Instructions to use yifanouyang/Meridian-Text-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yifanouyang/Meridian-Text-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="yifanouyang/Meridian-Text-1.7B")

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

tokenizer = AutoTokenizer.from_pretrained("yifanouyang/Meridian-Text-1.7B")
model = AutoModelForCausalLM.from_pretrained("yifanouyang/Meridian-Text-1.7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yifanouyang/Meridian-Text-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yifanouyang/Meridian-Text-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yifanouyang/Meridian-Text-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yifanouyang/Meridian-Text-1.7B

SGLang

How to use yifanouyang/Meridian-Text-1.7B 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 "yifanouyang/Meridian-Text-1.7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yifanouyang/Meridian-Text-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "yifanouyang/Meridian-Text-1.7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yifanouyang/Meridian-Text-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yifanouyang/Meridian-Text-1.7B with Docker Model Runner:
```
docker model run hf.co/yifanouyang/Meridian-Text-1.7B
```

Meridian Text 1.7B

An English STEM text-completion base with 1.7B parameters, a complete 3.44 GB BF16 checkpoint and a 4,096-token training context. No chat or instruction tuning.

Code & quick start · Local / offline setup · Training

hf download yifanouyang/Meridian-Text-1.7B --local-dir weights

Local workflow

The GitHub toolkit supports resumable JSONL completion, duplicate-ID and settings checks, CPU/CUDA/MPS selection and offline loading. Standard Qwen3 architecture; no Hub Python execution is required.

A domain-adaptation trainer saves separate checkpoints. The training pipeline was smoke-tested with a tiny local Qwen3. Released 1.7B weights are unchanged; full-checkpoint inference and benchmark evaluation have not been validated here.

Outputs may repeat or contain incorrect information. CPU FP32 inference requires substantially more memory than the checkpoint size; full-parameter training also needs gradients and optimizer states.

License

Apache-2.0 · Source · Model reference · Notices

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16