Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🧠 Phi-2 GPTQ (Quantized)
|
| 2 |
|
| 3 |
This repository provides a 4-bit GPTQ quantized version of the **Phi-2** model by Microsoft, optimized for efficient inference using `gptqmodel`.
|
|
@@ -30,8 +46,8 @@ This model is ready-to-use with the Hugging Face `transformers` library.
|
|
| 30 |
|
| 31 |
## 📖 References
|
| 32 |
|
| 33 |
-
- Microsoft Phi-2: https://huggingface.co/microsoft/phi-2
|
| 34 |
-
- GPTQModel: https://github.com/ModelCoud/GPTQModel
|
| 35 |
- Transformers: https://github.com/huggingface/transformers
|
| 36 |
|
| 37 |
## ⚖️ License
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- gptq
|
| 5 |
+
- quantized
|
| 6 |
+
- causal-lm
|
| 7 |
+
- transformers
|
| 8 |
+
- pytorch
|
| 9 |
+
- phi-2
|
| 10 |
+
- text-generation
|
| 11 |
+
library_name: transformers
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
base_model: microsoft/phi-2
|
| 14 |
+
inference: true
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
# 🧠 Phi-2 GPTQ (Quantized)
|
| 18 |
|
| 19 |
This repository provides a 4-bit GPTQ quantized version of the **Phi-2** model by Microsoft, optimized for efficient inference using `gptqmodel`.
|
|
|
|
| 46 |
|
| 47 |
## 📖 References
|
| 48 |
|
| 49 |
+
- Microsoft Phi-2: https://huggingface.co/microsoft/phi-2
|
| 50 |
+
- GPTQModel: https://github.com/ModelCoud/GPTQModel
|
| 51 |
- Transformers: https://github.com/huggingface/transformers
|
| 52 |
|
| 53 |
## ⚖️ License
|