vrr/talemate
2
0
Fork 0
mirror of https://github.com/vegu-ai/talemate.git synced 2025-09-01 18:09:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
veguAI 2024-05-18 12:31:32 +03:00 • committed by GitHub
parent 02c88f75a1
commit cc7cb773d1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
README.md
View file

@ -95,6 +95,8 @@ There is also a [troubleshooting guide](docs/troubleshoot.md) that might help.
### Docker
:warning: Some users currently experience issues with missing dependencies inside the docker container, issue tracked at [#114](https://github.com/vegu-ai/talemate/issues/114)
1. `git clone https://github.com/vegu-ai/talemate.git`
1. `cd talemate`
1. `cp config.example.yaml config.yaml`
@ -171,14 +173,7 @@ In the case for `bartowski_Nous-Hermes-2-Mistral-7B-DPO-exl2_8_0` that is `ChatM
### Recommended Models
As of 2024.05.06 my personal regular drivers (the ones i test with) are:
- meta-llama_Meta-Llama-3-8B-Instruct
- brucethemoose_Yi-34B-200K-RPMerge
- rAIfle_Verdict-8x7B
- meta-llama_Meta-Llama-3-70B-Instruct
That said, any of the top models in any of the size classes here should work well (i wouldn't recommend going lower than 7B):
Any of the top models in any of the size classes here should work well (i wouldn't recommend going lower than 7B):
[https://oobabooga.github.io/benchmark.html](https://oobabooga.github.io/benchmark.html)
@ -266,4 +261,4 @@ Then open the file and edit the `ALLOWED_HOSTS` and `VUE_APP_TALEMATE_BACKEND_W
ALLOWED_HOSTS=example.com
# wss if behind ssl, ws if not
VUE_APP_TALEMATE_BACKEND_WEBSOCKET_URL=wss://example.com:5050
```
```