-
### by using DynamicCache llm don't need to re compute the previous prompt. it can re use previous prompt kv cache!
### In gemini it's called context caching gemini & in anthropic it's called prompt …
-
If you are trying to resolve an environment-specific issue or have a one-off question about the edge case that does not require a feature then please consider asking a question in argocd slack [channe…
-
I checked the [documentation](https://docs.ragas.io/en/latest/concepts/testset_generation.html) and related resources and couldn't find an answer to my question.
I wanna know the high level underst…
-
# Issues
- #99
- #98
- #80
- #75
- #70
- #68
# Pull Requests
- #106
- #97
- #96
- #85
- #83
- #81
- #78
-
First off thank you for building this repo!
I tried training a t5 base model on mini pile and got some interesting results.
https://wandb.ai/amazingvince/flasht5-pretrain/runs/ch4a9y51?nw=nwuseram…
-
Hello,
Thank you for sharing your work.
I'm interested in evaluating alpaca-lora on QA tasks. I started with BoolQ dataset. I followed the `generate.py` script and constructed a prompt that work…
-
Hello, FlexFlow team!
Thank you for your outstanding work! I am attempting to reproduce the experimental results from the paper "SpecInfer: Accelerating Generative Large Language Model Serving with…
-
2023-09-26 15:38:45,990 - INFO
Client: Address(host='127.0.0.1', port=61107)
Url: http://127.0.0.1:8000/
Body: b''
2023-09-26 15:38:45,998 - INFO
Client: Address(host='127.0.0.1', port=61107)
…
-
```
a) Before posting your issue you MUST answer to the questions otherwise it
will be rejected (invalid status) by us
b) Please check the issue tacker to avoid duplication
c) Please provide network c…
-
```
a) Before posting your issue you MUST answer to the questions otherwise it
will be rejected (invalid status) by us
b) Please check the issue tacker to avoid duplication
c) Please provide network c…