-
Hi, friend, maybe you can try to use the llama architecture instead of the original Transformer?(You can refer to llama architecture in llama2.c)
-
Hi there, I wrote two methods that allow unsloth models to be loaded into memory and unloaded into memory. To my knowledge, I believe this is the only way to do change unsloth models
```
llm_mode…
-
### What happened?
all modeles are flat
![image](https://github.com/user-attachments/assets/c70fb40c-8a4c-4…
-
I use the multi-LoRA for offline inference:
sql_lora_path = "/home/zyn/models/slot_lora_gd"
from vllm import LLM, SamplingParams
from vllm.lora.request import LoRARequest
llm = LLM(model="/ho…
-
sql_lora_path = "/home/zyn/models/slot_lora_gd"
from vllm import LLM, SamplingParams
from vllm.lora.request import LoRARequest
llm = LLM(model="/home/models/dem_14b/base",
enable_lor…
-
DeviceListPage should be reworked so that it:
- does not use a single _deviceDisplayInfo() function to configure its delegates, as causes binding updates to all delegates whenever any of the displa…
-
### Guidelines
- [X] I checked for duplicate bug reports
- [X] I tried to find a way to reproduce the bug
### Version
Development (Staging)
### What happened? What did you expect to happen?
When …
-
Got this while running from main branch in Podman AI Lab:
```
�llama_model_loader: loaded meta data with 25 key-value pairs and 291 tensors from /granite-7b-lab-Q4_K_M.gguf (version GGUF V3 (lates…
-
Hi,
I'm trying to recover data from a bricked Wiko Pulp 4G, but although I get no errors dumping the userdata partition, the data is severely corrupted. And not just that, they are bit flips on sin…
smiba updated
2 weeks ago
-
Can't download model
`model = torch.hub.load("intel-isl/MiDaS", "DPT_Large")`
gives this on Windows 10, Anaconda env, Pytorch 1.9, Pycharm IDE
```
Traceback (most recent call last):
File …
xvel updated
2 months ago