mafyuh/Auto-Homelab

Archived

Fork 0

⬆️ Update docker.mafyuh.xyz/ollama/ollama Docker tag to v0.1.39 #243

Merged

mafyuh merged 1 commit from renovate/docker.mafyuh.xyz-ollama-ollama-0.x into main

2024-05-24 08:47:21 -04:00

renovatebot commented

2024-05-24 04:28:35 -04:00

Collaborator

This PR contains the following updates:

Package	Update	Change
docker.mafyuh.xyz/ollama/ollama	patch	`0.1.38` -> `0.1.39`

Release Notes

ollama/ollama (docker.mafyuh.xyz/ollama/ollama)

`v0.1.39`

Compare Source

New models

Cohere Aya 23: A new state-of-the-art, multilingual LLM covering 23 different languages.
Mistral 7B 0.3: A new version of Mistral 7B with initial support for function calling.
Phi-3 Medium: a 14B parameters, lightweight, state-of-the-art open model by Microsoft.

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

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-rc1

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

If you want to rebase/retry this PR, check this box

This PR has been generated by Renovate Bot.

This PR contains the following updates: | Package | Update | Change | |---|---|---| | docker.mafyuh.xyz/ollama/ollama | patch | `0.1.38` -> `0.1.39` | --- ### Release Notes <details> <summary>ollama/ollama (docker.mafyuh.xyz/ollama/ollama)</summary> ### [`v0.1.39`](https://github.com/ollama/ollama/releases/tag/v0.1.39) [Compare Source](https://github.com/ollama/ollama/compare/v0.1.38...v0.1.39) #### 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. #### 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` #### New Contributors - [@rapmd73](https://github.com/rapmd73) made their first contribution in https://github.com/ollama/ollama/pull/4467 - [@sammcj](https://github.com/sammcj) made their first contribution in https://github.com/ollama/ollama/pull/4120 - [@likejazz](https://github.com/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-rc1 </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).

renovatebot added 1 commit 2024-05-24 04:28:35 -04:00

⬆️ Update docker.mafyuh.xyz/ollama/ollama Docker tag to v0.1.39

continuous-integration/drone/pr Build is passing

Details

612626a1c7

mafyuh merged commit 2c3678eb58 into main

2024-05-24 08:47:21 -04:00

mafyuh deleted branch renovate/docker.mafyuh.xyz-ollama-ollama-0.x

2024-05-24 08:47:21 -04:00

mafyuh referenced this pull request from a commit

2024-05-24 08:47:22 -04:00

Merge pull request ':arrow_up: Update docker.mafyuh.xyz/ollama/ollama Docker tag to v0.1.39' (#243) from renovate/docker.mafyuh.xyz-ollama-ollama-0.x into main

CD-Bot reviewed 2024-05-24 08:47:44 -04:00

CD-Bot left a comment

Collaborator

Continuous Deployment successfully ran.

Git Logs:

Updating 0a0e928..2c3678e
Fast-forward
AI/docker-compose.yml | 2 +-
README.md | 8 +++++++-
ag-backup/docker-compose.yml | 2 +-
ag-main/docker-compose.yml | 2 +-
4 files changed, 10 insertions(+), 4 deletions(-)

Docker Compose Logs:

time="2024-05-24T08:47:29-04:00" level=warning msg="/home/mafyuh/Auto-Homelab/AI/docker-compose.yml: version is obsolete"
ollama Pulling
ollama Pulled
Container mindsdb Running
Container open-webui Running
Container ollama Recreate
Container ollama Recreated
Container ollama Starting
Container ollama Started

## Continuous Deployment successfully ran. ### Git Logs: Updating 0a0e928..2c3678e Fast-forward AI/docker-compose.yml | 2 +- README.md | 8 +++++++- ag-backup/docker-compose.yml | 2 +- ag-main/docker-compose.yml | 2 +- 4 files changed, 10 insertions(+), 4 deletions(-) ### Docker Compose Logs: time="2024-05-24T08:47:29-04:00" level=warning msg="/home/mafyuh/Auto-Homelab/AI/docker-compose.yml: `version` is obsolete" ollama Pulling ollama Pulled Container mindsdb Running Container open-webui Running Container ollama Recreate Container ollama Recreated Container ollama Starting Container ollama Started

This repo is archived. You cannot comment on pull requests.

No reviewers