Zubiiiiiii294 commited on
Commit
cdfb616
·
verified ·
1 Parent(s): ebfb862

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +179 -37
README.md CHANGED
@@ -25,25 +25,33 @@ pipeline_tag: text-generation
25
 
26
  ### Model Description
27
 
28
- <!-- Provide a longer summary of what this model is. -->
29
 
30
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
31
 
32
- - **Developed by:** [More Information Needed]
33
- - **Funded by [optional]:** [More Information Needed]
34
- - **Shared by [optional]:** [More Information Needed]
35
- - **Model type:** [More Information Needed]
36
- - **Language(s) (NLP):** [More Information Needed]
37
- - **License:** [More Information Needed]
38
- - **Finetuned from model [optional]:** [More Information Needed]
 
 
 
 
 
39
 
40
  ### Model Sources [optional]
41
 
42
  <!-- Provide the basic links for the model. -->
43
 
44
- - **Repository:** [More Information Needed]
45
- - **Paper [optional]:** [More Information Needed]
46
- - **Demo [optional]:** [More Information Needed]
 
 
 
47
 
48
  ## Uses
49
 
@@ -53,29 +61,75 @@ This is the model card of a 🤗 transformers model that has been pushed on the
53
 
54
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
55
 
56
- [More Information Needed]
 
 
 
 
 
 
 
 
57
 
58
  ### Downstream Use [optional]
59
 
60
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
61
 
62
- [More Information Needed]
 
 
 
 
 
 
 
 
 
63
 
64
  ### Out-of-Scope Use
65
 
66
  <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
67
 
68
- [More Information Needed]
 
 
 
 
 
69
 
70
  ## Bias, Risks, and Limitations
71
 
72
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
73
 
74
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
  ### Recommendations
 
 
 
 
 
 
 
77
 
78
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
79
 
80
  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
81
 
@@ -83,38 +137,76 @@ Users (both direct and downstream) should be made aware of the risks, biases and
83
 
84
  Use the code below to get started with the model.
85
 
86
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
87
 
88
  ## Training Details
89
 
90
  ### Training Data
91
 
92
- <!-- 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. -->
 
 
 
 
93
 
94
- [More Information Needed]
95
 
96
  ### Training Procedure
97
 
98
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
 
 
 
 
 
 
 
 
 
99
 
100
  #### Preprocessing [optional]
101
 
102
- [More Information Needed]
103
 
104
 
105
  #### Training Hyperparameters
106
 
107
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
 
 
 
 
 
 
108
 
109
  #### Speeds, Sizes, Times [optional]
110
 
111
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
112
 
113
- [More Information Needed]
 
 
 
 
 
114
 
115
  ## Evaluation
116
 
117
- <!-- This section describes the evaluation protocols and provides the results. -->
 
 
 
118
 
119
  ### Testing Data, Factors & Metrics
120
 
@@ -128,17 +220,24 @@ Use the code below to get started with the model.
128
 
129
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
130
 
131
- [More Information Needed]
 
 
132
 
133
  #### Metrics
134
 
135
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
136
 
137
- [More Information Needed]
138
-
139
  ### Results
140
 
141
- [More Information Needed]
 
 
 
 
 
 
 
142
 
143
  #### Summary
144
 
@@ -152,7 +251,15 @@ Use the code below to get started with the model.
152
 
153
  ## Environmental Impact
154
 
155
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
 
 
 
 
 
 
 
 
156
 
157
  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).
158
 
@@ -162,7 +269,16 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
162
  - **Compute Region:** [More Information Needed]
163
  - **Carbon Emitted:** [More Information Needed]
164
 
165
- ## Technical Specifications [optional]
 
 
 
 
 
 
 
 
 
166
 
167
  ### Model Architecture and Objective
168
 
@@ -170,7 +286,10 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
170
 
171
  ### Compute Infrastructure
172
 
173
- [More Information Needed]
 
 
 
174
 
175
  #### Hardware
176
 
@@ -186,17 +305,30 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
186
 
187
  **BibTeX:**
188
 
189
- [More Information Needed]
 
 
 
 
 
 
 
190
 
191
  **APA:**
192
 
193
- [More Information Needed]
 
194
 
195
  ## Glossary [optional]
196
 
197
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
 
 
 
 
198
 
199
- [More Information Needed]
 
