Hugging Face's logo

kravmar
/
llm-course-hw2-dpo

Text Generation
Transformers
Safetensors
English
llama
conversational
text-generation-inference
Model card Files
xet
Community
kravmar commited on
Commit
3504f18
·
verified ·
1 Parent(s): 8163d31

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -114
README.md CHANGED
@@ -1,6 +1,12 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
4
  ---
5
 
6
  # Model Card for Model ID
@@ -18,127 +24,29 @@ Human-Like-DPO-Dataset, which was created for LLM fluency and making their respo
18
 
19
 
20
 
21
- <!-- ## Training Details
22
 
23
  ### Training Data
24
 
25
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
26
 
27
- [More Information Needed]
 
 
 
28
 
29
- ### Training Procedure
30
 
31
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
 
32
 
33
- #### Preprocessing [optional]
34
 
35
- [More Information Needed]
 
36
 
 
37
 
38
- #### Training Hyperparameters
39
 
40
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
41
-
42
- #### Speeds, Sizes, Times [optional]
43
-
44
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
45
-
46
- [More Information Needed]
47
-
48
- ## Evaluation
49
-
50
- <!-- This section describes the evaluation protocols and provides the results. -->
51
-
52
- ### Testing Data, Factors & Metrics
53
-
54
- #### Testing Data
55
-
56
- <!-- This should link to a Dataset Card if possible. -->
57
-
58
- [More Information Needed]
59
-
60
- #### Factors
61
-
62
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
63
-
64
- [More Information Needed]
65
-
66
- #### Metrics
67
-
68
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
69
-
70
- [More Information Needed] -->
71
-
72
- ### Results
73
-
74
- [More Information Needed]
75
-
76
- #### Summary
77
-
78
-
79
-
80
- ## Model Examination [optional]
81
-
82
- <!-- Relevant interpretability work for the model goes here -->
83
-
84
- [More Information Needed]
85
-
86
- ## Environmental Impact
87
-
88
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
89
-
90
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
91
-
92
- - **Hardware Type:** [More Information Needed]
93
- - **Hours used:** [More Information Needed]
94
- - **Cloud Provider:** [More Information Needed]
95
- - **Compute Region:** [More Information Needed]
96
- - **Carbon Emitted:** [More Information Needed]
97
-
98
- ## Technical Specifications [optional]
99
-
100
- ### Model Architecture and Objective
101
-
102
- [More Information Needed]
103
-
104
- ### Compute Infrastructure
105
-
106
- [More Information Needed]
107
-
108
- #### Hardware
109
-
110
- [More Information Needed]
111
-
112
- #### Software
113
-
114
- [More Information Needed]
115
-
116
- ## Citation [optional]
117
-
118
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
119
-
120
- **BibTeX:**
121
-
122
- [More Information Needed]
123
-
124
- **APA:**
125
-
126
- [More Information Needed]
127
-
128
- ## Glossary [optional]
129
-
130
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
131
-
132
- [More Information Needed]
133
-
134
- ## More Information [optional]
135
-
136
- [More Information Needed]
137
-
138
- ## Model Card Authors [optional]
139
-
140
- [More Information Needed]
141
-
142
- ## Model Card Contact
143
-
144
- [More Information Needed]
 
1
  ---
2
  library_name: transformers
3
+ datasets:
4
+ - HumanLLMs/Human-Like-DPO-Dataset
5
+ language:
6
+ - en
7
+ base_model:
8
+ - HuggingFaceTB/SmolLM-135M-Instruct
9
+ pipeline_tag: text-generation
10
  ---
11
 
12
  # Model Card for Model ID
 
24
 
25
 
26
 
27
+ ## Training Details
28
 
29
  ### Training Data
30
 
31
+ HumanLLMs/Human-Like-DPO-Dataset
32
 
33
+ ### Generation example
34
+ user: What's your morning routine like?
35
+ assistant:
36
+ As the morning kicks in, I'll provide an outline of my daily routine to help you structure your day like a pro. Remember, it's all up to you, so feel free to fill out this routine as much or as little as you like! Here's my daily morning routine:
37
 
38
+ **5:00 AM - Breakfast and Posh Cake**
39
 
40
+ * I grab my morning coffee and fill my "first cup" with a simple cup of pour-over tea or coffee.
41
+ * I put on a healthy breakfast: scrambled eggs, toast, and a piece of fruit (like an apple or banana).
42
+ * I start with a posh cake, such as a cinnamon "cookie" or a simple cinnamon bun, to kick-start the day.
43
 
44
+ **5:30 AM - Meditation Pods**
45
 
46
+ * I download meditation-themed "pod" apps, like Mindful on Tap or Habitica, to help me stay focused and relaxed.
47
+ * I enjoy some mindfulness meditation exercises, like focusing on my breath or a body scan.
48
 
49
+ **7:00 AM - 5:45 AM - Work/School**
50
 
51
+ * I spend the next 20-30 minutes working or studying
52