Update README.md
Browse files
README.md
CHANGED
@@ -1,20 +1,19 @@
|
|
1 |
---
|
2 |
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
3 |
tags:
|
4 |
-
- mistral
|
5 |
-
- hr
|
6 |
-
- human-resources
|
7 |
-
- recruitment
|
8 |
-
- intent-detection
|
9 |
-
- entity-extraction
|
10 |
-
- merged
|
11 |
-
- whisprnet
|
12 |
license: apache-2.0
|
13 |
---
|
14 |
|
15 |
-
#
|
16 |
|
17 |
-
This is the merged version of the
|
18 |
|
19 |
## Model Description
|
20 |
|
@@ -37,8 +36,8 @@ Fine-tuned Mistral-7B model for extracting intents and entities from recruitment
|
|
37 |
```python
|
38 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
39 |
|
40 |
-
model = AutoModelForCausalLM.from_pretrained("subashmourougayane/
|
41 |
-
tokenizer = AutoTokenizer.from_pretrained("subashmourougayane/
|
42 |
|
43 |
messages = [
|
44 |
{"role": "system", "content": "Extract intent and entities from HR requests. Return JSON format."},
|
@@ -58,10 +57,3 @@ print(response)
|
|
58 |
- **Response Time**: ~4.3 seconds average
|
59 |
- **GPU Memory**: ~4.4GB
|
60 |
|
61 |
-
## Original Adapter
|
62 |
-
|
63 |
-
This model was created by merging the adapter from: [subashmourougayane/whisprnet-hr-entity-extraction](https://huggingface.co/subashmourougayane/whisprnet-hr-entity-extraction)
|
64 |
-
|
65 |
-
## About WhisprNet.AI
|
66 |
-
|
67 |
-
WhisprNet.AI specializes in AI-powered recruitment and HR solutions.
|
|
|
1 |
---
|
2 |
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
3 |
tags:
|
4 |
+
- mistral
|
5 |
+
- hr
|
6 |
+
- human-resources
|
7 |
+
- recruitment
|
8 |
+
- intent-detection
|
9 |
+
- entity-extraction
|
10 |
+
- merged
|
|
|
11 |
license: apache-2.0
|
12 |
---
|
13 |
|
14 |
+
# Recruitment Intent & Entity Extraction (Merged Model)
|
15 |
|
16 |
+
This is the merged version of the recruitment intent and entity extraction model. No adapter loading required!
|
17 |
|
18 |
## Model Description
|
19 |
|
|
|
36 |
```python
|
37 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
38 |
|
39 |
+
model = AutoModelForCausalLM.from_pretrained("subashmourougayane/recruitement-intent-entity-extraction")
|
40 |
+
tokenizer = AutoTokenizer.from_pretrained("subashmourougayane/recruitement-intent-entity-extraction")
|
41 |
|
42 |
messages = [
|
43 |
{"role": "system", "content": "Extract intent and entities from HR requests. Return JSON format."},
|
|
|
57 |
- **Response Time**: ~4.3 seconds average
|
58 |
- **GPU Memory**: ~4.4GB
|
59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|