blair-johnson commited on
Commit
acbdb85
1 Parent(s): e25a60e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md CHANGED
@@ -30,6 +30,51 @@ The Alpaca dataset is a set of 52k instruct-response pairs designed to enhace th
30
  The GALACTICA model card specifies that the primary indended users of the GALACTICA models are researchers studying language models applied to the scientific domain, and it cautions against production use of GALACTICA without safeguards due to the potential for the model to produce inaccurate information.
31
  The original GALACTICA models are available under a non-commercial CC BY-NC 4.0 license, and models based on the Evol-Instruct-70k dataset are additionally subject to the [OpenAI Terms of Service](https://openai.com/policies/terms-of-use).
32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  ## Training Data
34
 
35
  This model was trained by fine-tuning pre-trained GALACTICA 6.7B on the Evol-Instruct-70k dataset. GALACTICA models were trained on 106 billion tokens of open-access scientific text and data, including papers, textbooks, scientific websites, encyclopedias, and more.
 
30
  The GALACTICA model card specifies that the primary indended users of the GALACTICA models are researchers studying language models applied to the scientific domain, and it cautions against production use of GALACTICA without safeguards due to the potential for the model to produce inaccurate information.
31
  The original GALACTICA models are available under a non-commercial CC BY-NC 4.0 license, and models based on the Evol-Instruct-70k dataset are additionally subject to the [OpenAI Terms of Service](https://openai.com/policies/terms-of-use).
32
 
33
+ <details>
34
+ <summary> Example Outputs </summary>
35
+
36
+ *__Full Prompt:__*
37
+ ```
38
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
39
+
40
+ ### Instruction:
41
+ Write out Maxwell's equations and explain each one.
42
+
43
+ ### Response:
44
+ ```
45
+
46
+ *__Response:__*
47
+
48
+ Maxwell's equations are a set of four equations that describe the behavior of electromagnetic fields. These equations were developed by James Clerk Maxwell in 1864 and are widely used in the study of electromagnetism.
49
+
50
+ 1. Gauss's Law: This equation states that the electric charge inside a closed surface is equal to the flux of electric field through the surface. Mathematically, it can be expressed as:
51
+
52
+ $$\nabla \bullet \textbf{E} = \frac{\rho}{\epsilon_0}$$
53
+
54
+ where E is the electric field, ρ is the charge density, ε0 is the electric constant, and ∇ is the divergence operator.
55
+
56
+ 2. Faraday's Law: This equation states that the electric field around a closed loop is proportional to the time rate of change of magnetic flux through the loop. Mathematically, it can be expressed as:
57
+
58
+ $$\nabla \times \textbf{E} = -\frac{\partial\textbf{B}}{\partial t}$$
59
+
60
+ where B is the magnetic field, t is time, and ∇ × is the curl operator.
61
+
62
+ 3. Gauss's Law for Magnetism: This equation states that the magnetic charge inside a closed surface is equal to the flux of magnetic field through the surface. Mathematically, it can be expressed as:
63
+
64
+ $$\nabla \bullet \textbf{B} = 0$$
65
+
66
+ where B is the magnetic field.
67
+
68
+ 4. Ampere's Law: This equation states that the magnetic field around a closed loop is proportional to the current through the loop. Mathematically, it can be expressed as:
69
+
70
+ $$\nabla \times \textbf{B} = \mu_0\textbf{J} + \mu_0\epsilon_0\frac{\partial \textbf{E}}{\partial t}$$
71
+
72
+ where J is the current density, μ0 is the magnetic constant, and ε0 is the electric constant.
73
+
74
+ These equations form the foundation of all electromagnetic theory and are used to describe the behavior of electromagnetic fields in a wide range of applications, from radio waves to high-energy particles.
75
+
76
+ </details>
77
+
78
  ## Training Data
79
 
80
  This model was trained by fine-tuning pre-trained GALACTICA 6.7B on the Evol-Instruct-70k dataset. GALACTICA models were trained on 106 billion tokens of open-access scientific text and data, including papers, textbooks, scientific websites, encyclopedias, and more.