Instructions to use MachadoDeCastro/krull-micro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MachadoDeCastro/krull-micro with Transformers:

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

pipe = pipeline("text-generation", model="MachadoDeCastro/krull-micro")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("MachadoDeCastro/krull-micro")
model = AutoModelForMaskedLM.from_pretrained("MachadoDeCastro/krull-micro", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MachadoDeCastro/krull-micro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MachadoDeCastro/krull-micro

SGLang

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

Docker Model Runner
How to use MachadoDeCastro/krull-micro with Docker Model Runner:
```
docker model run hf.co/MachadoDeCastro/krull-micro
```

krull-micro / tokenizer.json

MachadoDeCastro

Upload folder using huggingface_hub

57dddf6 verified 4 months ago

Raw

History Blame Contribute Delete

19.8 kB

	{
	"version": "1.0",
	"truncation": null,
	"padding": null,
	"added_tokens": [
	{
	"id": 0,
	"content": "<pad>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 1,
	"content": "<unk>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 2,
	"content": "<bos>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 3,
	"content": "<eos>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	}
	],
	"normalizer": null,
	"pre_tokenizer": {
	"type": "ByteLevel",
	"add_prefix_space": false,
	"trim_offsets": true,
	"use_regex": true
	},
	"post_processor": {
	"type": "ByteLevel",
	"add_prefix_space": true,
	"trim_offsets": false,
	"use_regex": true
	},
	"decoder": {
	"type": "ByteLevel",
	"add_prefix_space": true,
	"trim_offsets": true,
	"use_regex": true
	},
	"model": {
	"type": "BPE",
	"dropout": null,
	"unk_token": "<unk>",
	"continuing_subword_prefix": null,
	"end_of_word_suffix": null,
	"fuse_unk": false,
	"byte_fallback": false,
	"ignore_merges": false,
	"vocab": {
	"<pad>": 0,
	"<unk>": 1,
	"<bos>": 2,
	"<eos>": 3,
	",": 4,
	".": 5,
	"A": 6,
	"E": 7,
	"K": 8,
	"S": 9,
	"T": 10,
	"a": 11,
	"b": 12,
	"c": 13,
	"d": 14,
	"e": 15,
	"f": 16,
	"g": 17,
	"h": 18,
	"i": 19,
	"k": 20,
	"l": 21,
	"m": 22,
	"n": 23,
	"o": 24,
	"p": 25,
	"q": 26,
	"r": 27,
	"s": 28,
	"t": 29,
	"u": 30,
	"v": 31,
	"w": 32,
	"x": 33,
	"y": 34,
	"Ċ": 35,
	"Ġ": 36,
	"an": 37,
	"Ġt": 38,
	"ed": 39,
	"en": 40,
	"Ġm": 41,
	"he": 42,
