munish0838
commited on
Commit
•
33e244f
1
Parent(s):
a493e2b
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
base_model: OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1
|
5 |
+
---
|
6 |
+
|
7 |
+
# QuantFactory/ArliAI-Llama-3-8B-Instruct-DPO-v0.1-GGUF
|
8 |
+
This is quantized version of [OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1](https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1) created using llama.cpp
|
9 |
+
|
10 |
+
# Model Description
|
11 |
+
Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:
|
12 |
+
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
13 |
+
|
14 |
+
|
15 |
+
DPO fine tuning method using the following datasets:
|
16 |
+
- https://huggingface.co/datasets/Intel/orca_dpo_pairs
|
17 |
+
- https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo
|
18 |
+
- https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2
|
19 |
+
- https://huggingface.co/datasets/M4-ai/prm_dpo_pairs_cleaned
|
20 |
+
- https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1
|
21 |
+
|
22 |
+
|
23 |
+
|
24 |
+
Instruct format:
|
25 |
+
```
|
26 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
27 |
+
|
28 |
+
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
29 |
+
|
30 |
+
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
31 |
+
|
32 |
+
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
33 |
+
|
34 |
+
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
35 |
+
```
|