Pankaj Mathur
commited on
Commit
•
79afbc4
1
Parent(s):
0aca5a9
Update README.md
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ datasets:
|
|
11 |
---
|
12 |
# orca_mini_v2_7b
|
13 |
|
14 |
-
An **Uncensored** LLaMA-7b model in collaboration with [Eric Hartford](https://huggingface.co/ehartford). trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches
|
15 |
|
16 |
Please note this model has *better code generation capabilities* compare to our original orca_mini_7b which was trained on base OpenLLaMA-7b model and which has the [empty spaces issues & found not good for code generation]((https://github.com/openlm-research/open_llama#update-06072023)).
|
17 |
|
@@ -51,7 +51,7 @@ please note num_fewshots varies for each below task as used by HuggingFaceH4 Ope
|
|
51 |
|
52 |
# Dataset
|
53 |
|
54 |
-
We used
|
55 |
|
56 |
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
57 |
|
|
|
11 |
---
|
12 |
# orca_mini_v2_7b
|
13 |
|
14 |
+
An **Uncensored** LLaMA-7b model in collaboration with [Eric Hartford](https://huggingface.co/ehartford). trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
|
15 |
|
16 |
Please note this model has *better code generation capabilities* compare to our original orca_mini_7b which was trained on base OpenLLaMA-7b model and which has the [empty spaces issues & found not good for code generation]((https://github.com/openlm-research/open_llama#update-06072023)).
|
17 |
|
|
|
51 |
|
52 |
# Dataset
|
53 |
|
54 |
+
We used uncensored script on top of the previous explain tuned datasets we build which are [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
|
55 |
|
56 |
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
57 |
|