Instructions to use tomg-group-umd/step-00006144-recurrence_full_512_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomg-group-umd/step-00006144-recurrence_full_512_0 with Transformers:

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

pipe = pipeline("text-generation", model="tomg-group-umd/step-00006144-recurrence_full_512_0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tomg-group-umd/step-00006144-recurrence_full_512_0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tomg-group-umd/step-00006144-recurrence_full_512_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tomg-group-umd/step-00006144-recurrence_full_512_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomg-group-umd/step-00006144-recurrence_full_512_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tomg-group-umd/step-00006144-recurrence_full_512_0

SGLang

How to use tomg-group-umd/step-00006144-recurrence_full_512_0 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 "tomg-group-umd/step-00006144-recurrence_full_512_0" \
    --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": "tomg-group-umd/step-00006144-recurrence_full_512_0",
		"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 "tomg-group-umd/step-00006144-recurrence_full_512_0" \
        --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": "tomg-group-umd/step-00006144-recurrence_full_512_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tomg-group-umd/step-00006144-recurrence_full_512_0 with Docker Model Runner:
```
docker model run hf.co/tomg-group-umd/step-00006144-recurrence_full_512_0
```

step-00006144-recurrence_full_512_0 / tokenizer_config.json

JonasGeiping

Upload tokenizer

05323d0 verified over 1 year ago

Raw History Blame Contribute Delete

6.62 kB

	{
	"added_tokens_decoder": {
	"65504": {
	"content": "<\|begin_text\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65505": {
	"content": "<\|end_text\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65506": {
	"content": "<\|begin_header\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65507": {
	"content": "<\|end_header\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65508": {
	"content": "<\|end_turn\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65509": {
	"content": "<\|pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65510": {
	"content": "<\|fim_prefix\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65511": {
	"content": "<\|fim_middle\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65512": {
	"content": "<\|fim_suffix\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65513": {
	"content": "<\|fim_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65514": {
	"content": "<\|...\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65515": {
	"content": "<\|del\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65516": {
	"content": "<\|c_0\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65517": {
	"content": "<\|c_1\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65518": {
	"content": "<\|c_2\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65519": {
	"content": "<\|c_3\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65520": {
	"content": "<\|c_4\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65521": {
	"content": "<\|c_5\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65522": {
	"content": "<\|c_6\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65523": {
	"content": "<\|c_7\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65524": {
	"content": "<\|c_8\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65525": {
	"content": "<\|c_9\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65526": {
	"content": "<\|?\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65527": {
	"content": "<\|&\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65528": {
	"content": "<\|!\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65529": {
	"content": "<\|-\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65530": {
	"content": "<\|+\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65531": {
	"content": "<\|interrupt\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65532": {
	"content": "<\|>>-\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65533": {
	"content": "<\|-<<\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65534": {
	"content": "<\|->>\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"65535": {
	"content": "<\|<<-\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"bos_token": "<\|begin_text\|>",
	"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set start_content = '<\|begin_header\|>' %}{% set end_content = message['content'] \| trim + '<\|end_turn\|>' %}{% if loop.index0 == 0 %}{% set start_content = bos_token + start_content %}{% endif %}{% if message['role'] == 'Huginn' or message['role'] == 'assistant' %}{% set start_content = start_content + 'Huginn<\|end_header\|>\n\n' %}{{ start_content }}{% generation %}{{ end_content }}{% endgeneration %}{% else %}{% set start_content = start_content + message['role'] + '<\|end_header\|>\n\n' %}{{ start_content }}{{ end_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<\|begin_header\|>Huginn<\|end_header\|>\n\n' }}{% else %}{{ '<\|end_text\|>' }}{% endif %}",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|end_text\|>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|pad\|>",
	"tokenizer_class": "PreTrainedTokenizerFast"
	}