Instructions to use DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it with Transformers:

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

pipe = pipeline("text-generation", model="DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it")
model = AutoModelForCausalLM.from_pretrained("DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it

SGLang

How to use DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it 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 "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it" \
    --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": "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it",
		"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 "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it" \
        --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": "DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it with Docker Model Runner:
```
docker model run hf.co/DeL-TaiseiOzaki/Tengentoppa-llm-jp-13B-reasoning-it
```

Tengentoppa-llm-jp-13B-reasoning-it / tokenizer_config.json

DeL-TaiseiOzaki

Upload merged model with VLLM support

ed2e6d1 verified over 1 year ago

Raw

History Blame Contribute Delete

7.45 kB

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "<MASK\|LLM-jp>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"4": {
	"content": "<PAD\|LLM-jp>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"5": {
	"content": "<CLS\|LLM-jp>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"6": {
	"content": "<SEP\|LLM-jp>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"7": {
	"content": "<EOD\|LLM-jp>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"99574": {
	"content": "<\|SYSTEM\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99575": {
	"content": "<\|WARNING\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99576": {
	"content": "</\|NOTE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99577": {
	"content": "</\|ASSISTANT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99578": {
	"content": "<\|REFERENCE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99579": {
	"content": "<\|ASSISTANT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99580": {
	"content": "</\|RESPONSE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99581": {
	"content": "<\|RESPONSE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99582": {
	"content": "<\|EXAMPLE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99583": {
	"content": "<\|HINT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99584": {
	"content": "</\|SYSTEM\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99585": {
	"content": "</\|USER\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99586": {
	"content": "</\|CONTEXT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99587": {
	"content": "</\|EXAMPLE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99588": {
	"content": "</\|IMPORTANT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99589": {
	"content": "</\|REASONING\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99590": {
	"content": "<\|USER\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99591": {
	"content": "<\|SOLUTION\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99592": {
	"content": "</\|WARNING\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99593": {
	"content": "<\|REASONING\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99594": {
	"content": "</\|ERROR\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99595": {
	"content": "</\|HINT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99596": {
	"content": "<\|CONTEXT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99597": {
	"content": "<\|IMPORTANT\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99598": {
	"content": "<\|NOTE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99599": {
	"content": "<\|ERROR\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99600": {
	"content": "</\|SOLUTION\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"99601": {
	"content": "</\|REFERENCE\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	}
	},
	"bos_token": "<s>",
	"chat_template": "{% for message in messages %}\n{%- if message['role'] == 'system' -%}\n<\|SYSTEM\|>{{ message['content'] }}</\|SYSTEM\|>\n{%- elif message['role'] == 'user' -%}\n<\|USER\|>{{ message['content'] }}</\|USER\|>\n{%- elif message['role'] == 'hint' -%}\n<\|HINT\|>{{ message['content'] }}</\|HINT\|>\n{%- elif message['role'] == 'reasoning' -%}\n<\|REASONING\|>{{ message['content'] }}</\|REASONING\|>\n{%- elif message['role'] == 'assistant' -%}\n<\|ASSISTANT\|>{{ message['content'] }}</\|ASSISTANT\|>\n{%- endif -%}\n{% endfor %}\n{%- if add_generation_prompt -%}\n<\|ASSISTANT\|>\n{%- endif -%}",
	"clean_up_tokenization_spaces": false,
	"cls_token": "<CLS\|LLM-jp>",
	"eod_token": "</s>",
	"eos_token": "</s>",
	"extra_ids": 0,
	"extra_special_tokens": {},
	"mask_token": "<MASK\|LLM-jp>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<PAD\|LLM-jp>",
	"sep_token": "<SEP\|LLM-jp>",
	"sp_model_kwargs": {},
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "<unk>"
	}