-
ollama/ollama:latest
-
-
is it possible to use llama3 via ollama rather than huggingface one?
-
How to make use of ollama models instead of Openai models?
-
ollama support at this link https://github.com/win4r/MoA
-
### Bug description
@rasbt I think I have found the issue why the Ollama API does not generate deterministic output, this code should solve it:
```python
def query_model(prompt, model="llama3", u…
-
{
"platform":"",
"hub-mirror": [
"若对OS/ARCH无要求,platform请留空,不要加任何值,默认就是linux/amd64",
"如需切换arm架构,请修改platform为arm64或linux/arm64/v8",
"格式:你需要转换的原始镜像$自定义镜像名:自定义标签名 (其中 …
-
I love your project, I want to use it with local ollama+llava and i tried many way including asking chat gpt.
I am on Windows 11, i tried docker and no go. changed api address from settings in front…
-
Ensure that Janus can be used with an Ollama endpoint
-
I meet this issue while using ollama on MTL iGPU
![image](https://github.com/intel-analytics/ipex-llm/assets/92354341/b9cc7b61-3b61-4615-b1f2-40a85ac22aee)
my IPEX-LLM version as below
![image](htt…