Commit
•
c069609
1
Parent(s):
22de0c3
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
3 |
datasets:
|
4 |
-
-
|
5 |
library_name: peft
|
6 |
license: apache-2.0
|
7 |
tags:
|
@@ -9,33 +9,38 @@ tags:
|
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
model-index:
|
12 |
-
- name: business_mistral-
|
13 |
results: []
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vjayram-enag-pes-university/huggingface/runs/u8906alp)
|
20 |
-
#
|
21 |
|
22 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: 0.5729
|
25 |
|
26 |
## Model description
|
27 |
|
28 |
-
|
|
|
|
|
29 |
|
30 |
## Intended uses & limitations
|
31 |
|
32 |
-
|
33 |
|
34 |
## Training and evaluation data
|
35 |
|
36 |
-
|
37 |
-
|
38 |
-
|
|
|
39 |
|
40 |
### Training hyperparameters
|
41 |
|
|
|
1 |
---
|
2 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
3 |
datasets:
|
4 |
+
- theoldmandthesea/17k_business_book
|
5 |
library_name: peft
|
6 |
license: apache-2.0
|
7 |
tags:
|
|
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
model-index:
|
12 |
+
- name: business_mistral-v1.0
|
13 |
results: []
|
14 |
+
language:
|
15 |
+
- en
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
should probably proofread and complete it, then remove this comment. -->
|
20 |
|
21 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vjayram-enag-pes-university/huggingface/runs/u8906alp)
|
22 |
+
# Mistral 7B Fine-Tuned for Business
|
23 |
|
24 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the [theoldmandthesea/17k_business_book](https://huggingface.co/datasets/theoldmandthesea/17k_business_book) dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 0.5729
|
27 |
|
28 |
## Model description
|
29 |
|
30 |
+
- Base Model: [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
|
31 |
+
- Quantization: 4 Bit
|
32 |
+
- Tokenizer: [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
|
33 |
|
34 |
## Intended uses & limitations
|
35 |
|
36 |
+
Mainly intended to be used at the backend of a chatbot application meant to assist children and teenager with knowledge of business and finances.
|
37 |
|
38 |
## Training and evaluation data
|
39 |
|
40 |
+
- Total number of samples: 17480
|
41 |
+
-
|
42 |
+
- Number of Training Samples: 13984
|
43 |
+
- Number of Validation / Test Samples: 3496
|
44 |
|
45 |
### Training hyperparameters
|
46 |
|