Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Qwen2.5-0.5B-Instruct AWQ + FP8_DYNAMIC
|
| 2 |
|
| 3 |
This is a quantized version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) using AWQ + FP8_DYNAMIC quantization scheme.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- quantization
|
| 8 |
+
- awq
|
| 9 |
+
- fp8
|
| 10 |
+
- llm-compressor
|
| 11 |
+
- vllm
|
| 12 |
+
- model-compression
|
| 13 |
+
- qwen2.5
|
| 14 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 15 |
+
datasets:
|
| 16 |
+
- gsm8k
|
| 17 |
+
model-index:
|
| 18 |
+
- name: Qwen2.5-0.5B-AWQ-FP8-Dynamic
|
| 19 |
+
results:
|
| 20 |
+
- task:
|
| 21 |
+
type: text-generation
|
| 22 |
+
name: Text Generation
|
| 23 |
+
dataset:
|
| 24 |
+
name: GSM8K
|
| 25 |
+
type: gsm8k
|
| 26 |
+
metrics:
|
| 27 |
+
- type: exact_match
|
| 28 |
+
value: 22.67
|
| 29 |
+
name: Strict Match
|
| 30 |
+
- type: flexible_extract
|
| 31 |
+
value: 30.78
|
| 32 |
+
name: Flexible Extract
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
# Qwen2.5-0.5B-Instruct AWQ + FP8_DYNAMIC
|
| 36 |
|
| 37 |
This is a quantized version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) using AWQ + FP8_DYNAMIC quantization scheme.
|