Instructions to use mrcha033/YunMin-tokenizer-96k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mrcha033/YunMin-tokenizer-96k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mrcha033/YunMin-tokenizer-96k")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mrcha033/YunMin-tokenizer-96k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mrcha033/YunMin-tokenizer-96k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mrcha033/YunMin-tokenizer-96k" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mrcha033/YunMin-tokenizer-96k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mrcha033/YunMin-tokenizer-96k
- SGLang
How to use mrcha033/YunMin-tokenizer-96k 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 "mrcha033/YunMin-tokenizer-96k" \ --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": "mrcha033/YunMin-tokenizer-96k", "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 "mrcha033/YunMin-tokenizer-96k" \ --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": "mrcha033/YunMin-tokenizer-96k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mrcha033/YunMin-tokenizer-96k with Docker Model Runner:
docker model run hf.co/mrcha033/YunMin-tokenizer-96k
Upload folder using huggingface_hub
Browse files- YunMin-tokenizer-96k.model +3 -0
- YunMin-tokenizer-96k.vocab +0 -0
- config.json +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +8 -0
YunMin-tokenizer-96k.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a4e5ab876585a64071833b33ceab083c9e3ad3b2e43cfa719e2067540a34d8
|
| 3 |
+
size 2139282
|
YunMin-tokenizer-96k.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert"
|
| 3 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "<pad>"
|
| 6 |
+
}
|
| 7 |
+
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "sentencepiece",
|
| 3 |
+
"unk_token": "<unk>",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>"
|
| 7 |
+
}
|
| 8 |
+
|