Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
MIT License
Bot releases are hidden (Show)
Published by jmorganca 7 months ago
Ollama now supports AMD graphics cards in preview on Windows and Linux. All the features are now accelerated by AMD graphics cards, and support is included by default in Ollama for Linux, Windows and Docker.
Family | Supported cards and accelerators |
---|---|
AMD Radeon RX |
7900 XTX 7900 XT 7900 GRE 7800 XT 7700 XT 7600 XT 7600 6950 XT 6900 XTX 6900XT 6800 XT 6800 Vega 64 Vega 56
|
AMD Radeon PRO |
W7900 W7800 W7700 W7600 W7500 W6900X W6800X Duo W6800X W6800 V620 V420 V340 V320 Vega II Duo Vega II VII SSG
|
AMD Instinct |
MI300X MI300A MI300 MI250X MI250 MI210 MI200 MI100 MI60 MI50
|
ollama <command> -h
will now show documentation for supported environment variablesnomic-embed-text
, all-minilm
or other embedding models would hang on LinuxFROM <directory with safetensors model>
command in the Modelfileollama run
would error when piping output to tee
and other toolsFull Changelog: https://github.com/ollama/ollama/compare/v0.1.28...v0.1.29
Published by jmorganca 8 months ago
llava
should now respond better to text promptsllava
1.6 models/api/embeddings
with an empty prompt
instead of hangingFull Changelog: https://github.com/ollama/ollama/compare/v0.1.27...v0.1.28
Published by jmorganca 8 months ago
Gemma is a new, top-performing family of lightweight open models built by Google DeepMind. Available in 2b
and 7b
parameter sizes:
ollama run gemma:2b
ollama run gemma:7b
(default)Full Changelog: https://github.com/ollama/ollama/compare/v0.1.26...v0.1.27
Published by jmorganca 8 months ago
bert
and nomic-bert
embedding modelsOLLAMA_HOST
on Windows/api/chat
endpoint/bye
or /exit
would not work with trailing spaces or characters after themFull Changelog: https://github.com/ollama/ollama/compare/v0.1.25...v0.1.26
Published by jmorganca 8 months ago
Ollama is now available on Windows in preview. Download it here. Ollama on Windows makes it possible to pull, run and create large language models in a new native Windows experience. It includes built-in GPU acceleration, access to the full model library, and the Ollama API including OpenAI compatibility.
ollama serve
wouldn't immediately quit when receiving a termination signal/api/chat
endpoint, such as where Ollama would omit the second system prompt in a series of messageskeep_alive
value (e.g. -1
) will now correctly keep the model loaded indefinitelyFull Changelog: https://github.com/ollama/ollama/compare/v0.1.24...v0.1.25
Published by jmorganca 8 months ago
This release adds initial compatibility support for the OpenAI Chat Completions API.
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "llama2",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
/api/chat
would hang when providing empty user
messages repeatedlyFull Changelog: https://github.com/ollama/ollama/compare/v0.1.23...v0.1.24
Published by jmorganca 9 months ago
The LLaVA model family on Ollama has been updated to version 1.6, and now includes a new 34b
version:
ollama run llava
A new 7B LLaVA model based on mistral.ollama run llava:13b
13B LLaVA modelollama run llava:34b
34B LLaVA model – one of the most powerful open-source vision models availableThese new models share new improvements:
keep_alive
parameter: control how long models stay loadedWhen making API requests, the new keep_alive
parameter can be used to control how long a model stays loaded in memory:
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"keep_alive": "30s"
}'
20m
, 1hr
or 30
), the model will stay loaded for the provided duration-1
), the model will stay loaded indefinitely0
, the model will be unloaded immediately once finishedTITAN X
980 Ti
980
970
960
950
750 Ti
750
980M
970M
965M
960M
950M
860M
850M
940M
930M
910M
840M
830M
M6000
M5500M
M5000
M2200
M1200
M620
M520
M60
M40
810
keep_alive
API parameter to control how long models stay loadedollama run
when running multimodal modelsollama pull
would slow down to 99%ollama serve
will now print prompt when OLLAMA_DEBUG=1
is setollama run
and the /api/chat
APIollama run
will now allow sending messages without images to multimodal modelsFull Changelog: https://github.com/ollama/ollama/compare/v0.1.22...v0.1.23
Published by jmorganca 9 months ago
Full Changelog: https://github.com/ollama/ollama/compare/v0.1.21...v0.1.22
Published by jmorganca 9 months ago
Ollama now supports CPUs without AVX. This means Ollama will now run on older CPUs and in environments (such as virtual machines, Rosetta, GitHub actions) that don't provide support for AVX instructions.
