Commit
•
5f0365d
1
Parent(s):
84c2c45
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,6 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
-
- de
|
| 5 |
-
- fr
|
| 6 |
-
- it
|
| 7 |
-
- pt
|
| 8 |
-
- hi
|
| 9 |
-
- es
|
| 10 |
-
- th
|
| 11 |
license: apache-2.0
|
| 12 |
library_name: transformers
|
| 13 |
tags:
|
|
@@ -15,13 +8,15 @@ tags:
|
|
| 15 |
- auto-round
|
| 16 |
- intel
|
| 17 |
- gptq
|
| 18 |
-
- awq
|
| 19 |
- auto-awq
|
| 20 |
- autoawq
|
|
|
|
| 21 |
- woq
|
| 22 |
-
- meta
|
| 23 |
- pytorch
|
| 24 |
- transformers
|
|
|
|
|
|
|
|
|
|
| 25 |
model_name: SmolLM2 1.7B
|
| 26 |
base_model: HuggingFaceTB/SmolLM2-1.7B
|
| 27 |
inference: false
|
|
@@ -34,7 +29,7 @@ quantized_by: fbaldassarri
|
|
| 34 |
|
| 35 |
## Model Information
|
| 36 |
|
| 37 |
-
Quantized version of [HuggingFaceTB/SmolLM2-1.7B](HuggingFaceTB/SmolLM2-1.7B) using torch.float32 for quantization tuning.
|
| 38 |
- 4 bits (INT4)
|
| 39 |
- group size = 128
|
| 40 |
- Symmetrical Quantization
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
|
|
|
| 8 |
- auto-round
|
| 9 |
- intel
|
| 10 |
- gptq
|
|
|
|
| 11 |
- auto-awq
|
| 12 |
- autoawq
|
| 13 |
+
- awq
|
| 14 |
- woq
|
|
|
|
| 15 |
- pytorch
|
| 16 |
- transformers
|
| 17 |
+
- safetensors
|
| 18 |
+
- onnx
|
| 19 |
+
- transformers.js
|
| 20 |
model_name: SmolLM2 1.7B
|
| 21 |
base_model: HuggingFaceTB/SmolLM2-1.7B
|
| 22 |
inference: false
|
|
|
|
| 29 |
|
| 30 |
## Model Information
|
| 31 |
|
| 32 |
+
Quantized version of [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B) using torch.float32 for quantization tuning.
|
| 33 |
- 4 bits (INT4)
|
| 34 |
- group size = 128
|
| 35 |
- Symmetrical Quantization
|