daha-kot commited on
Commit
08a4a14
1 Parent(s): 77f55a0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -166
README.md CHANGED
@@ -1,76 +1,60 @@
1
  ---
2
  library_name: peft
3
  base_model: core42/jais-13b
 
 
 
 
 
 
 
 
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
-
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Shared by [optional]:** [More Information Needed]
22
- - **Model type:** [More Information Needed]
23
- - **Language(s) (NLP):** [More Information Needed]
24
- - **License:** [More Information Needed]
25
- - **Finetuned from model [optional]:** [More Information Needed]
26
 
27
- ### Model Sources [optional]
28
 
29
- <!-- Provide the basic links for the model. -->
30
-
31
- - **Repository:** [More Information Needed]
32
- - **Paper [optional]:** [More Information Needed]
33
- - **Demo [optional]:** [More Information Needed]
34
-
35
- ## Uses
36
-
37
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
 
39
- ### Direct Use
40
 
41
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
 
43
- [More Information Needed]
44
 
45
- ### Downstream Use [optional]
46
 
47
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
 
49
- [More Information Needed]
 
 
 
50
 
51
- ### Out-of-Scope Use
52
 
53
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
 
55
- [More Information Needed]
56
 
57
- ## Bias, Risks, and Limitations
58
 
59
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
 
61
- [More Information Needed]
62
 
63
  ### Recommendations
64
 
65
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
 
67
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
-
69
- ## How to Get Started with the Model
70
 
71
- Use the code below to get started with the model.
72
-
73
- [More Information Needed]
74
 
75
  ## Training Details
76
 
@@ -78,26 +62,8 @@ Use the code below to get started with the model.
78
 
79
  <!-- This should link to a Data 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. -->
80
 
81
- [More Information Needed]
82
-
83
- ### Training Procedure
84
-
85
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
-
87
- #### Preprocessing [optional]
88
-
89
- [More Information Needed]
90
-
91
 
92
- #### Training Hyperparameters
93
-
94
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
-
96
- #### Speeds, Sizes, Times [optional]
97
-
98
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
-
100
- [More Information Needed]
101
 
102
  ## Evaluation
103
 
@@ -105,118 +71,21 @@ Use the code below to get started with the model.
105
 
106
  ### Testing Data, Factors & Metrics
107
 
108
- #### Testing Data
109
-
110
- <!-- This should link to a Data Card if possible. -->
111
 
112
- [More Information Needed]
113
-
114
- #### Factors
115
-
116
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
-
118
- [More Information Needed]
119
 
120
  #### Metrics
121
 
122
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
 
124
- [More Information Needed]
125
 
126
  ### Results
127
 
128
- [More Information Needed]
129
-
130
- #### Summary
131
-
132
-
133
-
134
- ## Model Examination [optional]
135
-
136
- <!-- Relevant interpretability work for the model goes here -->
137
-
138
- [More Information Needed]
139
-
140
- ## Environmental Impact
141
-
142
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
-
144
- 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).
145
-
146
- - **Hardware Type:** [More Information Needed]
147
- - **Hours used:** [More Information Needed]
148
- - **Cloud Provider:** [More Information Needed]
149
- - **Compute Region:** [More Information Needed]
150
- - **Carbon Emitted:** [More Information Needed]
151
-
152
- ## Technical Specifications [optional]
153
-
154
- ### Model Architecture and Objective
155
-
156
- [More Information Needed]
157
-
158
- ### Compute Infrastructure
159
-
160
- [More Information Needed]
161
-
162
- #### Hardware
163
-
164
- [More Information Needed]
165
-
166
- #### Software
167
-
168
- [More Information Needed]
169
-
170
- ## Citation [optional]
171
-
172
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
-
174
- **BibTeX:**
175
-
176
- [More Information Needed]
177
-
178
- **APA:**
179
-
180
- [More Information Needed]
181
-
182
- ## Glossary [optional]
183
-
184
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
-
186
- [More Information Needed]
187
-
188
- ## More Information [optional]
189
-
190
- [More Information Needed]
191
-
192
- ## Model Card Authors [optional]
193
-
194
- [More Information Needed]
195
-
196
- ## Model Card Contact
197
-
198
- [More Information Needed]
199
-
200
-
201
- ## Training procedure
202
-
203
-
204
- The following `bitsandbytes` quantization config was used during training:
205
- - quant_method: bitsandbytes
206
- - load_in_8bit: False
207
- - load_in_4bit: True
208
- - llm_int8_threshold: 6.0
209
- - llm_int8_skip_modules: None
210
- - llm_int8_enable_fp32_cpu_offload: False
211
- - llm_int8_has_fp16_weight: False
212
- - bnb_4bit_quant_type: nf4
213
- - bnb_4bit_use_double_quant: True
214
- - bnb_4bit_compute_dtype: float16
215
-
216
- ### Framework versions
217
 
