-
### Bug Description
The example code demonstrating how to use SchemaLLMPathExtractor produces an AssertionError when run.
Specifically - it fails the check to see if the kg_schema produced in indi…
-
### What is the issue?
Error: llama runner process has terminated: signal: aborted
logs:
```
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected …
-
### Check for existing issues
- [X] Completed
### Describe the bug / provide steps to reproduce it
After #16877 any prompt to ollama with llama3.1:latest crashes the ollama runner (ROCm). This does…
-
### System Info / 系統信息
H100 python 3.11.
Running the openai demo with other various images. Not sure exactly which image I sent to hit this.
```
Traceback (most recent call last):
File "/ho…
-
### What is the issue?
When I run the **70b-instruct-q4_1** version of Llama3.1 ollama gives a buggy reply:
My sample request:
> ➜ ollama-tests curl http://localhost:11434/api/chat -d '{
…
-
So, I've been testing to generate text using exllamav2 with some config following huggingface generator. Here is my script
```python
import torch, os
from contextlib import contextmanager
from p…
-
when I run
!bash scripts/merge_lora.sh
after
Loading LLama3.2-Vision from base model...
Loading LoRA weights...
Traceback (most recent call last):
raise ValueError(
ValueError: Targe…
-
### What is the issue?
I am running ollama via docker. Everything works smootly but vision models.
I tried `llava` and `bakllava` with no success.
### What did you expect to see?
The description o…
-
### Model Requests
https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
and 11b
### Which formats?
- [X] GGUF (llama.cpp)
- [ ] TensorRT (TensorRT-LLM)
- [X] ONNX (Onnx Runtime)
-
### Your current environment
The output of `python collect_env.py`
```text
PyTorch version: 2.5.0.dev20240726+rocm6.1
Is debug build: False
CUDA used to build PyTorch: N/A
ROCM used to bui…