Update README_en.md
Browse files- README_en.md +2 -0
README_en.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
# microsoft/phi-4 Quantized Models
|
| 2 |
## Overview
|
| 3 |
This model applies GPTQ quantization to [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) as the base model. It optimizes performance in Japanese environments by using Japanese text as calibration data.
|
|
|
|
| 4 |
- **Model Variants**:
|
| 5 |
- [nejumi/phi-4-GPTQ-Int4-calib-ja-1k](https://huggingface.co/nejumi/phi-4-GPTQ-Int4-calib-ja-1k)
|
| 6 |
- [nejumi/phi-4-GPTQ-Int8-calib-ja-1k](https://huggingface.co/nejumi/phi-4-GPTQ-Int8-calib-ja-1k)
|
|
@@ -15,6 +16,7 @@ This model applies GPTQ quantization to [microsoft/phi-4](https://huggingface.co
|
|
| 15 |
- desc_act: True
|
| 16 |
- use_exllama: False
|
| 17 |
- model_seqlen: 2048
|
|
|
|
| 18 |
---
|
| 19 |
## Performance Evaluation
|
| 20 |
Evaluation results from [Nejumi LLM Leaderboard 3 (W&B)](https://wandb.ai/wandb-japan/llm-leaderboard3/reports/Nejumi-LLM-3---Vmlldzo4NTI1NTUx)
|
|
|
|
| 1 |
# microsoft/phi-4 Quantized Models
|
| 2 |
## Overview
|
| 3 |
This model applies GPTQ quantization to [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) as the base model. It optimizes performance in Japanese environments by using Japanese text as calibration data.
|
| 4 |
+
|
| 5 |
- **Model Variants**:
|
| 6 |
- [nejumi/phi-4-GPTQ-Int4-calib-ja-1k](https://huggingface.co/nejumi/phi-4-GPTQ-Int4-calib-ja-1k)
|
| 7 |
- [nejumi/phi-4-GPTQ-Int8-calib-ja-1k](https://huggingface.co/nejumi/phi-4-GPTQ-Int8-calib-ja-1k)
|
|
|
|
| 16 |
- desc_act: True
|
| 17 |
- use_exllama: False
|
| 18 |
- model_seqlen: 2048
|
| 19 |
+
|
| 20 |
---
|
| 21 |
## Performance Evaluation
|
| 22 |
Evaluation results from [Nejumi LLM Leaderboard 3 (W&B)](https://wandb.ai/wandb-japan/llm-leaderboard3/reports/Nejumi-LLM-3---Vmlldzo4NTI1NTUx)
|