Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
MIT License
Bot releases are visible (Hide)
Published by github-actions[bot] about 1 month ago
ollama stop
command to unload a running modelollama/ollama
container image will now start running almost immediately, leading to 5s faster start timesollama show
would show excessive whitespace in the outputFull Changelog: https://github.com/ollama/ollama/compare/v0.3.10...v0.3.11
Published by github-actions[bot] about 1 month ago
ollama show
ollama create
to import Gemma 2 models from safetensorstemperature
and frequency_penalty
Full Changelog: https://github.com/ollama/ollama/compare/v0.3.9...v0.3.10
Published by github-actions[bot] about 2 months ago
OLLAMA_HOST
will now work with with URLs that contain pathsFull Changelog: https://github.com/ollama/ollama/compare/v0.3.8...v0.3.9
ollama
CLI couldn't be found on the path when upgrading Ollama on WindowsFull Changelog: https://github.com/ollama/ollama/compare/v0.3.7...v0.3.8
Published by github-actions[bot] about 2 months ago
ollama pull
and ollama push
on slower connectionsOLLAMA_NUM_PARALLEL
would cause models to be reloaded on lower VRAM systemstar.gz
file, which contains the ollama
binary along with required libraries.Full Changelog: https://github.com/ollama/ollama/compare/v0.3.6...v0.3.7-rc5
Published by github-actions[bot] 2 months ago
/api/embed
would return an error instead of loading the model when the input
field was not provided.ollama create
can now import Phi-3 models from Safetensorsollama create
when importing GGUF filesFull Changelog: https://github.com/ollama/ollama/compare/v0.3.5...v0.3.6
Published by github-actions[bot] 2 months ago
Incorrect function
error when downloading models on WindowsFull Changelog: https://github.com/ollama/ollama/compare/v0.3.4...v0.3.5
Published by github-actions[bot] 2 months ago
/api/embed
would sometimes return embedding results out of orderFull Changelog: https://github.com/ollama/ollama/compare/v0.3.3...v0.3.4
Published by github-actions[bot] 3 months ago
/api/embed
endpoint now returns statistics: total_duration
, load_duration
, and prompt_eval_count
/v1/embeddings
OpenAI compatibility API/api/generate
would respond with an empty string if provided a context
/api/generate
would return an incorrect value for context
/show modefile
will now render MESSAGE
commands correctlyFull Changelog: https://github.com/ollama/ollama/compare/v0.3.2...v0.3.3
Published by github-actions[bot] 3 months ago
ollama pull
would not resume download progressphi3
would report an error on older versionsFull Changelog: https://github.com/ollama/ollama/compare/v0.3.1...v0.3.2
Published by github-actions[bot] 3 months ago
min_p
sampling optionollama pull
ollama create
will now autodetect required stop parameters when importing certain models/save
would cause parameters to be saved incorrectly.finish_reason
of tool_calls
if a tool call occured.Full Changelog: https://github.com/ollama/ollama/compare/v0.3.0...v0.3.1
Published by github-actions[bot] 3 months ago
Ollama now supports tool calling with popular models such as Llama 3.1. This enables a model to answer a given prompt using tool(s) it knows about, making it possible for models to perform more complex tasks or interact with the outside world.
Example tools include:
https://github.com/user-attachments/assets/957ef0d6-e7b7-4168-8033-13b0fe5f7029
To use tools, provide the tools
field when using Ollama's Chat API:
import ollama
response = ollama.chat(
model='llama3.1',
messages=[{'role': 'user', 'content': 'What is the weather in Toronto?'}],
# provide a weather checking tool to the model
tools=[{
'type': 'function',
'function': {
'name': 'get_current_weather',
'description': 'Get the current weather for a city',
'parameters': {
'type': 'object',
'properties': {
'city': {
'type': 'string',
'description': 'The name of the city',
},
},
'required': ['city'],
},
},
},
],
)
print(response['message']['tool_calls'])
More information:
ollama create
Full Changelog: https://github.com/ollama/ollama/compare/v0.2.8...v0.3.0
Published by github-actions[bot] 3 months ago
assistant
message would not be considered for continuing a responseollama create
will now validate templatesFull Changelog: https://github.com/ollama/ollama/compare/v0.2.7...v0.2.8
Published by github-actions[bot] 3 months ago
content
response fieldFull Changelog: https://github.com/ollama/ollama/compare/v0.2.6...v0.2.7
Published by github-actions[bot] 3 months ago
USER
would no longer work in the chat endpointsFull Changelog: https://github.com/ollama/ollama/compare/v0.2.5...v0.2.6
Published by github-actions[bot] 3 months ago
SYSTEM
message not be appliedFull Changelog: https://github.com/ollama/ollama/compare/v0.2.4...v0.2.5
Published by github-actions[bot] 3 months ago
context
, load_duration
and total_duration
fields would not be set in the /api/generate
endpoint.Full Changelog: https://github.com/ollama/ollama/compare/v0.2.3...v0.2.4
Published by github-actions[bot] 3 months ago
Full Changelog: https://github.com/ollama/ollama/compare/v0.2.2...v0.2.3
Published by github-actions[bot] 3 months ago
glm4
models will no longer report of memory issuesdeepseek-v2
modelsFull Changelog: https://github.com/ollama/ollama/compare/v0.2.1...v0.2.2-rc2
Published by github-actions[bot] 3 months ago
OLLAMA_NUM_PARALLEL
would cause models to be reloaded after each requestFull Changelog: https://github.com/ollama/ollama/compare/v0.2.0...v0.2.1