Instructions to use Ochiroo/tiny_mn_gpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ochiroo/tiny_mn_gpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ochiroo/tiny_mn_gpt")# Load model directly from transformers import AutoTokenizer, TF_AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ochiroo/tiny_mn_gpt") model = TF_AutoModelForCausalLM.from_pretrained("Ochiroo/tiny_mn_gpt") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ochiroo/tiny_mn_gpt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ochiroo/tiny_mn_gpt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ochiroo/tiny_mn_gpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ochiroo/tiny_mn_gpt
- SGLang
How to use Ochiroo/tiny_mn_gpt 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 "Ochiroo/tiny_mn_gpt" \ --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": "Ochiroo/tiny_mn_gpt", "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 "Ochiroo/tiny_mn_gpt" \ --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": "Ochiroo/tiny_mn_gpt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ochiroo/tiny_mn_gpt with Docker Model Runner:
docker model run hf.co/Ochiroo/tiny_mn_gpt
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,10 +33,6 @@ beam_outputs = model.generate(
|
|
| 33 |
print(tokenizer.decode(beam_outputs[0]))
|
| 34 |
```
|
| 35 |
|
| 36 |
-
#### Limitations and bias
|
| 37 |
-
|
| 38 |
-
Provide examples of latent issues and potential remediations.
|
| 39 |
-
|
| 40 |
## Training data and biases
|
| 41 |
|
| 42 |
Trained on 500MB of Mongolian news dataset (IKON) on RTX 2060.
|
|
|
|
| 33 |
print(tokenizer.decode(beam_outputs[0]))
|
| 34 |
```
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Training data and biases
|
| 37 |
|
| 38 |
Trained on 500MB of Mongolian news dataset (IKON) on RTX 2060.
|