Update README.md
Browse files
README.md
CHANGED
|
@@ -3,32 +3,41 @@ base_model:
|
|
| 3 |
- PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
| 6 |
-
-
|
| 7 |
-
-
|
| 8 |
-
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
# Francois-PE
|
| 11 |
|
| 12 |
-
This is
|
| 13 |
-
|
| 14 |
-
## Merge Details
|
| 15 |
-
### Merge Method
|
| 16 |
-
|
| 17 |
-
This model was merged using the Passthrough merge method using [PocketDoc/Dans-PersonalityEngine-V1.1.0-12b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.1.0-12b) + /home/mango/Loras/francois as a base.
|
| 18 |
-
|
| 19 |
-
### Models Merged
|
| 20 |
-
|
| 21 |
-
The following models were included in the merge:
|
| 22 |
|
|
|
|
| 23 |
|
| 24 |
-
### Configuration
|
| 25 |
-
|
| 26 |
-
The following YAML configuration was used to produce this model:
|
| 27 |
-
|
| 28 |
-
```yaml
|
| 29 |
-
base_model: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b+/home/mango/Loras/francois
|
| 30 |
-
dtype: bfloat16
|
| 31 |
-
merge_method: passthrough
|
| 32 |
-
models:
|
| 33 |
-
- model: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b+/home/mango/Loras/francois
|
| 34 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- finetune
|
| 8 |
+
- roleplaying
|
| 9 |
+
- RP
|
| 10 |
+
- Mistral
|
| 11 |
---
|
| 12 |
# Francois-PE
|
| 13 |
|
| 14 |
+
This is the base model for Francois-PE-Huali, I'd reccomend using that instead of this, The model is extremely underfit and via KTO - was fixed and wayyyyyyyyyyy more coherent
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
+
List of datasets:
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
```
|
| 19 |
+
datasets:
|
| 20 |
+
- PocketDoc/Dans-Personamaxx-VN
|
| 21 |
+
- NewEden/LIMARP-Complexity
|
| 22 |
+
- NewEden/PIPPA-Mega-Filtered
|
| 23 |
+
- NewEden/OpenCAI-ShareGPT
|
| 24 |
+
- NewEden/Creative_Writing-Complexity
|
| 25 |
+
- NewEden/Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed
|
| 26 |
+
- PocketDoc/Dans-Failuremaxx-Adventure-3
|
| 27 |
+
- NewEden/Books-V2-ShareGPT
|
| 28 |
+
- NewEden/Deepseek-V3-RP-Filtered
|
| 29 |
+
- NewEden/BlueSky-10K-Complexity
|
| 30 |
+
- NewEden/Final-Alpindale-LNs-ShareGPT
|
| 31 |
+
- NewEden/DeepseekRP-Filtered
|
| 32 |
+
- NewEden/RP-logs-V2-Experimental
|
| 33 |
+
- anthracite-org/kalo_opus_misc_240827
|
| 34 |
+
- anthracite-org/kalo_misc_part2
|
| 35 |
+
- NewEden/vanilla-backrooms-claude-sharegpt
|
| 36 |
+
- NewEden/Storium-Prefixed-Clean
|
| 37 |
+
- NewEden/KTO-IF-Dans
|
| 38 |
+
- NewEden/KTO-Instruct-Mix
|
| 39 |
+
- NewEden/Opus-accepted-hermes-rejected-shuffled
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
KTO wandb: https://wandb.ai/new-eden/Francois-V2/runs/f2qejmu0?nw=nwuserdeltavector
|
| 43 |
+
SFT wandb: https://wandb.ai/new-eden/Francois/runs/sn3utrs1?nw=nwuserdeltavector
|