Instructions to use raygx/distilGPT-Nepali with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use raygx/distilGPT-Nepali with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="raygx/distilGPT-Nepali")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("raygx/distilGPT-Nepali") model = AutoModelForCausalLM.from_pretrained("raygx/distilGPT-Nepali", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use raygx/distilGPT-Nepali with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "raygx/distilGPT-Nepali" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "raygx/distilGPT-Nepali", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/raygx/distilGPT-Nepali
- SGLang
How to use raygx/distilGPT-Nepali 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 "raygx/distilGPT-Nepali" \ --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": "raygx/distilGPT-Nepali", "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 "raygx/distilGPT-Nepali" \ --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": "raygx/distilGPT-Nepali", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use raygx/distilGPT-Nepali with Docker Model Runner:
docker model run hf.co/raygx/distilGPT-Nepali
Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -18,8 +18,8 @@
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized":
|
| 22 |
-
"special":
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50001,
|
|
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"special": false
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 50001,
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
-
"model_max_length":
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|