Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Model Card for Microsoft-phi-4-Instruct-AutoRound-GPTQ-4bit
|
2 |
+
|
3 |
+
Model Overview
|
4 |
+
|
5 |
+
Model Name: Microsoft-phi-4-Instruct-AutoRound-GPTQ-4bitModel Type: Instruction-tuned, Quantized GPT-4-based language modelQuantization: GPTQ 4-bitAuthor: Satwik11Hosted on: Hugging Face
|
6 |
+
|
7 |
+
Description
|
8 |
+
|
9 |
+
This model is a quantized version of the Microsoft phi-4 Instruct model, designed to deliver high performance while maintaining computational efficiency. By leveraging the GPTQ 4-bit quantization method, it enables deployment in environments with limited resources while retaining a high degree of accuracy.
|
10 |
+
|
11 |
+
The model is fine-tuned for instruction-following tasks, making it ideal for applications in conversational AI, question answering, and general-purpose text generation.
|
12 |
+
|
13 |
+
Key Features
|
14 |
+
|
15 |
+
Instruction-tuned: Fine-tuned to follow human-like instructions effectively.
|
16 |
+
|
17 |
+
Quantized for Efficiency: Uses GPTQ 4-bit quantization to reduce memory requirements and inference latency.
|
18 |
+
|
19 |
+
Pre-trained Base: Built on the Microsoft phi-4 framework, ensuring state-of-the-art performance on NLP tasks.
|
20 |
+
|
21 |
+
Use Cases
|
22 |
+
|
23 |
+
Chatbots and virtual assistants.
|
24 |
+
|
25 |
+
Summarization and content generation.
|
26 |
+
|
27 |
+
Research and educational applications.
|
28 |
+
|
29 |
+
Semantic search and knowledge retrieval.
|
30 |
+
|
31 |
+
Model Details
|
32 |
+
|
33 |
+
Architecture
|
34 |
+
|
35 |
+
Base Model: Microsoft phi-4
|
36 |
+
|
37 |
+
Quantization Technique: GPTQ (4-bit)
|
38 |
+
|
39 |
+
Language: English
|
40 |
+
|
41 |
+
Training Objective: Instruction-following fine-tuning
|
42 |
+
|