 
218
 
219
- - PEFT 0.6.0.dev0
220
  ## Training procedure
221
 
222
 
@@ -228,11 +97,11 @@ The following `bitsandbytes` quantization config was used during training:
228
  - llm_int8_skip_modules: None
229
  - llm_int8_enable_fp32_cpu_offload: False
230
  - llm_int8_has_fp16_weight: False
231
- - bnb_4bit_quant_type: nf4
232
- - bnb_4bit_use_double_quant: True
233
- - bnb_4bit_compute_dtype: float16
234
 
235
  ### Framework versions
236
 
237
 
238
- - PEFT 0.6.0.dev0
 
1
  ---
2
  library_name: peft
3
  base_model: core42/jais-13b
4
+ license: mit
5
+ datasets:
6
+ - arbml/Ashaar_dataset
7
+ language:
8
+ - ar
9
+ metrics:
10
+ - perplexity
11
+ - bertscore
12
  ---
13
 
14
  # Model Card for Model ID
15
 
16
+ Fine-tuned using QLoRA for poem generation task.
17
 
18
 
 
 
 
19
  ### Model Description
20
 
21
+ We utilize Ashaar dataset and fine-tune the model to generate poems.
 
 
 
 
 
 
 
 
 
22
 
23
+ The input to the model is structred as follows:
24
 
25
+ '''
 
 
 
 
 
 
 
 
26
 
27
+ \#\#\# Instruction: Generate a poem based on the following title, and the given era:
28
 
29
+ \#\#\# Input: \{Title of a poem + poet era\}
30
 
31
+ \#\#\# Response: \{Poem verses\}
32
 
33
+ '''
34
 
 
35
 
36
+ - **Developed by:** Abdelrahman ’Boda’ Sadallah, Anastasiia Demidova, Daria Kotova
37
+ - **Model type:** Causal LM
38
+ - **Language(s) (NLP):** Arabic
39
+ - **Finetuned from model [optional]:** core42/jais-13b
40
 
41
+ ### Model Sources
42
 
43
+ - **Repository:** https://github.com/BodaSadalla98/llm-optimized-fintuning
44
 
45
+ ## Uses
46
 
47
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
48
 
49
+ The model is the result of our AI project. If you intend to use it, please, refer to the repo.
50
 
 
51
 
52
  ### Recommendations
53
 
54
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
55
 
56
+ For improving stories generation, you can play parameters: temeperature, top_p/top_k, repetition_penalty, etc.
 
 
57
 
 
 
 
58
 
59
  ## Training Details
60
 
 
62
 
63
  <!-- This should link to a Data 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. -->
64
 
65
+ Link to the dataset on huggungface: https://huggingface.co/datasets/arbml/ashaar.
 
 
 
 
 
 
 
 
 
66
 
 
 
 
 
 
 
 
 
 
67
 
68
  ## Evaluation
69
 
 
71
 
72
  ### Testing Data, Factors & Metrics
73
 
 
 
 
74
 
75
+ Test split of the same dataset.
 
 
 
 
 
 
76
 
77
  #### Metrics
78
 
79
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
80
 
81
+ We are using perplexity and BERTScore.
82
 
83
  ### Results
84
 
85
+ Perplexity: 48.3125
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
 
87
+ BERTScore: 59.33
88
 
 
89
  ## Training procedure
90
 
91
 
 
97
  - llm_int8_skip_modules: None
98
  - llm_int8_enable_fp32_cpu_offload: False
99
  - llm_int8_has_fp16_weight: False
100
+ - bnb_4bit_quant_type: fp4
101
+ - bnb_4bit_use_double_quant: False
102
+ - bnb_4bit_compute_dtype: float32
103
 
104
  ### Framework versions
105
 
106
 
107
+ - PEFT 0.6.0.dev0