-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [ x ] I am running the latest code. Development is very rapid so there are no tagged versions as …
-
### System Info
Python version: 3.10.12
Pytorch version:
llama_models version: 0.0.42
llama_stack version: 0.0.42
llama_stack_client version: 0.0.41
Hardware: 4xA100 (40GB VRAM/GPU)
local-…
-
As llama.cpp is now best backend for opensource models, and llama-cpp-python (used as python software backend for python powered GUIs) have buildin OpenAI API support with function (tools) calling sup…
luzik updated
9 months ago
-
**Describe the bug**
I have updated to the latest HEAD, and now when using data generate, the served model reports an AssertionError. I get the same error on different models.
**To Reproduce**…
-
After updating comfyui's pip to the latest, I ComfyUI_VLM_nodes the following error message: FileNotFoundError: [WinError 3] εͳҲָ·: 'D:psûw11variableCUDA11.8bin'
Traceback (most recent call last):
…
-
Can someone help me configure this
Using Python 3.11
ROCm Version 5.5.1
× Building wheel for llama-cpp-python (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [55 lines o…
-
### Description
Have tried a number of huggingface models and consistently get the error message:
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 292, …
-
### Describe the bug
llamacpp doesn't see radeon rx6900xt, previous version worked fine, it seems it has missing dependencies (rocm 5.7.1 is installed)
in particular llama_cpp_cuda can not be import…
pl752 updated
3 months ago
-
Trying to see how the in-flight batching and pagedattention help with the throughput based on Llama-7b model.
Scenario 1
`python3 examples/llama/build.py --model_dir Llama-2-7b-chat-hf --dtype fl…
-
**Describe the bug**
A Valid Toxonomy is throwing errors instead of being used to train data.
**To Reproduce**
Steps to reproduce the behavior:
1. Clone taxonomy
2. add your taxonomy data to on…