-
I wanted to extend my sincere appreciation for your project. As a devoted fan of your work, I have thoroughly enjoyed being part of this journey. However, I have recently encountered an issue with the…
-
Hello @mshumer . I am trying to run the code on colab and running into CUDA out of memory error as below :
OutOfMemoryError Traceback (most recent call last)
[](https://loc…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
I am able to chat just fine with my llama3:instruct model just fine, but when I try to use the autocomplete, it is always failing with a 500 status on the api/generate call.
MacOS version: Sonoma…
-
Hi team,
I am trying to build llama engine files using `nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3` container and was getting the below error:
```
Traceback (most recent call last):
…
-
Great idea to build this- Model downloading is unnecessarily annoying with HF.
Very slow xfer in wsl2
_Downloading Storage/turboderp_CodeLlama-34B-instruct-exl2/output-00001-of-00004.safetensors…
-
I tried to finetune CodeLlama 7b Instruct by downloading weights through official repository
Folder Structure of Folder Containing CodeLlama Instruct Weights
![image](https://github.com/pytorch/…
-
### Describe the need of your request
Inline code completion is very useful feature, but it would be awesome to make it more customisable.
For example, now it always generates a lot of lines of…
-
**What problem or use case are you trying to solve?**
Experimenting OpenDevin on local workspace with ollama and 7/8B models (llama3, codellama, codegemma) on my 6GB VRAM GPU, since I cannot try bi…
-
(dbgpt_hub) aistudio@jupyter-4913610-7006586:~/DB_GPT_Hub/DB-GPT-Hub-0.2.0$ sh dbgpt_hub/scripts/gen_train_eval_data.sh
===================================BUG REPORT================================…