Instructions to use juancopi81/mmmbachbar_4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juancopi81/mmmbachbar_4b with Transformers:

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

pipe = pipeline("text-generation", model="juancopi81/mmmbachbar_4b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("juancopi81/mmmbachbar_4b")
model = AutoModelForCausalLM.from_pretrained("juancopi81/mmmbachbar_4b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use juancopi81/mmmbachbar_4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juancopi81/mmmbachbar_4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juancopi81/mmmbachbar_4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/juancopi81/mmmbachbar_4b

SGLang

How to use juancopi81/mmmbachbar_4b 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 "juancopi81/mmmbachbar_4b" \
    --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": "juancopi81/mmmbachbar_4b",
		"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 "juancopi81/mmmbachbar_4b" \
        --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": "juancopi81/mmmbachbar_4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use juancopi81/mmmbachbar_4b with Docker Model Runner:
```
docker model run hf.co/juancopi81/mmmbachbar_4b
```

mmmbachbar_4b / tokenizer.json

juancopi81

Upload tokenizer.json with huggingface_hub

b15a568 over 3 years ago

Raw

History Blame Contribute Delete

5.82 kB

	{
	"version": "1.0",
	"truncation": null,
	"padding": null,
	"added_tokens": [
	{
	"id": 0,
	"content": "[UNK]",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 1,
	"content": "[CLS]",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 2,
	"content": "[SEP]",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 3,
	"content": "[PAD]",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 4,
	"content": "[MASK]",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	}
	],
	"normalizer": null,
	"pre_tokenizer": {
	"type": "WhitespaceSplit"
	},
	"post_processor": null,
	"decoder": null,
	"model": {
	"type": "WordLevel",
	"vocab": {
	"[UNK]": 0,
	"[CLS]": 1,
	"[SEP]": 2,
	"[PAD]": 3,
	"[MASK]": 4,
	"BAR_END": 5,
	"BAR_START": 6,
	"FILL_IN": 7,
	"TIME_DELTA=4.0": 8,
	"TIME_DELTA=2.0": 9,
	"TRACK_END": 10,
	"TRACK_START": 11,
	"DENSITY=0": 12,
	"FILL_END": 13,
	"FILL_START": 14,
	"INST=0": 15,
	"INST=1": 16,
	"INST=2": 17,
	"INST=3": 18,
	"PIECE_START": 19,
	"NOTE_OFF=57": 20,
	"NOTE_ON=57": 21,
	"NOTE_OFF=55": 22,
	"NOTE_ON=55": 23,
	"NOTE_OFF=59": 24,
	"NOTE_ON=59": 25,
	"NOTE_OFF=54": 26,
	"NOTE_ON=54": 27,
	"NOTE_OFF=52": 28,
	"NOTE_ON=52": 29,
	"NOTE_OFF=56": 30,
	"NOTE_ON=56": 31,
	"NOTE_OFF=58": 32,
	"NOTE_ON=58": 33,
	"NOTE_OFF=53": 34,
	"NOTE_ON=53": 35,
	"NOTE_OFF=60": 36,
	"NOTE_ON=60": 37,
	"NOTE_OFF=50": 38,
	"NOTE_ON=50": 39,
	"NOTE_OFF=62": 40,
	"NOTE_ON=62": 41,
	"NOTE_OFF=61": 42,
	"NOTE_ON=61": 43,
	"TIME_DELTA=1.0": 44,
