Update README.md
Browse files
README.md
CHANGED
@@ -9,8 +9,19 @@ tags:
|
|
9 |
- llama
|
10 |
- trl
|
11 |
- sft
|
|
|
12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
|
|
|
|
|
|
13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
# Uploaded model
|
16 |
|
@@ -20,4 +31,4 @@ base_model: unsloth/llama-3-8b-bnb-4bit
|
|
20 |
|
21 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
22 |
|
23 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
9 |
- llama
|
10 |
- trl
|
11 |
- sft
|
12 |
+
- not-for-all-audiences
|
13 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
14 |
+
datasets:
|
15 |
+
- grimulkan/LimaRP-augmented
|
16 |
+
- mpasila/LimaRP-augmented-8k-context
|
17 |
---
|
18 |
+
This is a merge of [mpasila/Llama-3-LimaRP-LoRA-8B](https://huggingface.co/mpasila/Llama-3-LimaRP-LoRA-8B).
|
19 |
+
|
20 |
+
LoRA trained in 4-bit with 8k context using [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B/) as the base model for 1 epoch.
|
21 |
+
|
22 |
+
Dataset used is [a modified](https://huggingface.co/datasets/mpasila/LimaRP-augmented-8k-context) version of [grimulkan/LimaRP-augmented](https://huggingface.co/datasets/grimulkan/LimaRP-augmented).
|
23 |
+
|
24 |
+
### Prompt format: ChatML
|
25 |
|
26 |
# Uploaded model
|
27 |
|
|
|
31 |
|
32 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
33 |
|
34 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|