Instructions to use huranokuma/es with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huranokuma/es with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huranokuma/es")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huranokuma/es") model = AutoModelForCausalLM.from_pretrained("huranokuma/es") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use huranokuma/es with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huranokuma/es" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huranokuma/es", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huranokuma/es
- SGLang
How to use huranokuma/es 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 "huranokuma/es" \ --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": "huranokuma/es", "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 "huranokuma/es" \ --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": "huranokuma/es", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huranokuma/es with Docker Model Runner:
docker model run hf.co/huranokuma/es
Commit ·
49ee59d
1
Parent(s): 6230b4c
Upload tokenizer_config.json
Browse files- tokenizer_config.json +16 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"extra_ids": 0,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"name_or_path": "rinna/japanese-gpt2-medium",
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82",
|
| 14 |
+
"tokenizer_class": "T5Tokenizer",
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|