200
 
201
  ## More Information [optional]
202
 
@@ -204,8 +336,18 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
204
 
205
  ## Model Card Authors [optional]
206
 
207
- [More Information Needed]
 
 
 
 
 
 
208
 
209
  ## Model Card Contact
210
 
211
- [More Information Needed]
 
 
 
 
 
25
 
26
  ### Model Description
27
 
28
+ Provide a longer summary of what this model is. -->
29
 
30
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
31
 
32
+ - **Developed by:** [Zubair Arshad Raoter CEO of SafeGuard.AI]
33
+ - **Funded by [optionl]:** [Self-funded using 100% free and open-source resources
34
+ ]
35
+ - **Shared by [Zubair Arshad Raoter
36
+ ]:** [More Information Needed]
37
+ - **Model type:** [ (Text Generation)
38
+ ]
39
+ - **Language(s) (NLP):** [ (English)
40
+ ]
41
+ - **License:** [MIT]
42
+ - **Finetuned from model [optional]:** [distilGPT2 by Hugging Face
43
+ ]
44
 
45
  ### Model Sources [optional]
46
 
47
  <!-- Provide the basic links for the model. -->
48
 
49
+ - **Repository:** [https://huggingface.co/Zubiiiiiii294/textbuddy]
50
+ - **Paper [optional]:** [No formal paper yet. This is an independent experimental build.
51
+ ]
52
+ - **Demo [optional]:** [Demo under development. Will be shared soon.
53
+
54
+ ]
55
 
56
  ## Uses
57
 
 
61
 
62
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
63
 
64
+ [For learning how LLMs work
65
+
66
+ For generating text, stories, content ideas
67
+
68
+ For experimenting with text prompts
69
+
70
+ For research, education & testing small-scale NLP models
71
+
72
+ ]
73
 
74
  ### Downstream Use [optional]
75
 
76
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
77
 
78
+ [This model can be further fine-tuned for:
79
+
80
+ Chatbots
81
+
82
+ Educational writing assistants
83
+
84
+ Text-based games
85
+
86
+ Idea generation tools
87
+ ]
88
 
89
  ### Out-of-Scope Use
90
 
91
  <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
92
 
93
+ [Not recommended for sensitive content
94
+
95
+ Not for decision-making in medical, legal, or security domains
96
+
97
+ Not for multi-language tasks (supports English only)
98
+ ]
99
 
100
  ## Bias, Risks, and Limitations
101
 
102
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
103
 
104
+ [This model may reflect biases present in the Wikitext dataset
105
+
106
+ Text output may be inaccurate or incomplete
107
+
108
+ Doesn’t understand emotional or moral context
109
+
110
+ Doesn’t support multilingual tasks
111
+
112
+ Not suitable for commercial or mission-critical use (yet!)
113
+ This model may reflect biases present in the Wikitext dataset
114
+
115
+ Text output may be inaccurate or incomplete
116
+
117
+ Doesn’t understand emotional or moral context
118
+
119
+ Doesn’t support multilingual tasks
120
+
121
+ Not suitable for commercial or mission-critical use (yet!)
122
+ ]
123
 
124
  ### Recommendations
125
+ Use in controlled environments (research, testing, education)
126
+
127
+ Don’t rely on its outputs as factual
128
+
129
+ Carefully evaluate before using in any product or service
130
+
131
+ Encourage transparency on limitations if shared publicly
132
 
 
133
 
134
  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
135
 
 
137
 
138
  Use the code below to get started with the model.
139
 
140
+ [from transformers import AutoModelForCausalLM, AutoTokenizer
141
+
142
+ model_name = "Zubiiiiiii294/textbuddy"
143
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
144
+ model = AutoModelForCausalLM.from_pretrained(model_name)
145
+
146
+ prompt = "The future of AI in Pakistan is"
147
+ inputs = tokenizer(prompt, return_tensors="pt")
148
+ outputs = model.generate(**inputs, max_length=50)
149
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
150
+ ]
151
 
152
  ## Training Details
153
 
154
  ### Training Data
155
 
156
+ <!-- Dataset: WikiText-2 (raw, preprocessed)
157
+
158
+ Source: Hugging Face Datasets
159
+
160
+ Type: General English knowledge, Wikipedia-style text
161
 
