Instructions to use MetaCore-LLM/MetaCore-1-Test-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaCore-LLM/MetaCore-1-Test-Base with Transformers:

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

pipe = pipeline("text-generation", model="MetaCore-LLM/MetaCore-1-Test-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaCore-LLM/MetaCore-1-Test-Base")
model = AutoModelForCausalLM.from_pretrained("MetaCore-LLM/MetaCore-1-Test-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MetaCore-LLM/MetaCore-1-Test-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaCore-LLM/MetaCore-1-Test-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaCore-LLM/MetaCore-1-Test-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaCore-LLM/MetaCore-1-Test-Base

SGLang

How to use MetaCore-LLM/MetaCore-1-Test-Base 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 "MetaCore-LLM/MetaCore-1-Test-Base" \
    --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": "MetaCore-LLM/MetaCore-1-Test-Base",
		"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 "MetaCore-LLM/MetaCore-1-Test-Base" \
        --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": "MetaCore-LLM/MetaCore-1-Test-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaCore-LLM/MetaCore-1-Test-Base with Docker Model Runner:
```
docker model run hf.co/MetaCore-LLM/MetaCore-1-Test-Base
```

MetaCore-LLM commited on 6 days ago

Commit

3643f45

verified ·

1 Parent(s): 17df6bf

Create README.md

Browse files

Files changed (1) hide show

README.md +25 -0

README.md ADDED Viewed

	@@ -0,0 +1,25 @@

+language:
+- ru
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- russian
+- llama
+- causal-lm
+- pretrained
+- tiny
+- from-scratch
+model-index:
+- name: MetaCore-1-Test-Base
+  results: []
+---
+# MetaCore-1-Test-Base
+**MetaCore-1-Test-Base** is a lightweight Russian language model trained from scratch. It serves as the foundation for further continued pre‑training (CPT) and instruction tuning (SFT). This model is designed for experimentation, educational purposes, and as a starting point for domain‑specific adaptation.
+- **Developer:** MetaCore-LLM
+- **Architecture:** Custom LLaMA-style (tiny config)
+- **Language:** Russian
+- **Parameter count:** ~16.2 million