For newer CPUs that support AVX2, Ollama will receive a small performance boost, running models about 10% faster.
ollama pull
and ollama push
/show parameter
would round decimal numbersFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.20...v0.1.21
Published by jmorganca 9 months ago
3.5-0106
.out of memory
CUDA errors* Fixed issue where Nvidia GPUs would not be detected by Ollama
Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.19...v0.1.20
Published by jmorganca 9 months ago
This release focuses on performance and fixing a number issues and crashes relating to memory allocation.
llama2
, mixtral
or llama2:13b
with limited GPU memorynum_ctx
will now work (up to a model's supported context window).To use a 32K context window with Mistral:
# ollama run
/set parameter num_ctx 32678
# api
curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"options": {"num_ctx": 32678}
}'
mixtral
can now be run on Macs with less memoryollama run
OLLAMA_ORIGINS
now supports browser extension URLsFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.18...v0.1.19
Published by jmorganca 10 months ago
ollama run wizardcoder:33b
/? shortcuts
help command to ollama run
to list keyboard shortcutsollama run
or via the API.ggml
format models. If using custom ggml
format models in a Modelfile
, please import GGUF models instead.Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.17...v0.1.18
Published by jmorganca 10 months ago
This release adds support for the Phi-2 model by Microsoft.
ollama run phi
Phi-2 is a new, powerful 2.7B model with strong reasoning and language understanding capabilities comparable to larger, 13B models. Given its small size, it will run effectively on a wide set of hardware configurations.
By default, phi
includes a prompt template designed for multi-turn conversations:
% ollama run phi
>>> Hello, can you help me find my way to Toronto?
Certainly! What is the exact location in Toronto that you are looking for?
>>> Yonge & Bloor
Sure, Yonge and Bloor is a busy intersection in downtown Toronto. Would you like to take public transportation or drive there?
>>> Public transportation
Great! The easiest way to get there is by taking the TTC subway. You can take Line 1, which runs along Yonge Street and passes through downtown Toronto.
Using Ollama's API:
curl http://localhost:11434/api/chat -d '{
"model": "phi",
"messages": [
{ "role": "user", "content": "why is the sky blue?" }
]
}'
Phi also responds well to a wide variety of prompt formats when using raw mode in Ollama's API, which bypasses all default prompt templating:
curl http://localhost:11434/api/generate -d '{
"model": "phi",
"prompt": "Instruct: Write a detailed analogy between mathematics and a lighthouse.\nOutput:",
"options": {
"stop": ["Instruct:", "Output:"]
},
"raw": true,
"stream": false
}'
curl http://localhost:11434/api/generate -d '{
"model": "phi",
"prompt": "def print_prime(n):\n ",
"raw": true,
"stream": false
}'
curl http://localhost:11434/api/generate -d '{
"model": "phi",
"prompt": "There once was a mouse named",
"raw": true,
"stream": false
}'
message
objects in /api/chat
would return "images": null
in the response/api/chat
now always returns a message
object, even if content
is an empty stringFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.16...v0.1.17
Published by jmorganca 10 months ago
This release adds support for Mixtral and other models with the mixture of experts architecture:
ollama run jmorgan/mixtral
Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.15...v0.1.16
Published by jmorganca 10 months ago
Ollama now supports multimodal models that can describe what they see. To use a multimodal model with ollama run
, include the full path of a png
or jpeg
image in the prompt:
% ollama run llava
>>> What does the text in this image say? /Users/mchiang/Downloads/image.png
Added image '/Users/mchiang/Downloads/image.png'
The text in this image says "The Ollamas."
A new images
parameter has been added to the Generate API, which takes a list of base64-encoded png
or jpeg
images. Images up to 100MB in size are supported.