	"Ġs": 43,
	"at": 44,
	"ge": 45,
	"ic": 46,
	"ll": 47,
	"de": 48,
	"er": 49,
	"Ġc": 50,
	"Ġl": 51,
	"in": 52,
	"io": 53,
	"is": 54,
	"or": 55,
	"Ġan": 56,
	"ent": 57,
	"al": 58,
	"ar": 59,
	"es": 60,
	"om": 61,
	"us": 62,
	"Ġa": 63,
	"Ġf": 64,
	"Ġthe": 65,
	"Ġmo": 66,
	"Ġand": 67,
	"The": 68,
	"ac": 69,
	"age": 70,
	"pr": 71,
	"ull": 72,
	"Ġb": 73,
	"Ġw": 74,
	"Ġde": 75,
	"Ġpr": 76,
	"Ġto": 77,
	"edic": 78,
	"Ġst": 79,
	"del": 80,
	"ion": 81,
	"ist": 82,
	"Ġmodel": 83,
	"Kr": 84,
	"all": 85,
	"dent": 86,
	"ef": 87,
	"em": 88,
	"ex": 89,
	"ear": 90,
	"gu": 91,
	"gen": 92,
	"it": 93,
	"ken": 94,
	"mall": 95,
	"ow": 96,
	"ran": 97,
	"rom": 98,
	"sf": 99,
	"te": 100,
	"udent": 101,
	"ved": 102,
	"vic": 103,
	"Ġd": 104,
	"Ġh": 105,
	"Ġr": 106,
	"Ġin": 107,
	"angu": 108,
	"edge": 109,
	"Ġso": 110,
	"Ġcan": 111,
	"Ġcom": 112,
	"Ġlangu": 113,
	"ory": 114,
	"Ġfrom": 115,
	"Ġdevic": 116,
	"Ġpredic": 117,
	"Ġtoken": 118,
	"Ġstudent": 119,
	"Krull": 120,
	"ext": 121,
	"owl": 122,
	"ransf": 123,
	"Ġcomp": 124,
	"Ġlanguage": 125,
	"Ġdevices": 126,
	"Ġpredict": 127,
	"Ar": 128,
	"Ed": 129,
	"Small": 130,
	"Transf": 131,
	"ab": 132,
	"ap": 133,
	"as": 134,
	"av": 135,
	"ain": 136,
	"aus": 137,
	"bs": 138,
	"bed": 139,
	"ce": 140,
	"ch": 141,
	"ci": 142,
	"dd": 143,
	"din": 144,
	"et": 145,
	"ev": 146,
	"eac": 147,
	"ft": 148,
	"fic": 149,
	"gn": 150,
	"gs": 151,
	"hen": 152,
	"il": 153,
	"im": 154,
	"iv": 155,
	"ill": 156,
	"ial": 157,
	"igen": 158,
	"idd": 159,
	"iet": 160,
	"ific": 161,
	"ign": 162,
	"kn": 163,
	"lowl": 164,
	"mer": 165,
	"ment": 166,
	"medic": 167,
	"ns": 168,
	"next": 169,
	"obs": 170,
	"qu": 171,
	"rain": 172,
	"ss": 173,
	"sis": 174,
	"sign": 175,
	"tent": 176,
	"tific": 177,
	"ul": 178,
	"ute": 179,
	"ysis": 180,
	"Ġat": 181,
	"Ġis": 182,
	"Ġus": 183,
	"Ġem": 184,
	"Ġgen": 185,
	"Ġedge": 186,
	"ĠKrull": 187,
	"Ġkn": 188,
	"Ġnext": 189,
	"Ġobs": 190,
	"Ġqu": 191,
	"ank": 192,
	"anage": 193,
	"Ġtin": 194,
	"Ġtext": 195,
	"Ġtransf": 196,
	"Ġteac": 197,
	"Ġtrain": 198,
	"Ġmic": 199,
	"Ġmus": 200,
	"Ġmem": 201,
	"Ġmap": 202,
	"Ġmanage": 203,
	"her": 204,
	"Ġsmall": 205,
	"Ġsci": 206,
	"Ġslowl": 207,
	"ata": 208,
	"ate": 209,
	"ater": 210,
	"ates": 211,
	"ation": 212,
	"atory": 213,
	"lligen": 214,
	"ers": 215,
	"erved": 216,
	"erate": 217,
	"Ġcar": 218,
	"Ġcaus": 219,
	"Ġlar": 220,
	"Ġlear": 221,
	"Ġlab": 222,
	"Ġlim": 223,
	"ious": 224,
