Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,9 @@ library_name: peft
|
|
| 32 |
pipeline_tag: text-generation
|
| 33 |
---
|
| 34 |
|
|
|
|
|
|
|
|
|
|
| 35 |
# Llama 3.2 - 3B OpenRP-A
|
| 36 |
"OpenRP-A Model"
|
| 37 |
Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2 3B Instruct model, optimized for role-playing (RP) tasks. This model was developed using the Unsloth AI training tool and fine-tuned over 60 epochs on two datasets: `openerotica/mixed-rp` (a diverse role-playing dataset from Openerotica) and `kingbri/PIPPA-shareGPT` (a supplementary dataset enhancing conversational RP capabilities). With 3 billion parameters, it delivers robust performance for uncensored, creative, and interactive applications.
|
|
|
|
| 32 |
pipeline_tag: text-generation
|
| 33 |
---
|
| 34 |
|
| 35 |
+
# OPENRP-A is HIGHLY HALLUCINATED MODEL, We're Working on Patching and Swiftly switching it to working Model,
|
| 36 |
+
- OpenElla Will replace the model, for now use pygmalion :3
|
| 37 |
+
|
| 38 |
# Llama 3.2 - 3B OpenRP-A
|
| 39 |
"OpenRP-A Model"
|
| 40 |
Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2 3B Instruct model, optimized for role-playing (RP) tasks. This model was developed using the Unsloth AI training tool and fine-tuned over 60 epochs on two datasets: `openerotica/mixed-rp` (a diverse role-playing dataset from Openerotica) and `kingbri/PIPPA-shareGPT` (a supplementary dataset enhancing conversational RP capabilities). With 3 billion parameters, it delivers robust performance for uncensored, creative, and interactive applications.
|