curl http://localhost:11434/api/generate -d '{
"model": "llava",
"prompt":"What is in this picture?",
"images": ["iVBORw0KGgoAAAANSUhEUgAAAG0AAABmCAYAAADBPx+VAAAACXBIWXMAAAsTAAALEwEAmpwYAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAA3VSURBVHgB7Z27r0zdG8fX743i1bi1ikMoFMQloXRpKFFIqI7LH4BEQ+NWIkjQuSWCRIEoULk0gsK1kCBI0IhrQVT7tz/7zZo888yz1r7MnDl7z5xvsjkzs2fP3uu71nNfa7lkAsm7d++Sffv2JbNmzUqcc8m0adOSzZs3Z+/XES4ZckAWJEGWPiCxjsQNLWmQsWjRIpMseaxcuTKpG/7HP27I8P79e7dq1ars/yL4/v27S0ejqwv+cUOGEGGpKHR37tzJCEpHV9tnT58+dXXCJDdECBE2Ojrqjh071hpNECjx4cMHVycM1Uhbv359B2F79+51586daxN/+pyRkRFXKyRDAqxEp4yMlDDzXG1NPnnyJKkThoK0VFd1ELZu3TrzXKxKfW7dMBQ6bcuWLW2v0VlHjx41z717927ba22U9APcw7Nnz1oGEPeL3m3p2mTAYYnFmMOMXybPPXv2bNIPpFZr1NHn4HMw0KRBjg9NuRw95s8PEcz/6DZELQd/09C9QGq5RsmSRybqkwHGjh07OsJSsYYm3ijPpyHzoiacg35MLdDSIS/O1yM778jOTwYUkKNHWUzUWaOsylE00MyI0fcnOwIdjvtNdW/HZwNLGg+sR1kMepSNJXmIwxBZiG8tDTpEZzKg0GItNsosY8USkxDhD0Rinuiko2gfL/RbiD2LZAjU9zKQJj8RDR0vJBR1/Phx9+PHj9Z7REF4nTZkxzX4LCXHrV271qXkBAPGfP/atWvu/PnzHe4C97F48eIsRLZ9+3a3f/9+87dwP1JxaF7/3r17ba+5l4EcaVo0lj3SBq5kGTJSQmLWMjgYNei2GPT1MuMqGTDEFHzeQSP2wi/jGnkmPJ/nhccs44jvDAxpVcxnq0F6eT8h4ni/iIWpR5lPyA6ETkNXoSukvpJAD3AsXLiwpZs49+fPn5ke4j10TqYvegSfn0OnafC+Tv9ooA/JPkgQysqQNBzagXY55nO/oa1F7qvIPWkRL12WRpMWUvpVDYmxAPehxWSe8ZEXL20sadYIozfmNch4QJPAfeJgW3rNsnzphBKNJM2KKODo1rVOMRYik5ETy3ix4qWNI81qAAirizgMIc+yhTytx0JWZuNI03qsrgWlGtwjoS9XwgUhWGyhUaRZZQNNIEwCiXD16tXcAHUs79co0vSD8rrJCIW98pzvxpAWyyo3HYwqS0+H0BjStClcZJT5coMm6D2LOF8TolGJtK9fvyZpyiC5ePFi9nc/oJU4eiEP0jVoAnHa9wyJycITMP78+eMeP37sXrx44d6+fdt6f82aNdkx1pg9e3Zb5W+RSRE+n+VjksQWifvVaTKFhn5O8my63K8Qabdv33b379/PiAP//vuvW7BggZszZ072/+TJk91YgkafPn166zXB1rQHFvouAWHq9z3SEevSUerqCn2/dDCeta2jxYbr69evk4MHDyY7d+7MjhMnTiTPnz9Pfv/+nfQT2ggpO2dMF8cghuoM7Ygj5iWCqRlGFml0QC/ftGmTmzt3rmsaKDsgBSPh0/8yPeLLBihLkOKJc0jp8H8vUzcxIA1k6QJ/c78tWEyj5P3o4u9+jywNPdJi5rAH9x0KHcl4Hg570eQp3+vHXGyrmEeigzQsQsjavXt38ujRo44LQuDDhw+TW7duRS1HGgMxhNXHgflaNTOsHyKvHK5Ijo2jbFjJBQK9YwFd6RVMzfgRBmEfP37suBBm/p49e1qjEP2mwTViNRo0VJWH1deMXcNK08uUjVUu7s/zRaL+oLNxz1bpANco4npUgX4G2eFbpDFyQoQxojBCpEGSytmOH8qrH5Q9vuzD6ofQylkCUmh8DBAr+q8JCyVNtWQIidKQE9wNtLSQnS4jDSsxNHogzFuQBw4cyM61UKVsjfr3ooBkPSqqQHesUPWVtzi9/vQi1T+rJj7WiTz4Pt/l3LxUkr5P2VYZaZ4URpsE+st/dujQoaBBYokbrz/8TJNQYLSonrPS9kUaSkPeZyj1AWSj+d+VBoy1pIWVNed8P0Ll/ee5HdGRhrHhR5GGN0r4LGZBaj8oFDJitBTJzIZgFcmU0Y8ytWMZMzJOaXUSrUs5RxKnrxmbb5YXO9VGUhtpXldhEUogFr3IzIsvlpmdosVcGVGXFWp2oU9kLFL3dEkSz6NHEY1sjSRdIuDFWEhd8KxFqsRi1uM/nz9/zpxnwlESONdg6dKlbsaMGS4EHFHtjFIDHwKOo46l4TxSuxgDzi+rE2jg+BaFruOX4HXa0Nnf1lwAPufZeF8/r6zD97WK2qFnGjBxTw5qNGPxT+5T/r7/7RawFC3j4vTp09koCxkeHjqbHJqArmH5UrFKKksnxrK7FuRIs8STfBZv+luugXZ2pR/pP9Ois4z+TiMzUUkUjD0iEi1fzX8GmXyuxUBRcaUfykV0YZnlJGKQpOiGB76x5GeWkWWJc3mOrK6S7xdND+W5N6XyaRgtWJFe13GkaZnKOsYqGdOVVVbGupsyA/l7emTLHi7vwTdirNEt0qxnzAvBFcnQF16xh/TMpUuXHDowhlA9vQVraQhkudRdzOnK+04ZSP3DUhVSP61YsaLtd/ks7ZgtPcXqPqEafHkdqa84X6aCeL7YWlv6edGFHb+ZFICPlljHhg0bKuk0CSvVznWsotRu433alNdFrqG45ejoaPCaUkWERpLXjzFL2Rpllp7PJU2a/v7Ab8N05/9t27Z16KUqoFGsxnI9EosS2niSYg9SpU6B4JgTrvVW1flt1sT+0ADIJU2maXzcUTraGCRaL1Wp9rUMk16PMom8QhruxzvZIegJjFU7LLCePfS8uaQdPny4jTTL0dbee5mYokQsXTIWNY46kuMbnt8Kmec+LGWtOVIl9cT1rCB0V8WqkjAsRwta93TbwNYoGKsUSChN44lgBNCoHLHzquYKrU6qZ8lolCIN0Rh6cP0Q3U6I6IXILYOQI513hJaSKAorFpuHXJNfVlpRtmYBk1Su1obZr5dnKAO+L10Hrj3WZW+E3qh6IszE37F6EB+68mGpvKm4eb9bFrlzrok7fvr0Kfv727dvWRmdVTJHw0qiiCUSZ6wCK+7XL/AcsgNyL74DQQ730sv78Su7+t/A36MdY0sW5o40ahslXr58aZ5HtZB8GH64m9EmMZ7FpYw4T6QnrZfgenrhFxaSiSGXtPnz57e9TkNZLvTjeqhr734CNtrK41L40sUQckmj1lGKQ0rC37x544r8eNXRpnVE3ZZY7zXo8NomiO0ZUCj2uHz58rbXoZ6gc0uA+F6ZeKS/jhRDUq8MKrTho9fEkihMmhxtBI1DxKFY9XLpVcSkfoi8JGnToZO5sU5aiDQIW716ddt7ZLYtMQlhECdBGXZZMWldY5BHm5xgAroWj4C0hbYkSc/jBmggIrXJWlZM6pSETsEPGqZOndr2uuuR5rF169a2HoHPdurUKZM4CO1WTPqaDaAd+GFGKdIQkxAn9RuEWcTRyN2KSUgiSgF5aWzPTeA/lN5rZubMmR2bE4SIC4nJoltgAV/dVefZm72AtctUCJU2CMJ327hxY9t7EHbkyJFseq+EJSY16RPo3Dkq1kkr7+q0bNmyDuLQcZBEPYmHVdOBiJyIlrRDq41YPWfXOxUysi5fvtyaj+2BpcnsUV/oSoEMOk2CQGlr4ckhBwaetBhjCwH0ZHtJROPJkyc7UjcYLDjmrH7ADTEBXFfOYmB0k9oYBOjJ8b4aOYSe7QkKcYhFlq3QYLQhSidNmtS2RATwy8YOM3EQJsUjKiaWZ+vZToUQgzhkHXudb/PW5YMHD9yZM2faPsMwoc7RciYJXbGuBqJ1UIGKKLv915jsvgtJxCZDubdXr165mzdvtr1Hz5LONA8jrUwKPqsmVesKa49S3Q4WxmRPUEYdTjgiUcfUwLx589ySJUva3oMkP6IYddq6HMS4o55xBJBUeRjzfa4Zdeg56QZ43LhxoyPo7Lf1kNt7oO8wWAbNwaYjIv5lhyS7kRf96dvm5Jah8vfvX3flyhX35cuX6HfzFHOToS1H4BenCaHvO8pr8iDuwoUL7tevX+b5ZdbBair0xkFIlFDlW4ZknEClsp/TzXyAKVOmmHWFVSbDNw1l1+4f90U6IY/q4V27dpnE9bJ+v87QEydjqx/UamVVPRG+mwkNTYN+9tjkwzEx+atCm/X9WvWtDtAb68Wy9LXa1UmvCDDIpPkyOQ5ZwSzJ4jMrvFcr0rSjOUh+GcT4LSg5ugkW1Io0/SCDQBojh0hPlaJdah+tkVYrnTZowP8iq1F1TgMBBauufyB33x1v+NWFYmT5KmppgHC+NkAgbmRkpD3yn9QIseXymoTQFGQmIOKTxiZIWpvAatenVqRVXf2nTrAWMsPnKrMZHz6bJq5jvce6QK8J1cQNgKxlJapMPdZSR64/UivS9NztpkVEdKcrs5alhhWP9NeqlfWopzhZScI6QxseegZRGeg5a8C3Re1Mfl1ScP36ddcUaMuv24iOJtz7sbUjTS4qBvKmstYJoUauiuD3k5qhyr7QdUHMeCgLa1Ear9NquemdXgmum4fvJ6w1lqsuDhNrg1qSpleJK7K3TF0Q2jSd94uSZ60kK1e3qyVpQK6PVWXp2/FC3mp6jBhKKOiY2h3gtUV64TWM6wDETRPLDfSakXmH3w8g9Jlug8ZtTt4kVF0kLUYYmCCtD/DrQ5YhMGbA9L3ucdjh0y8kOHW5gU/VEEmJTcL4Pz/f7mgoAbYkAAAAAElFTkSuQmCC"]
}'
With the new Chat API introduced in version 0.1.14
, images
can also be added to messages from the user
role:
curl http://localhost:11434/api/chat -d '{
"model": "llava",
"messages": [
{
"role": "user",
"content": "What is in this picture?",
"images": ["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"]
}
]
}'
/set template
and /set system
wouldn't work correctly in ollama run
curl http://localhost:11434/api/show -d '{ "name": "llava" }'
{
...
"details": {
"format": "gguf",
"families": [
"llama",
"clip"
],
