Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -16,6 +16,23 @@ widget:
|
|
| 16 |
- role: user
|
| 17 |
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
| 18 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Model Summary
|
| 20 |
|
| 21 |
The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties.
|
|
|
|
| 16 |
- role: user
|
| 17 |
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
| 18 |
---
|
| 19 |
+
**Exllamav2** quant (**exl2** / **3.5 bpw**) made with ExLlamaV2 v0.0.21
|
| 20 |
+
|
| 21 |
+
Other EXL2 quants:
|
| 22 |
+
| **Quant** | **Model Size** | **lm_head** |
|
| 23 |
+
| ----- | ---------- | ------- |
|
| 24 |
+
|<center>**[2.2](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-2_2bpw_exl2)**</center> | <center>4032 MB</center> | <center>6</center> |
|
| 25 |
+
|<center>**[2.5](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-2_5bpw_exl2)**</center> | <center>4495 MB</center> | <center>6</center> |
|
| 26 |
+
|<center>**[3.0](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-3_0bpw_exl2)**</center> | <center>5312 MB</center> | <center>6</center> |
|
| 27 |
+
|<center>**[3.5](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-3_5bpw_exl2)**</center> | <center>6120 MB</center> | <center>6</center> |
|
| 28 |
+
|<center>**[3.75](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-3_75bpw_exl2)**</center> | <center>6531 MB</center> | <center>6</center> |
|
| 29 |
+
|<center>**[4.0](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-4_0bpw_exl2)**</center> | <center>6937 MB</center> | <center>6</center> |
|
| 30 |
+
|<center>**[4.25](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-4_25bpw_exl2)**</center> | <center>7343 MB</center> | <center>6</center> |
|
| 31 |
+
|<center>**[5.0](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-5_0bpw_exl2)**</center> | <center>8555 MB</center> | <center>6</center> |
|
| 32 |
+
|<center>**[6.0](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-6_0bpw_exl2)**</center> | <center>10213 MB</center> | <center>8</center> |
|
| 33 |
+
|<center>**[6.5](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-6_5bpw_exl2)**</center> | <center>11024 MB</center> | <center>8</center> |
|
| 34 |
+
|<center>**[8.0](https://huggingface.co/Zoyd/microsoft_Phi-3-medium-4k-instruct-8_0bpw_exl2)**</center> | <center>12599 MB</center> | <center>8</center> |
|
| 35 |
+
|
| 36 |
## Model Summary
|
| 37 |
|
| 38 |
The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties.
|