Create a model from a Safetensors directory

POST

http://localhost:11434/api/create

The files parameter should include a dictionary of files for the safetensors model which includes the file names and SHA256 digest of each file. Use /api/blobs/:digest to first push each of the files to the server before calling this API. Files will remain in the cache until the Ollama server is restarted.

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'http://localhost:11434/api/create' \
--header 'Content-Type: application/json' \
--data-raw ''

Response Example

{"status":"converting model"}
{"status":"creating new layer sha256:05ca5b813af4a53d2c2922933936e398958855c44ee534858fcfd830940618b6"}
{"status":"using autodetected template llama3-instruct"}
{"status":"using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb"}
{"status":"writing manifest"}
{"status":"success"}

Request

Body Params application/json

model

string

required

Model name

Example:

bert-base-chinese

files

object

required

config.json

string

required

Configuration file hash

Example:

a1b2c3d4e5f6

generation_config.json

string

required

Generate configuration file hash value

Example:

b2c3d4e5f6g7

special_tokens_map.json

string

required

Special token mapping file hash

Example:

c3d4e5f6g7h8

tokenizer.json

string

required

Word Segmentation File Hash

Example:

d4e5f6g7h8i9

tokenizer_config.json

string

required

Word Segmentation profile hash

Example:

e5f6g7h8i9j0

model.safetensors

string

required

Model weight file hash

Example:

f6g7h8i9j0k1

Examples

Responses

🟢200Success

application/json

A stream of JSON objects is returned:

Body

status

string

required

Modified at 2025-03-28 02:48:51

Create a model from GGUF

Overview