Rezaul Karim commited on
Commit
d53107b
1 Parent(s): 39758da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -24
README.md CHANGED
@@ -11,25 +11,20 @@ https://huggingface.co/rezahf2024/fine_tuned_financial_setiment_analysis_gpt2_mo
11
  ## Model Details
12
 
13
  ### Model Description
14
-
15
- This a fine-tuned GPT2 model on the https://huggingface.co/datasets/FinGPT/fingpt-sentiment-train dataset for the down-stream financial sentiment analysis.
16
 
17
  - **Developed by:** Rezaul Karim, Ph.D.
18
- - **Funded by [optional]:** Self
19
- - **Shared by [optional]:** Rezaul Karim, Ph.D.
20
  - **Model type:** Fine-tuned GPT2
21
  - **Language(s) (NLP):** financial sentiment analysis
22
  - **License:** MIT
23
- - **Finetuned from model [optional]:** https://huggingface.co/datasets/mteb/tweet_sentiment_extraction
24
-
25
- ### Model Sources [optional]
26
 
 
27
  - **Repository:** https://github.com/rezacsedu/financial_sentiment_analysis_LLM
28
  - **Paper [optional]:** on the way
29
  - **Demo [optional]:** on the way
30
 
31
  ## Uses
32
-
33
  The model is already fine-tuned for downstream financial sentiment analysis tasks.
34
 
35
  ```
@@ -80,12 +75,6 @@ for label, prob in predictions:
80
  print(f"{label}: {prob:.3f}")
81
  ```
82
 
83
- ## How to Get Started with the Model
84
-
85
- Use the code below to get started with the model.
86
-
87
- [More Information Needed]
88
-
89
  ## Training Details
90
 
91
  ### Training Data
@@ -168,15 +157,11 @@ trainer.save_model("fine_tuned_finsetiment_model")
168
  ```
169
 
170
  #### Training Hyperparameters
171
-
172
  - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
173
 
174
  #### Speeds, Sizes, Times [optional]
175
-
176
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
177
 
178
- [More Information Needed]
179
-
180
  ## Evaluation
181
 
182
  ```
@@ -193,19 +178,14 @@ def compute_metrics(eval_pred):
193
 
194
  ### Results
195
 
196
- [More Information Needed]
197
 
198
  #### Summary
199
 
200
  ## Citation [optional]
201
 
202
- <!-- If a paper or blog post is introducing the model, the APA and Bibtex information for that should go in this section. -->
203
 
204
  **BibTeX:**
205
 
206
- [More Information Needed]
207
-
208
-
209
  ## Model Card Contact
210
-
211
  rezaul.karim.fit@gmail.com
 
11
  ## Model Details
12
 
13
  ### Model Description
14
+ This a fine-tuned GPT2 model on the https://huggingface.co/datasets/FinGPT/fingpt-sentiment-train dataset for the downstream financial sentiment analysis.
 
15
 
16
  - **Developed by:** Rezaul Karim, Ph.D.
 
 
17
  - **Model type:** Fine-tuned GPT2
18
  - **Language(s) (NLP):** financial sentiment analysis
19
  - **License:** MIT
20
+ - **Finetuned from model:** https://huggingface.co/datasets/mteb/tweet_sentiment_extraction
 
 
21
 
22
+ ### Model Sources
23
  - **Repository:** https://github.com/rezacsedu/financial_sentiment_analysis_LLM
24
  - **Paper [optional]:** on the way
25
  - **Demo [optional]:** on the way
26
 
27
  ## Uses
 
28
  The model is already fine-tuned for downstream financial sentiment analysis tasks.
29
 
30
  ```
 
75
  print(f"{label}: {prob:.3f}")
76
  ```
77
 
 
 
 
 
 
 
78
  ## Training Details
79
 
80
  ### Training Data
 
157
  ```
158
 
159
  #### Training Hyperparameters
 
160
  - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
161
 
162
  #### Speeds, Sizes, Times [optional]
 
163
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
164
 
 
 
165
  ## Evaluation
166
 
167
  ```
 
178
 
179
  ### Results
180
 
 
181
 
182
  #### Summary
183
 
184
  ## Citation [optional]
185
 
186
+ <!-- If a paper or blog post introduces the model, the APA and Bibtex information should go in this section. -->
187
 
188
  **BibTeX:**
189
 
 
 
 
190
  ## Model Card Contact
 
191
  rezaul.karim.fit@gmail.com