Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,12 @@ The model, finetuned on _Llama-3.1-8B-base_, was trained with a multi-user, mult
|
|
| 24 |
- **2024-09-01 (v0.2)**: increased RP data to 94 samples / 710k tokens. Maybe now more hallucination-prone?
|
| 25 |
- **2024-08-31 (v0.1)**: initial release, 77 samples / 580k tokens.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
| 27 |
## Limitations
|
|
|
|
|
|
|
| 28 |
- Herrsimian is _not_ a general-purpose roleplay finetune.
|
| 29 |
- **Only forum/book style roleplay format with narration in third person + past tense and quote marks-delimited dialogue lines is _in-distribution_ and has been tested in depth.**
|
| 30 |
- Users are supposed to "play along" as one would during a real roleplaying session, and not deliberately write nonsense or ultra-low effort messages; the model was simply not trained to deal with them.
|
|
|
|
| 24 |
- **2024-09-01 (v0.2)**: increased RP data to 94 samples / 710k tokens. Maybe now more hallucination-prone?
|
| 25 |
- **2024-08-31 (v0.1)**: initial release, 77 samples / 580k tokens.
|
| 26 |
|
| 27 |
+
## Usage notes
|
| 28 |
+
The model is probably best used when merged or applied as a LoRA to [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
|
| 29 |
+
|
| 30 |
## Limitations
|
| 31 |
+
Notes mainly pertaining to the raw model trained on Llama-3.1-8B-Base.
|
| 32 |
+
|
| 33 |
- Herrsimian is _not_ a general-purpose roleplay finetune.
|
| 34 |
- **Only forum/book style roleplay format with narration in third person + past tense and quote marks-delimited dialogue lines is _in-distribution_ and has been tested in depth.**
|
| 35 |
- Users are supposed to "play along" as one would during a real roleplaying session, and not deliberately write nonsense or ultra-low effort messages; the model was simply not trained to deal with them.
|