-
Given existing support for GPT-J and its rotary embeddings, is LLaMA supported as well? Huggingface just shipped their implementation: https://github.com/huggingface/transformers/commit/464d4207756538…
-
llama3-8B-instruct will crash **every time** after I ask the following 3 questions consecutively in a conversation dialog.
I ask these 3 questions no matter what the response was:
1.write python …
-
### The problem
Since a day or 2 my iRobot i7 integration was not responding. I deleted the integration and added it again, now the intergration configures itself as usual but does not create a devic…
-
### Please verify that you have read and understood the guidelines.
yes
### A clear and concise description of the issue.
any settings running the frigate.sh script fails
### What settings are you…
-
## Hardware and versions
* Inverter model & generation: Gen1 Hybrid 3.6
* Inverter firmware version: D0.450-A0.451
* Battery firmware version: 3015
* Home Assistant integration version: 2.…
-
### Describe the bug
You can in this screenshot that the time for the "usage-playground" generation is -0.00s. This happens, when you call `trace.generation()` after calling `generation.end()`.
…
-
I am trying to nail down in my mind, the fundamental _orthogonal_ semantic concepts of our proposed programming language.
| Concept | Description |
| --- | --- |
| `data` | [Unified sum, product,…
-
### System Info
- TensorRT-LLM v0.8.0 (pinned to release commit)
- Nvidia A100
- Mistral-7B-Instruct-v0.2
- Using the CPP runner
- Installed with `pip install tensorrt_llm==0.8.0 --extra-index-ur…
-
I'm using your library with [phi-2](https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF) on an Android device (after updating the llama.cpp version). I've noticed that generation seems to ignore or…
-
# Issue
WSL 2 seems to NAT it's virtual network, instead of making it bridged to the host NIC. My goal is for a service running in Ubuntu in WSL 2 to be accessible from anywhere on my local network.
…