Ollama

What's Changed
* Fixed issue on Windows 10 and 11 with Intel CPUs with integrated GPUs where Ollama would encounter an error

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.40...v0.1.41


New models
* [Codestral](https://ollama.com/library/codestral): Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
* [IBM Granite Code](https://ollama.com/library/granite-code): now in [3B](https://ollama.com/library/granite-code:3b) and [8B](https://ollama.com/library/granite-code:8b) parameter sizes.
* [Deepseek V2](https://ollama.com/library/deepseek-v2): A Strong, Economical, and Efficient Mixture-of-Experts Language Model

What's Changed
* Fixed out of memory and incorrect token issues when running Codestral on 16GB Macs
* Fixed issue where full-width characters (e.g. Japanese, Chinese, Russian) were deleted at end of the line when using `ollama run`

New Examples
* [Use open-source models as coding assistant with Continue](https://ollama.com/blog/continue-code-assistant)

New Contributors
* zhewang1-intc made their first contribution in https://github.com/ollama/ollama/pull/3278

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.39...v0.1.40

New models
- [Cohere Aya 23](https://ollama.com/library/aya): A new state-of-the-art, multilingual LLM covering 23 different languages.
- [Mistral 7B 0.3](https://ollama.com/library/mistral:v0.3): A new version of Mistral 7B with initial support for function calling.
- [Phi-3 Medium](https://ollama.com/library/phi3:medium): a 14B parameters, lightweight, state-of-the-art open model by Microsoft.
- [Phi-3 Mini 128K](https://ollama.com/library/phi3:mini-128k) and [Phi-3 Medium 128K](https://ollama.com/library/phi3:medium-128k): versions of the Phi-3 models that support a context window size of 128K
- [Granite code](https://ollama.com/library/granite-code): A family of open foundation models by IBM for Code Intelligence

Llama 3 import

It is now possible to import and quantize Llama 3 and its finetunes from Safetensors format to Ollama.

First, clone a Hugging Face repo with a Safetensors model:


git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
cd Meta-Llama-3-8B-Instruct


Next, create a `Modelfile`:


FROM .

TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""

PARAMETER stop <|start_header_id|>
PARAMETER stop <|end_header_id|>
PARAMETER stop <|eot_id|>


Then, create and quantize a model:


ollama create --quantize q4_0 -f Modelfile my-llama3
ollama run my-llama3


What's Changed
* Fixed issues where wide characters such as Chinese, Korean, Japanese and Russian languages.
* Added new `OLLAMA_NOHISTORY=1` environment variable that can be set to disable history when using `ollama run`
* New experimental `OLLAMA_FLASH_ATTENTION=1` flag for `ollama serve` that improves token generation speed on Apple Silicon Macs and NVIDIA graphics cards
* Fixed error that would occur on Windows running `ollama create -f Modelfile`
* `ollama create` can now create models from I-Quant GGUF files
* Fixed `EOF` errors when resuming downloads via `ollama pull`
* Added a `Ctrl+W` shortcut to `ollama run`


New Contributors
* rapmd73 made their first contribution in https://github.com/ollama/ollama/pull/4467
* sammcj made their first contribution in https://github.com/ollama/ollama/pull/4120
* likejazz made their first contribution in https://github.com/ollama/ollama/pull/4535

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.38...v0.1.39

New Models
- [Falcon 2](https://ollama.com/library/falcon2): A new 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
- [Yi 1.5](https://ollama.com/library/yi): A new high-performing version of Yi, now licensed as Apache 2.0. Available in [6B](https://ollama.com/library/yi:6b), [9B](https://ollama.com/library/yi:9b) and [34B](https://ollama.com/library/yi:34b) sizes.

What's Changed

`ollama ps`

A new command is now available: `ollama ps`. This command displays currently loaded models, their memory footprint, and the processors used (GPU or CPU):


% ollama ps
NAME ID SIZE PROCESSOR UNTIL
mixtral:latest 7708c059a8bb 28 GB 47%/53% CPU/GPU Forever
llama3:latest a6990ed6be41 5.5 GB 100% GPU 4 minutes from now
all-minilm:latest 1b226e2802db 585 MB 100% GPU 4 minutes from now


`/clear`

To clear the chat history for a session when running `ollama run`, use `/clear`:


>>> /clear
Cleared session context


* Fixed issue where switching loaded models on Windows would take several seconds
* Running `/save` will no longer abort the chat session if an incorrect name is provided
* The `/api/tags` API endpoint will now correctly return an empty list `[]` instead of `null` if no models are provided

New Contributors
* fangtaosong made their first contribution in https://github.com/ollama/ollama/pull/4387
* machimachida made their first contribution in https://github.com/ollama/ollama/pull/4424

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.37...v0.1.38

What's Changed
* Fixed issue where models with uppercase characters in the name would not show with `ollama list`
* Fixed usage string for `ollama create`
* Fix `finish_reason` being `""` instead of `null` in the Open-AI compatible chat API.

New Contributors
* todashuta made their first contribution in https://github.com/ollama/ollama/pull/4362

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.36...v0.1.37

What's Changed
* Fixed `exit status 0xc0000005` error with AMD graphics cards on Windows
* Fixed rare out of memory errors when loading a model to run with CPU

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.35...v0.1.36