	"iomedic": 225,
	"ormer": 226,
	"oratory": 227,
	"Ġanal": 228,
	"entist": 229,
	"esear": 230,
	"Ġass": 231,
	"Ġfor": 232,
	"Ġfac": 233,
	"Ġmoved": 234,
	"act": 235,
	"ully": 236,
	"Ġbe": 237,
	"Ġbank": 238,
	"Ġbiomedic": 239,
	"Ġwas": 240,
	"Ġwhen": 241,
	"Ġwater": 242,
	"Ġdesign": 243,
	"Ġprev": 244,
	"Ġstates": 245,
	"ions": 246,
	"istill": 247,
	"Ġmodels": 248,
	"eful": 249,
	"efully": 250,
	"ity": 251,
	"ited": 252,
	"telligen": 253,
	"Ġdata": 254,
	"Ġdistill": 255,
	"Ġhav": 256,
	"Ġhidd": 257,
	"Ġriv": 258,
	"Ġresear": 259,
	"Ġintelligen": 260,
	"Ġsoft": 261,
	"Ġtokens": 262,
	"owledge": 263,
	"Ġcompute": 264,
	"Ġcompact": 265,
	"Ġpredicts": 266,
	"Ġpredictions": 267,
	"Artific": 268,
	"Edge": 269,
	"Transformer": 270,
	"beddin": 271,
	"ility": 272,
	"tention": 273,
	"Ġattention": 274,
	"Ġuseful": 275,
	"Ġembeddin": 276,
	"Ġgenerate": 277,
	"Ġknowledge": 278,
	"Ġobserved": 279,
	"Ġquiet": 280,
	"Ġtiny": 281,
	"Ġtransfers": 282,
	"Ġteacher": 283,
	"Ġtrained": 284,
	"Ġmice": 285,
	"Ġmust": 286,
	"Ġmemory": 287,
	"Ġmaps": 288,
	"Ġmanagement": 289,
	"Ġscientist": 290,
	"Ġslowly": 291,
	"Ġcarefully": 292,
	"Ġcausal": 293,
	"Ġlarge": 294,
	"Ġlearns": 295,
	"Ġlaboratory": 296,
	"Ġlimited": 297,
	"Ġanalysis": 298,
	"Ġassist": 299,
	"Ġfacility": 300,
	"Ġbiomedical": 301,
	"Ġdesigned": 302,
	"Ġprevious": 303,
	"Ġdistillation": 304,
	"Ġhave": 305,
	"Ġhidden": 306,
	"Ġriver": 307,
	"Ġresearch": 308,
	"Ġintelligence": 309,
	"Artificial": 310,
	"Ġembeddings": 311
	},
	"merges": [
	[
	"a",
	"n"
	],
	[
	"Ġ",
	"t"
	],
	[
	"e",
	"d"
	],
	[
	"e",
	"n"
	],
	[
	"Ġ",
	"m"
	],
	[
	"h",
	"e"
	],
	[
	"Ġ",
	"s"
	],
	[
	"a",
	"t"
	],
	[
	"g",
	"e"
	],
	[
	"i",
	"c"
	],
	[
	"l",
	"l"
	],
	[
	"d",
	"e"
	],
	[
	"e",
	"r"
	],
	[
	"Ġ",
	"c"
	],
	[
	"Ġ",
	"l"
	],
	[
	"i",
	"n"
	],
	[
	"i",
	"o"
	],
	[
	"i",
	"s"
	],
	[
	"o",
	"r"
	],
	[
	"Ġ",
	"an"
	],
	[
	"en",
	"t"
	],
	[
	"a",
	"l"
	],
	[
	"a",
	"r"
	],
	[
	"e",
	"s"
	],
	[
	"o",
	"m"
	],
	[
	"u",
	"s"
	],
	[
	"Ġ",
	"a"
	],
	[
	"Ġ",
	"f"
	],
	[
	"Ġt",
	"he"
	],
	[
	"Ġm",
	"o"
	],
	[
	"Ġan",
	"d"
	],
	[
	"T",
	"he"
	],
	[
	"a",
	"c"
	],
	[
	"a",
	"ge"
	],
	[
	"p",
	"r"
	],
	[
	"u",
	"ll"
	],
	[
	"Ġ",
	"b"
	],
	[
	"Ġ",
	"w"
	],
	[
	"Ġ",
	"de"
	],
	[
	"Ġ",
	"pr"
	],
	[
	"Ġt",
	"o"
	],
	[
	"ed",
	"ic"
	],
	[
	"Ġs",
	"t"
	],
	[
	"de",
	"l"
	],
	[
	"io",
	"n"
	],
	[
	"is",
	"t"
	],
	[
	"Ġmo",
	"del"
	],
	[
	"K",
	"r"