	"DENSITY=1": 45,
	"NOTE_OFF=51": 46,
	"NOTE_ON=51": 47,
	"NOTE_OFF=48": 48,
	"NOTE_ON=48": 49,
	"NOTE_OFF=64": 50,
	"NOTE_ON=64": 51,
	"NOTE_OFF=63": 52,
	"NOTE_ON=63": 53,
	"NOTE_OFF=49": 54,
	"NOTE_ON=49": 55,
	"TIME_DELTA=8.0": 56,
	"NOTE_OFF=47": 57,
	"NOTE_ON=47": 58,
	"NOTE_OFF=45": 59,
	"NOTE_ON=45": 60,
	"NOTE_OFF=46": 61,
	"NOTE_ON=46": 62,
	"NOTE_OFF=65": 63,
	"NOTE_ON=65": 64,
	"NOTE_OFF=66": 65,
	"NOTE_ON=66": 66,
	"NOTE_OFF=67": 67,
	"NOTE_ON=67": 68,
	"NOTE_OFF=43": 69,
	"NOTE_ON=43": 70,
	"NOTE_OFF=44": 71,
	"NOTE_ON=44": 72,
	"NOTE_OFF=42": 73,
	"NOTE_ON=42": 74,
	"NOTE_OFF=69": 75,
	"NOTE_ON=69": 76,
	"NOTE_OFF=68": 77,
	"NOTE_ON=68": 78,
	"NOTE_OFF=41": 79,
	"NOTE_ON=41": 80,
	"DENSITY=4": 81,
	"NOTE_OFF=40": 82,
	"NOTE_ON=40": 83,
	"NOTE_OFF=71": 84,
	"NOTE_ON=71": 85,
	"NOTE_OFF=70": 86,
	"NOTE_ON=70": 87,
	"TIME_DELTA=6.0": 88,
	"NOTE_OFF=39": 89,
	"NOTE_ON=39": 90,
	"NOTE_OFF=38": 91,
	"NOTE_ON=38": 92,
	"DENSITY=2": 93,
	"NOTE_OFF=72": 94,
	"NOTE_ON=72": 95,
	"TIME_DELTA=12.0": 96,
	"DENSITY=3": 97,
	"NOTE_OFF=73": 98,
	"NOTE_ON=73": 99,
	"NOTE_OFF=37": 100,
	"NOTE_ON=37": 101,
	"NOTE_OFF=74": 102,
	"NOTE_ON=74": 103,
	"NOTE_OFF=36": 104,
	"NOTE_ON=36": 105,
	"NOTE_OFF=35": 106,
	"NOTE_ON=35": 107,
	"NOTE_OFF=76": 108,
	"NOTE_ON=76": 109,
	"NOTE_OFF=75": 110,
	"NOTE_ON=75": 111,
	"NOTE_OFF=34": 112,
	"NOTE_ON=34": 113,
	"NOTE_OFF=33": 114,
	"NOTE_ON=33": 115,
	"NOTE_OFF=77": 116,
	"NOTE_ON=77": 117,
	"NOTE_OFF=78": 118,
	"NOTE_ON=78": 119,
	"NOTE_OFF=79": 120,
	"NOTE_ON=79": 121,
	"NOTE_OFF=31": 122,
	"NOTE_ON=31": 123,
	"NOTE_OFF=80": 124,
	"NOTE_ON=80": 125,
	"NOTE_OFF=81": 126,
	"NOTE_ON=81": 127,
	"NOTE_OFF=32": 128,
	"NOTE_ON=32": 129,
	"TIME_DELTA=3.0": 130,
	"INST=4": 131,
	"NOTE_OFF=82": 132,
	"NOTE_ON=82": 133,
	"INST=5": 134,
	"INST=6": 135,
	"NOTE_OFF=83": 136,
	"NOTE_ON=83": 137,
	"NOTE_OFF=30": 138,
	"NOTE_ON=30": 139,
	"NOTE_OFF=84": 140,
	"NOTE_ON=84": 141,
	"INST=7": 142,
	"NOTE_OFF=29": 143,
	"NOTE_ON=29": 144,
	"NOTE_OFF=85": 145,
	"NOTE_ON=85": 146,
	"TIME_DELTA=0.5": 147,
	"NOTE_OFF=86": 148,
	"NOTE_ON=86": 149,
	"NOTE_OFF=28": 150,
	"NOTE_ON=28": 151,
	"NOTE_OFF=27": 152,
	"NOTE_ON=27": 153,
	"NOTE_OFF=26": 154,
	"NOTE_ON=26": 155,
	"NOTE_OFF=87": 156,
	"NOTE_ON=87": 157,
	"TIME_DELTA=16.0": 158,
	"TIME_DELTA=10.0": 159,
	"NOTE_OFF=88": 160,
	"NOTE_ON=88": 161,
	"INST=10": 162,
	"INST=11": 163,
	"INST=12": 164,
	"INST=13": 165,
	"INST=14": 166,
	"INST=8": 167,
	"INST=9": 168,
	"NOTE_OFF=89": 169,
	"NOTE_ON=89": 170,
	"NOTE_OFF=90": 171,
	"NOTE_ON=90": 172,
	"NOTE_OFF=24": 173,
	"NOTE_OFF=25": 174,
	"NOTE_ON=24": 175,
	"NOTE_ON=25": 176,
	"NOTE_OFF=91": 177,
	"NOTE_ON=91": 178,
	"NOTE_OFF=92": 179,
	"NOTE_OFF=93": 180,
	"NOTE_ON=92": 181,
	"NOTE_ON=93": 182,
	"NOTE_OFF=94": 183,
	"NOTE_OFF=95": 184,
	"NOTE_ON=94": 185,
	"NOTE_ON=95": 186,
	"NOTE_OFF=96": 187,
	"NOTE_ON=96": 188
	},
	"unk_token": "[UNK]"
	}
	}