Instructions to use buildersloop/bl-chat-290m-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use buildersloop/bl-chat-290m-onnx with Transformers:

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

pipe = pipeline("text-generation", model="buildersloop/bl-chat-290m-onnx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("buildersloop/bl-chat-290m-onnx")
model = AutoModelForCausalLM.from_pretrained("buildersloop/bl-chat-290m-onnx")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use buildersloop/bl-chat-290m-onnx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "buildersloop/bl-chat-290m-onnx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "buildersloop/bl-chat-290m-onnx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/buildersloop/bl-chat-290m-onnx

SGLang

How to use buildersloop/bl-chat-290m-onnx 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 "buildersloop/bl-chat-290m-onnx" \
    --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": "buildersloop/bl-chat-290m-onnx",
		"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 "buildersloop/bl-chat-290m-onnx" \
        --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": "buildersloop/bl-chat-290m-onnx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use buildersloop/bl-chat-290m-onnx with Docker Model Runner:
```
docker model run hf.co/buildersloop/bl-chat-290m-onnx
```

BuildersLoop AI (290M)

BuildersLoop が一から自作した日本語LLM です。既存モデルのファインチューニングではなく、 自作トークナイザー → 事前学習 → チャット化 まで全部スクラッチで作りました。

パラメータ数: 約 293M（GPT-2系アーキ / n_layer=20, n_embd=1024, block_size=512）
トークナイザー: 自作BPE（語彙 40,016）
性格: 気さくな相棒型（タメ口・あいさつ/雑談/気持ちの話が得意）
まだ勉強中なので、難しい知識質問は苦手です。

このリポジトリは ONNX（transformers.js / WebGPU 用） です。

使い方（ブラウザ・transformers.js）

import { pipeline } from '@huggingface/transformers';
const pipe = await pipeline('text-generation', 'buildersloop/bl-chat-290m-onnx', { device: 'webgpu' });
const out = await pipe('ユーザー: こんにちは！自己紹介して AI: ',
                       { max_new_tokens: 120, temperature: 0.6, top_k: 200, repetition_penalty: 1.3 });
console.log(out[0].generated_text);

会話フォーマットは ユーザー: <発話> AI: 。デモ: https://huggingface.co/spaces/buildersloop/buildersloop-ai

Downloads last month: 74

buildersloop
/

bl-chat-290m-onnx

BuildersLoop AI (290M)

使い方（ブラウザ・transformers.js）

Space using buildersloop/bl-chat-290m-onnx 1