ChuckMcSneed
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ language:
|
|
10 |
- ru
|
11 |
---
|
12 |
![logo-gembo-1.1.png](logo-gembo-1.1.png)
|
13 |
-
This is like [Gembo v1](https://huggingface.co/ChuckMcSneed/Gembo-v1-70b), but with 6-7% more human data. Does perform a bit worse on the benches(who cares), but should be able to write in more diverse styles(
|
14 |
|
15 |
# Observations
|
16 |
- GPTisms and repetition: put temperature and rep. pen. higher, make GPTisms stop sequences
|
@@ -19,12 +19,15 @@ This is like [Gembo v1](https://huggingface.co/ChuckMcSneed/Gembo-v1-70b), but w
|
|
19 |
- Fairly neutral, can be violent if you ask it really good, Goliath is a bit better at it
|
20 |
- Has a bit of optimism baked in, but it's not very severe, maybe a tiny bit more than in v1?
|
21 |
- Don't put too many style tags, here less is better
|
22 |
-
- Unlike v1, 1.1 knows
|
23 |
- Needs more wrangling than v1, but once you get it going it's good
|
24 |
- Sometimes can't handle '
|
25 |
- Moderately intelligent
|
26 |
- Quite creative
|
27 |
|
|
|
|
|
|
|
28 |
# Naming
|
29 |
Internal name of this model was euryale-guano-saiga-med-janboros-kim-wing-lima-wiz-tony-d30-s40, but I decided to keep it short, and since it was iteration G in my files, I called it "Gembo".
|
30 |
|
|
|
10 |
- ru
|
11 |
---
|
12 |
![logo-gembo-1.1.png](logo-gembo-1.1.png)
|
13 |
+
This is like [Gembo v1](https://huggingface.co/ChuckMcSneed/Gembo-v1-70b), but with 6-7% more human data. Does perform a bit worse on the benches(who cares? I do.), but should be able to write in more diverse styles(See [waxwing-styles.txt](waxwing-styles.txt), tested it with v1, v1 does it better.). Mainly made for RP, but should be okay as an assistant. Turned out quite good, considering the amount of LORAs I merged into it.
|
14 |
|
15 |
# Observations
|
16 |
- GPTisms and repetition: put temperature and rep. pen. higher, make GPTisms stop sequences
|
|
|
19 |
- Fairly neutral, can be violent if you ask it really good, Goliath is a bit better at it
|
20 |
- Has a bit of optimism baked in, but it's not very severe, maybe a tiny bit more than in v1?
|
21 |
- Don't put too many style tags, here less is better
|
22 |
+
- Unlike v1, 1.1 knows a bit better when to stop
|
23 |
- Needs more wrangling than v1, but once you get it going it's good
|
24 |
- Sometimes can't handle '
|
25 |
- Moderately intelligent
|
26 |
- Quite creative
|
27 |
|
28 |
+
# Worth over v1?
|
29 |
+
Meh. I prefer hyperslop over this "humanized" one. Maybe I've been poisoned by slop.
|
30 |
+
|
31 |
# Naming
|
32 |
Internal name of this model was euryale-guano-saiga-med-janboros-kim-wing-lima-wiz-tony-d30-s40, but I decided to keep it short, and since it was iteration G in my files, I called it "Gembo".
|
33 |
|