ChandruK commited on
Commit
65f8346
·
verified ·
1 Parent(s): a5e3e32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -189
README.md CHANGED
@@ -1,199 +1,96 @@
1
  ---
2
- library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
9
 
 
10
 
 
11
 
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- 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. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- 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).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
 
195
- [More Information Needed]
 
 
196
 
197
- ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - zero-shot-classification
7
+ - nli
8
+ - cross-encoder
9
+ - intent-routing
10
+ - docgeniee
11
+ - debberta
12
+ pipeline_tag: zero-shot-classification
13
+ widget:
14
+ - text: "Generate a formal project proposal in Word format."
15
+ candidate_labels: "a Word document creation request, an Excel spreadsheet creation request, a PowerPoint presentation deck creation request, a PDF document analysis query, general chitchat"
16
  ---
17
 
18
+ # MarkOne (formerly SystemOne) 🤖
19
 
20
+ **MarkOne** is a high-precision, zero-shot NLI cross-encoder model designed for **dynamic intent routing and query classification** within modular AI architectures (such as [DocGeniee](https://github.com/ChandruK/DocGeniee)).
21
 
22
+ It evaluates user prompts against arbitrary numbers of candidate choice labels ($N = 3, 6, 8, \dots$) by computing sequence pair entailment probabilities without requiring dedicated single-label classification fine-tuning for every domain.
23
 
24
+ ---
25
 
26
+ ## 🌟 Key Features
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
 
28
+ - **Dynamic Choice Counts:** Handles variable numbers of candidate labels on the fly across different routing domains.
29
+ - **Cross-Encoder Accuracy:** Outperforms single-text classifiers by evaluating joint attention over `(Premise, Hypothesis)` pairs.
30
+ - **DocGeniee Native:** Pre-configured for routing document generation workflows (Word, Excel, PowerPoint), PDF RAG queries, and chitchat/out-of-scope filtering.
31
 
32
+ ---
33
 
34
+ ## 🚀 Quickstart & Usage
35
+
36
+ Because **MarkOne** operates as an NLI cross-encoder, it evaluates candidate choices by pairing the input prompt as a **Premise** with a set of generated candidate **Hypotheses**.
37
+
38
+ ### Zero-Shot NLI Classification (Python)
39
+
40
+ ```python
41
+ import torch
42
+ import torch.nn.functional as F
43
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
44
+
45
+ # Load model and tokenizer
46
+ MODEL_ID = "ChandruK/MarkOne"
47
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
48
+
49
+ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
50
+ model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID).to(device)
51
+ model.eval()
52
+
53
+ # Entailment label index (Index 2 for standard DeBERTa MNLI architecture)
54
+ ENTAILMENT_IDX = 2
55
+
56
+ # 1. Define Candidate Labels and Hypothesis Template
57
+ CANDIDATE_LABELS = [
58
+ "a Word document creation request",
59
+ "an Excel spreadsheet creation request",
60
+ "a PowerPoint presentation deck creation request",
61
+ "a PDF document analysis or extraction query",
62
+ "general chitchat or off-topic conversation"
63
+ ]
64
+ HYPOTHESIS_TEMPLATE = "This user prompt is {}."
65
+
66
+ # 2. Input Prompt
67
+ prompt = "Generate a formal project proposal in Word format."
68
+
69
+ # 3. Construct Premise-Hypothesis Pairs
70
+ hypotheses = [HYPOTHESIS_TEMPLATE.format(label) for label in CANDIDATE_LABELS]
71
+ premises = [prompt] * len(CANDIDATE_LABELS)
72
+
73
+ # 4. Tokenize Pairs
74
+ inputs = tokenizer(
75
+ text=premises,
76
+ text_pair=hypotheses,
77
+ padding=True,
78
+ truncation=True,
79
+ return_tensors="pt"
80
+ ).to(device)
81
+
82
+ # 5. Model Inference
83
+ with torch.no_grad():
84
+ outputs = model(**inputs)
85
+ # Extract Entailment logits vector across all dynamic candidates
86
+ entailment_logits = outputs.logits[:, ENTAILMENT_IDX]
87
+
88
+ # Softmax probability normalization
89
+ probabilities = F.softmax(entailment_logits / 0.5, dim=-1)
90
+ top_prob, top_idx = torch.max(probabilities, dim=-1)
91
+
92
+ predicted_label = CANDIDATE_LABELS[top_idx.item()]
93
+ confidence = top_prob.item() * 100
94
+
95
+ print(f"💬 Prompt : '{prompt}'")
96
+ print(f"🏷️ Predicted : {predicted_label} ({confidence:.2f}% confidence)")