Rezaul Karim
commited on
Commit
•
d53107b
1
Parent(s):
39758da
Update README.md
Browse files
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
|
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
|
203 |
|
204 |
**BibTeX:**
|
205 |
|
206 |
-
[More Information Needed]
|
207 |
-
|
208 |
-
|
209 |
## Model Card Contact
|
210 |
-
|
211 |
|
|
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 |