Instructions to use tiny-random/kormo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/kormo with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/kormo", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tiny-random/kormo", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tiny-random/kormo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/kormo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/kormo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/kormo

SGLang

How to use tiny-random/kormo 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 "tiny-random/kormo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/kormo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tiny-random/kormo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/kormo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/kormo with Docker Model Runner:
```
docker model run hf.co/tiny-random/kormo
```

kormo / tokenizer_config.json

yujiepan

Upload folder using huggingface_hub

a52c335 verified 7 months ago

raw

history blame contribute delete

8.33 kB

	{
	"added_tokens_decoder": {
	"125000": {
	"content": "\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125001": {
	"content": "\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125002": {
	"content": "\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125003": {
	"content": "\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125004": {
	"content": "\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125005": {
	"content": "\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125006": {
	"content": "\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125007": {
	"content": "\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125008": {
	"content": "\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125009": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125010": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125011": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125012": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125013": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125014": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125015": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125016": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125017": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125018": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125019": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125020": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125021": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125022": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125023": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125024": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125025": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125026": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125027": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125028": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125029": {
	"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125030": {
	"content": "<\|BOS\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"125031": {
	"content": "<\|EOS\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"125032": {
	"content": "<\|PAD\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"125033": {
	"content": "<think>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125034": {
	"content": "</think>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125035": {
	"content": "<tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125036": {
	"content": "</tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125037": {
	"content": "<tool_response>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125038": {
	"content": "</tool_response>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"125039": {
	"content": "<\|BOT\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"125040": {
	"content": "<\|EOT\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"bos_token": "<\|BOS\|>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|EOT\|>",
	"extra_special_tokens": {},
	"model_input_names": [
	"input_ids",
	"attention_mask"
	],
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|PAD\|>",
	"tokenizer_class": "PreTrainedTokenizerFast"
	}