	],
	[
	"a",
	"ll"
	],
	[
	"d",
	"ent"
	],
	[
	"e",
	"f"
	],
	[
	"e",
	"m"
	],
	[
	"e",
	"x"
	],
	[
	"e",
	"ar"
	],
	[
	"g",
	"u"
	],
	[
	"g",
	"en"
	],
	[
	"i",
	"t"
	],
	[
	"k",
	"en"
	],
	[
	"m",
	"all"
	],
	[
	"o",
	"w"
	],
	[
	"r",
	"an"
	],
	[
	"r",
	"om"
	],
	[
	"s",
	"f"
	],
	[
	"t",
	"e"
	],
	[
	"u",
	"dent"
	],
	[
	"v",
	"ed"
	],
	[
	"v",
	"ic"
	],
	[
	"Ġ",
	"d"
	],
	[
	"Ġ",
	"h"
	],
	[
	"Ġ",
	"r"
	],
	[
	"Ġ",
	"in"
	],
	[
	"an",
	"gu"
	],
	[
	"ed",
	"ge"
	],
	[
	"Ġs",
	"o"
	],
	[
	"Ġc",
	"an"
	],
	[
	"Ġc",
	"om"
	],
	[
	"Ġl",
	"angu"
	],
	[
	"or",
	"y"
	],
	[
	"Ġf",
	"rom"
	],
	[
	"Ġde",
	"vic"
	],
	[
	"Ġpr",
	"edic"
	],
	[
	"Ġto",
	"ken"
	],
	[
	"Ġst",
	"udent"
	],
	[
	"Kr",
	"ull"
	],
	[
	"ex",
	"t"
	],
	[
	"ow",
	"l"
	],
	[
	"ran",
	"sf"
	],
	[
	"Ġcom",
	"p"
	],
	[
	"Ġlangu",
	"age"
	],
	[
	"Ġdevic",
	"es"
	],
	[
	"Ġpredic",
	"t"
	],
	[
	"A",
	"r"
	],
	[
	"E",
	"d"
	],
	[
	"S",
	"mall"
	],
	[
	"T",
	"ransf"
	],
	[
	"a",
	"b"
	],
	[
	"a",
	"p"
	],
	[
	"a",
	"s"
	],
	[
	"a",
	"v"
	],
	[
	"a",
	"in"
	],
	[
	"a",
	"us"
	],
	[
	"b",
	"s"
	],
	[
	"b",
	"ed"
	],
	[
	"c",
	"e"
	],
	[
	"c",
	"h"
	],
	[
	"c",
	"i"
	],
	[
	"d",
	"d"
	],
	[
	"d",
	"in"
	],
	[
	"e",
	"t"
	],
	[
	"e",
	"v"
	],
	[
	"e",
	"ac"
	],
	[
	"f",
	"t"
	],
	[
	"f",
	"ic"
	],
	[
	"g",
	"n"
	],
	[
	"g",
	"s"
	],
	[
	"h",
	"en"
	],
	[
	"i",
	"l"
	],
	[
	"i",
	"m"
	],
	[
	"i",
	"v"
	],
	[
	"i",
	"ll"
	],
	[
	"i",
	"al"
	],
	[
	"i",
	"gen"
	],
	[
	"i",
	"dd"
	],
	[
	"i",
	"et"
	],
	[
	"i",
	"fic"
	],
	[
	"i",
	"gn"
	],
	[
	"k",
	"n"
	],
	[
	"l",
	"owl"
	],
	[
	"m",
	"er"
	],
	[
	"m",
	"ent"
	],
	[
	"m",
	"edic"
	],
	[
	"n",
	"s"
	],
	[
	"n",
	"ext"
	],
	[
	"o",
	"bs"
	],
	[
	"q",
	"u"
	],
	[
	"r",
	"ain"
	],
	[
	"s",
	"s"
	],
	[
	"s",
	"is"
	],
	[
	"s",
	"ign"
	],
	[
	"t",
	"ent"
	],
	[
	"t",
	"ific"
	],
	[
	"u",
	"l"
	],
	[
	"u",
	"te"
	],
	[
	"y",
	"sis"
	],
	[
	"Ġ",
	"at"
	],
	[
	"Ġ",
	"is"
	],
	[
	"Ġ",
	"us"
	],
	[
	"Ġ",
	"em"
	],
	[
	"Ġ",
	"gen"
	],
	[
	"Ġ",
	"edge"
	],
	[
	"Ġ",
	"Krull"
	],
	[
	"Ġ",
	"kn"
	],
	[
	"Ġ",
	"next"
	],
	[
	"Ġ",
	"obs"
	],
	[
	"Ġ",
	"qu"
	],
	[
	"an",
	"k"
	],
	[
	"an",
	"age"
	],
	[
	"Ġt",
	"in"
	],
	[
	"Ġt",
	"ext"
	],
	[
	"Ġt",
	"ransf"
	],
	[
	"Ġt",
	"eac"
	],
	[
	"Ġt",
	"rain"
	],
	[
	"Ġm",
	"ic"
	],
	[
	"Ġm",
	"us"
	],
	[
	"Ġm",
	"em"
	],
	[
	"Ġm",
	"ap"
	],
	[
	"Ġm",
	"anage"
	],
	[
	"he",
	"r"
	],
	[
	"Ġs",
	"mall"
	],
	[
	"Ġs",
	"ci"
