-
### What happened?
Using [ir19.flagfile](https://gist.githubusercontent.com/silvasean/3cf5d0078a2351e601c7f46e2b173cd6/raw/ca9103a884b81d9c24aed4c4663780e05daa9500/ir19.flagfile) and [ir19.no_shard…
-
referring to `reask`
Might be useful to have max retry count or similar
-
Hi there 👋
As a continuation of #448 I decided to create another issue where I'll put results for other small experiments of performance improvements for the LoRA implementation:
- [x] 1. Repla…
-
After the CUDA refactor PR #1703 by @JohannesGaessler was merged i wanted to try it out this morning and measure the performance difference on my ardware.
I use my standard prompts with different mod…
-
hello guys,
i have an issue when i convert the weights i just got the error message :
Killed
and nothing more there is any verbose mode to understand what's happend ?
full log
~/lit-lla…
-
I'm able to successfully run the gpt-j model using the shared pretrained model on CPU. the below result is just for a single input.
```
Results
{'rouge1': 32.7869, 'rouge2': 6.7797, 'rougeL': 2…
-
### Describe the bug
Always got 0 tokens output generated when run HuggingFace.co/TheBloke_StableBeluga2-70B-GPTQ
Load model and try to run it, with a simple request, it always return 0 tokens a…
-
```python
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.9/runpy.py", line 197, in _run_module_as_main
…
-
Consider the below instruction + rail spec:
```
query = "new booking from hong kong to london with 2 pallets in a 40 HC"
rail_spec = """
…
-
hey, another small parsing issue.
My sample case:
```py
from langchain.output_parsers import GuardrailsOutputParser
from langchain.chat_models import ChatOpenAI
from langchain import PromptTemp…