-
Hi!
Curious to know some more details about FIM and its effect on the pre-trained model.
Here's a paragraph from the SantaCoder paper:
> FIM for cheap
We observe a minor drop in performance of…
-
I am using Ubuntu 22.04 LTS. I followed the instructions in the readme.md to run download.sh and selected all the models. The installation went smoothly at the beginning until it reached CodeLlama-34b…
-
Hi,
I am trying to integrate AWQ into vLLM library. The current issue is that AWQ has worse throughput than the unquantised variant: I think it should at least match this.
Issues when profilin…
-
I removed all local files, re-cloned the repository, and requested a new download link, but when I run ./download.sh and entered the download link, chose the model, it still gave the ERROR 403: Forbid…
-
as describe in titlle,much appreciate
-
While I pulled already llama2:7b , I wanted to install llama2 (without the 7b tag). My understanding was that it was the same exact model (same hash), so maybe ollama would install only the metadata f…
-
how i use this with ollama locally? i have this list ready to go
ollama list
NAME ID SIZE MODIFIED
hub/stewart/multi-agent:latest 8cc6e95685ac 3.8 GB 10…
-
We should not react on issues that were not labeled with `bug`
-
While downloading 13B, the model size is around 12 GB and it is saying that
consolidated.00.pth -> OK
consolidated.01.pth -> FAILED
I am following all the steps as mentioned but nothing ain't …
-
I have trying to host the Code Llama from Hugging Face locally and trying to run it. It runs soley on CPU and it is not utilizing GPU available in the machine despite having Nvidia Drivers and Cuda …