	],
	[
	"Ġs",
	"lowl"
	],
	[
	"at",
	"a"
	],
	[
	"at",
	"e"
	],
	[
	"at",
	"er"
	],
	[
	"at",
	"es"
	],
	[
	"at",
	"ion"
	],
	[
	"at",
	"ory"
	],
	[
	"ll",
	"igen"
	],
	[
	"er",
	"s"
	],
	[
	"er",
	"ved"
	],
	[
	"er",
	"ate"
	],
	[
	"Ġc",
	"ar"
	],
	[
	"Ġc",
	"aus"
	],
	[
	"Ġl",
	"ar"
	],
	[
	"Ġl",
	"ear"
	],
	[
	"Ġl",
	"ab"
	],
	[
	"Ġl",
	"im"
	],
	[
	"io",
	"us"
	],
	[
	"io",
	"medic"
	],
	[
	"or",
	"mer"
	],
	[
	"or",
	"atory"
	],
	[
	"Ġan",
	"al"
	],
	[
	"ent",
	"ist"
	],
	[
	"es",
	"ear"
	],
	[
	"Ġa",
	"ss"
	],
	[
	"Ġf",
	"or"
	],
	[
	"Ġf",
	"ac"
	],
	[
	"Ġmo",
	"ved"
	],
	[
	"ac",
	"t"
	],
	[
	"ull",
	"y"
	],
	[
	"Ġb",
	"e"
	],
	[
	"Ġb",
	"ank"
	],
	[
	"Ġb",
	"iomedic"
	],
	[
	"Ġw",
	"as"
	],
	[
	"Ġw",
	"hen"
	],
	[
	"Ġw",
	"ater"
	],
	[
	"Ġde",
	"sign"
	],
	[
	"Ġpr",
	"ev"
	],
	[
	"Ġst",
	"ates"
	],
	[
	"ion",
	"s"
	],
	[
	"ist",
	"ill"
	],
	[
	"Ġmodel",
	"s"
	],
	[
	"ef",
	"ul"
	],
	[
	"ef",
	"ully"
	],
	[
	"it",
	"y"
	],
	[
	"it",
	"ed"
	],
	[
	"te",
	"lligen"
	],
	[
	"Ġd",
	"ata"
	],
	[
	"Ġd",
	"istill"
	],
	[
	"Ġh",
	"av"
	],
	[
	"Ġh",
	"idd"
	],
	[
	"Ġr",
	"iv"
	],
	[
	"Ġr",
	"esear"
	],
	[
	"Ġin",
	"telligen"
	],
	[
	"Ġso",
	"ft"
	],
	[
	"Ġtoken",
	"s"
	],
	[
	"owl",
	"edge"
	],
	[
	"Ġcomp",
	"ute"
	],
	[
	"Ġcomp",
	"act"
	],
	[
	"Ġpredict",
	"s"
	],
	[
	"Ġpredict",
	"ions"
	],
	[
	"Ar",
	"tific"
	],
	[
	"Ed",
	"ge"
	],
	[
	"Transf",
	"ormer"
	],
	[
	"bed",
	"din"
	],
	[
	"il",
	"ity"
	],
	[
	"tent",
	"ion"
	],
	[
	"Ġat",
	"tention"
	],
	[
	"Ġus",
	"eful"
	],
	[
	"Ġem",
	"beddin"
	],
	[
	"Ġgen",
	"erate"
	],
	[
	"Ġkn",
	"owledge"
	],
	[
	"Ġobs",
	"erved"
	],
	[
	"Ġqu",
	"iet"
	],
	[
	"Ġtin",
	"y"
	],
	[
	"Ġtransf",
	"ers"
	],
	[
	"Ġteac",
	"her"
	],
	[
	"Ġtrain",
	"ed"
	],
	[
	"Ġmic",
	"e"
	],
	[
	"Ġmus",
	"t"
	],
	[
	"Ġmem",
	"ory"
	],
	[
	"Ġmap",
	"s"
	],
	[
	"Ġmanage",
	"ment"
	],
	[
	"Ġsci",
	"entist"
	],
	[
	"Ġslowl",
	"y"
	],
	[
	"Ġcar",
	"efully"
	],
	[
	"Ġcaus",
	"al"
	],
	[
	"Ġlar",
	"ge"
	],
	[
	"Ġlear",
	"ns"
	],
	[
	"Ġlab",
	"oratory"
	],
	[
	"Ġlim",
	"ited"
	],
	[
	"Ġanal",
	"ysis"
	],
	[
	"Ġass",
	"ist"
	],
	[
	"Ġfac",
	"ility"
	],
	[
	"Ġbiomedic",
	"al"
	],
	[
	"Ġdesign",
	"ed"
	],
	[
	"Ġprev",
	"ious"
	],
	[
	"Ġdistill",
	"ation"
	],
	[
	"Ġhav",
	"e"
	],
	[
	"Ġhidd",
	"en"
	],
	[
	"Ġriv",
	"er"
	],
	[
	"Ġresear",
	"ch"
	],
	[
	"Ġintelligen",
	"ce"
	],
	[
	"Artific",
	"ial"
	],
	[
	"Ġembeddin",
	"gs"
	]
	]
	}
	}