Rafael Aguilar

Now appear the menu when i type `` but when choose the snippet the two chars are select to overwrite. I thinks is other issue than reported by me previously,...

A year and a half and this keep been a relevant feature, any updates on merging this @wmalinowski @benoitc ?

Can you try it with: ```python import json self.client.post('/api/notes/', data=json.dumps({ 'tag': ["xyz"], 'iv': 'random', 'content': "New content", 'date': self.current_date_time })) ``` to check if this "post" only translate the `dict`...

I'm not sure what Ollama uses, but for the `llama.cpp` [backend](https://github.com/ggerganov/llama.cpp/pull/4406) you can override a Key in the model with: ``` --override-kv KEY=TYPE:VALUE advanced option to override model metadata by...

You would need to check in the console, there are multiple problems that can prompt this error. Paste the console output in your description so maintainers or people from the...

Just to add to the list of the broken ones, the 70B Stable Beluga (Q6_K) which states that around 49GB is the recommended allocation size but model was higher (~54GB):...

Btw, using @mbosc [fork](https://github.com/mbosc/llama.cpp), I could run over M1 Max GPU the 70B with `q4_K_M` quantization from [TheBloke's Repo](https://huggingface.co/TheBloke/StableBeluga2-70B-GGML), this time the `mem required` was ~40GB. The speed can be...