egon-nlpulse
commited on
Commit
•
ff43c14
1
Parent(s):
02086ca
ajustes
Browse files
README.md
CHANGED
@@ -5,6 +5,7 @@ language:
|
|
5 |
- en
|
6 |
datasets:
|
7 |
- Abirate/english_quotes
|
|
|
8 |
---
|
9 |
|
10 |
# Quantization 4Bits - 5.02 GB GPU memory usage for inference:
|
@@ -52,7 +53,6 @@ Swap: 37Gi 3.8Gi 34Gi
|
|
52 |
|
53 |
## Inference
|
54 |
```
|
55 |
-
import os
|
56 |
import torch
|
57 |
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
58 |
from peft import PeftConfig, PeftModel
|
|
|
5 |
- en
|
6 |
datasets:
|
7 |
- Abirate/english_quotes
|
8 |
+
pipeline_tag: text-generation
|
9 |
---
|
10 |
|
11 |
# Quantization 4Bits - 5.02 GB GPU memory usage for inference:
|
|
|
53 |
|
54 |
## Inference
|
55 |
```
|
|
|
56 |
import torch
|
57 |
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
58 |
from peft import PeftConfig, PeftModel
|