"parameter_size": "7B",
"quantization_level": "Q4_0"
}
}
Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.14...v0.1.15
Published by jmorganca 11 months ago
curl http://localhost:11434/api/chat -d '{
"model": "mistral",
"messages": [
{ "role": "system", "content": "You are a helpful assistant that answers concisely." },
{ "role": "user", "content": "why is the sky blue?" }
]
}'
ollama run
ollama run
as expected/api/generate
would not work when waiting for another request to finishFROM
command would cause an errorOLLAMA_HOST
/api/version
API for checking Ollama's versionFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.13...v0.1.14
Published by jmorganca 11 months ago
ollama pull
with a simpler design that displays a more consistent download speed and remaining timeollama run
using /set system <system prompt>
.ollama run
using /set <parameter> <value>
. Examples:
/set parameter num_ctx 16384
/set parameter temperature 1
/set parameter seed 1048
Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.12...v0.1.13
Published by jmorganca 11 months ago
ollama run yi:34b
– the chat variant of the popular Yi 34b model ."""
) and pasting functionality inollama run
ollama run
Full Changelog: https://github.com/jmorganca/ollama/compare/v0.1.11...v0.1.12
Published by jmorganca 11 months ago
ollama create
would error with invalid cross-device link
ollama run
Ollama would exit with an error on macOS Big Sur and Montereyq5_0
and q5_1
models will now use GPUmax retries exceeded
errors when running ollama pull
or ollama push
ollama create
would result in a "file not found" error FROM
referred to local fileollama pull
would cause repeated progress bar messagesFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.10...v0.1.11
Published by jmorganca 11 months ago
ollama run openchat
– An open-source chat model trained on a wide variety of data, surpassing ChatGPT on various benchmarks.ollama run neural-chat
– New chat model by Intelollama run goliath
– A large chat model created by combining two fine-tuned versions of Llama 2 70Bollama run
:
--format json
flag or/set format json
to change the current chat session to use JSON modeollama run
. For example: head -30 README.md | ollama run codellama "how do I install Ollama on Linux?"
ollama create
now works with OLLAMA_HOST
to build models using Ollama running on a remote machineollama pull
progress would reverse when re-trying a failed connectionollama show --modelfile
would show an incorrect FROM
commandollama run
via standard inputollama create
on Linuxollama push
would result in a 405 errorollama push
will now return a better error when trying to push to a namespace the current user does not have access toFull Changelog: https://github.com/jmorganca/ollama/compare/v0.1.9...v0.1.10