pankajmathur
commited on
Commit
•
ac5e24a
1
Parent(s):
fec86e3
Update README.md
Browse files
README.md
CHANGED
@@ -114,10 +114,19 @@ model-index:
|
|
114 |
---
|
115 |
# orca_mini_7b
|
116 |
|
117 |
-
|
118 |
|
|
|
|
|
119 |
|
120 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
|
122 |
We build explain tuned [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).
|
123 |
|
@@ -127,7 +136,7 @@ This helps student model aka this model to learn ***thought*** process from teac
|
|
127 |
|
128 |
Please see below example usage how the **System** prompt is added before each **instruction**.
|
129 |
|
130 |
-
|
131 |
|
132 |
The training configurations are provided in the table below.
|
133 |
|
@@ -149,7 +158,7 @@ Here are some of params used during training:
|
|
149 |
|
150 |
|
151 |
|
152 |
-
|
153 |
|
154 |
Below shows an example on how to use this model
|
155 |
|
@@ -222,8 +231,6 @@ Sincerely,
|
|
222 |
|
223 |
```
|
224 |
|
225 |
-
**P.S. I am #opentowork and #collaboration, if you can help, please reach out to me at www.linkedin.com/in/pankajam**
|
226 |
-
|
227 |
**
|
228 |
|
229 |
Next Goals:
|
|
|
114 |
---
|
115 |
# orca_mini_7b
|
116 |
|
117 |
+
<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
|
118 |
|
119 |
+
<strong>
|
120 |
+
Passionate about Generative AI? I help companies to privately train and deploy custom LLM/MLLM affordably. For startups, I can even assist with securing GPU grants to get you started. Let's chat!
|
121 |
|
122 |
+
<a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a> Looking forward to connecting!
|
123 |
+
</strong>
|
124 |
+
|
125 |
+
<br>
|
126 |
+
|
127 |
+
**An [OpenLLaMa-7B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.**
|
128 |
+
|
129 |
+
### Dataset
|
130 |
|
131 |
We build explain tuned [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).
|
132 |
|
|
|
136 |
|
137 |
Please see below example usage how the **System** prompt is added before each **instruction**.
|
138 |
|
139 |
+
### Training
|
140 |
|
141 |
The training configurations are provided in the table below.
|
142 |
|
|
|
158 |
|
159 |
|
160 |
|
161 |
+
### Example Usage
|
162 |
|
163 |
Below shows an example on how to use this model
|
164 |
|
|
|
231 |
|
232 |
```
|
233 |
|
|
|
|
|
234 |
**
|
235 |
|
236 |
Next Goals:
|