en
+- vi
+base_model:
+- BlossomsAI/BloomVN-8B-chat
+---
+<div align="center">
+<img src="https://github.com/bloomifycafe/blossomsAI/blob/main/assets/logo.png?raw=true" alt="Logo"/>
+</div>
+</br>
+<div align="center">
+# 🌟 [Repo Name]
+</div>
+### A fine-tuned multilingual model for Vietnamese reasoning
+## 📋 Overview
+- A language model with reasoning capability that provides step-by-step reasoning in Vietnamese before delivering answers.
+- The model follows a structured XML format with explicit reasoning tags.
+- It's designed for educational applications and complex problem-solving tasks in Vietnamese.
+## 🔧 Method
+- Fine-tuned using Guided Ranking for Preference Optimization (GRPO).
+- Employs rule-based reward functions to encourage adherence to Vietnamese XML reasoning format.
+- Uses LoRA adaptation on a Vietnamese dataset spanning various task types.
+## 💫 Quantization
+Coming Soon!
+## 🤝 Contributors
+Developed with ❤️ by [BlossomAI](https://github.com/BlossomAI)
+---
+<div align="center">
+<sub>Star ⭐️ this repo if you find it valuable!</sub>
+</div>