Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: llama3
|
| 3 |
---
|
| 4 |
|
| 5 |
-
# Llama-3.1-70B-ArliAI-RPMax-v1.
|
| 6 |
=====================================
|
| 7 |
|
| 8 |
## RPMax Series Overview
|
|
@@ -28,16 +28,11 @@ Ask questions in our new Discord Server! https://discord.com/invite/t75KbPgwhk
|
|
| 28 |
|
| 29 |
## Model Description
|
| 30 |
|
| 31 |
-
Llama-3.1-70B-ArliAI-RPMax-v1.
|
| 32 |
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
v1.2 update completely removes non-creative/RP examples in the dataset and is also an incremental improvement of the RPMax dataset which dedups the dataset even more and better filtering to cutout irrelevant description text that came from card sharing sites.
|
| 36 |
-
|
| 37 |
-
### Specs
|
| 38 |
|
| 39 |
-
|
| 40 |
-
* **Parameters**: 70B
|
| 41 |
|
| 42 |
### Training Details
|
| 43 |
|
|
@@ -52,8 +47,12 @@ v1.2 update completely removes non-creative/RP examples in the dataset and is al
|
|
| 52 |
|
| 53 |
The model is available in quantized formats:
|
| 54 |
|
| 55 |
-
|
| 56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
## Suggested Prompt Format
|
| 59 |
|
|
|
|
| 2 |
license: llama3
|
| 3 |
---
|
| 4 |
|
| 5 |
+
# Llama-3.1-70B-ArliAI-RPMax-v1.1
|
| 6 |
=====================================
|
| 7 |
|
| 8 |
## RPMax Series Overview
|
|
|
|
| 28 |
|
| 29 |
## Model Description
|
| 30 |
|
| 31 |
+
Llama-3.1-70B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-70B-Instruct model.
|
| 32 |
|
| 33 |
+
This version is an early test on 70B that is only run with a short sequence length for training, we are planning to run another training with higher sequence length.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
Let us know what you think of the model! The 8B and 12B versions of RPMax had great feedback from users, so we expect this 70B version to one of the best RP models.
|
|
|
|
| 36 |
|
| 37 |
### Training Details
|
| 38 |
|
|
|
|
| 47 |
|
| 48 |
The model is available in quantized formats:
|
| 49 |
|
| 50 |
+
We recommend using full weights or GPTQ. GGUF provided by https://huggingface.co/mradermacher/Llama-3.1-70B-ArliAI-RPMax-v1.1-GGUF
|
| 51 |
+
|
| 52 |
+
* **FP16**: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1
|
| 53 |
+
* **GPTQ_Q4**: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GPTQ_Q4
|
| 54 |
+
* **GPTQ_Q8**: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GPTQ_Q8
|
| 55 |
+
* **GGUF**: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GGUF
|
| 56 |
|
| 57 |
## Suggested Prompt Format
|
| 58 |
|