 
162
 
163
  ### Training Procedure
164
 
165
+ Platform: Google Colab
166
+
167
+ Tokenizer: distilgpt2 (EOS padded)
168
+
169
+ Model: distilgpt2
170
+
171
+ Run-time: ~30 minutes total
172
+
173
+ Finetuning: Light-touch to demonstrate model building
174
+
175
+
176
 
177
  #### Preprocessing [optional]
178
 
179
+ []
180
 
181
 
182
  #### Training Hyperparameters
183
 
184
+ - Precision: fp32
185
+
186
+ Epochs: 1-2 (basic)
187
+
188
+ GPU: Colab T4 GPU
189
+
190
+ Batch size: Small (default)
191
+
192
 
193
  #### Speeds, Sizes, Times [optional]
194
 
195
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
196
 
197
+ [Model size: 0.1B (117M parameters)
198
+
199
+ File size: ~328MB
200
+
201
+ Upload: Hugging Face model repo
202
+ ]
203
 
204
  ## Evaluation
205
 
206
+ Testing Data
207
+
208
+ Manual test prompts used during Colab testing
209
+
210
 
211
  ### Testing Data, Factors & Metrics
212
 
 
220
 
221
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
222
 
223
+ [Focused on simple generation
224
+
225
+ No subpopulation or fairness breakdown]
226
 
227
  #### Metrics
228
 
229
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
230
 
 
 
231
  ### Results
232
 
233
+ [Model is functional and responsive
234
+
235
+ Good for basic prompt-based text generation
236
+
237
+ Excellent for learning & showcasing LLMs from Pakistan
238
+
239
+
240
+ ]
241
 
242
  #### Summary
243
 
 
251
 
252
  ## Environmental Impact
253
 
254
+ <!-- Hardware Type: Google Colab (shared cloud GPU)
255
+
256
+ Hours used: ~2 hours
257
+
258
+ Cloud Provider: Google
259
+
260
+ Compute Region: Not specified
261
+
262
+ Carbon Emitted: Minimal (low-resource training)
263
 
264
  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).
265
 
 
269
  - **Compute Region:** [More Information Needed]
270
  - **Carbon Emitted:** [More Information Needed]
271
 
272
+ ## Technical Specifications [ Model Architecture and Objective
273
+
274
+ Base model: distilgpt2
275
+
276
+ Task: Text generation
277
+
278
+ Objective: Predict next word/token in prompt-based context
279
+
280
+
281
+ ]
282
 
283
  ### Model Architecture and Objective
284
 
 
286
 
287
  ### Compute Infrastructure
288
 
289
+ [Cloud: Google Colab (T4 GPU)
290
+
291
+ Software: Hugging Face Transformers, PyTorch, Datasets
292
+ ]
293
 
294
  #### Hardware
295
 
 
305
 
306
  **BibTeX:**
307
 
308
+ [@misc{zubair2025textbuddy,
309
+ title={TextBuddy: Pakistan’s 1st Open-Source Chat AI Model},
310
+ author={Zubair Arshad Raoter},
311
+ year={2025},
312
+ howpublished={\url{https://huggingface.co/Zubiiiiiii294/textbuddy}},
313
+ note={Self-trained via Colab}
314
+ }
315
+ ]
316
 
317
  **APA:**
318
 
319
+ [Zubair Arshad Raoter. (2025). TextBuddy: Pakistan’s 1st Open-Source Chat AI Model. Hugging Face. Retrieved from https://huggingface.co/Zubiiiiiii294/textbuddy
320
+ ]
321
 
322
  ## Glossary [optional]
323
 
324
+ [LLM Large Language Model
325
+
326
+ Tokenization – Breaking down sentences into model-readable pieces
327
+
328
+ Finetuning – Training a model from an existing base on a custom dataset
329
 
330
+
331
+ ]
332
 
333
  ## More Information [optional]
334
 
 
336
 
337
  ## Model Card Authors [optional]
338
 
339
+ [Zubair Arshad Raoter – CEO, SafeGuard.AI
340
+
341
+ Contributor to: Youth AI Movement in Pakistan
342
+
343
+ Model inspired by ChatGPT & Grok logic
344
+
345
+ ]
346
 
347
  ## Model Card Contact
348
 
349
+ [Email: [[email protected]]
350
+
351
+ LinkedIn: www.linkedin.com/in/zubair-arshad-raoter-7b1210289
352
+
353
+ Location: Karachi, Pakistan ]