Update README.md
Browse files
README.md
CHANGED
@@ -3,7 +3,7 @@ base_model: meta-llama/Llama-3.3-70B-Instruct
|
|
3 |
|
4 |
---
|
5 |
|
6 |
-
# MISHANM/meta-llama-3.3-70B-Instruct-int4
|
7 |
|
8 |
This model is an INT4 quantized version of the meta-llama/Llama-3.3-70B-Instruct, offering maximum compression for specialized hardware environments, supported languages : English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
|
9 |
|
@@ -30,7 +30,7 @@ import torch
|
|
30 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
31 |
|
32 |
# Load the fine-tuned model and tokenizer
|
33 |
-
model_path = "MISHANM/meta-llama-3.3-70B-Instruct-int4"
|
34 |
|
35 |
model = AutoModelForCausalLM.from_pretrained(model_path,device_map="auto")
|
36 |
|
@@ -68,7 +68,7 @@ print(text)
|
|
68 |
|
69 |
## Citation Information
|
70 |
```
|
71 |
-
@misc{MISHANM/meta-llama-3.3-70B-Instruct-int4,
|
72 |
author = {Mishan Maurya},
|
73 |
title = {Introducing INT4 quantized version of meta-llama/Llama-3.3-70B-Instruct},
|
74 |
year = {2024},
|
|
|
3 |
|
4 |
---
|
5 |
|
6 |
+
# MISHANM/meta-llama-Llama-3.3-70B-Instruct-int4
|
7 |
|
8 |
This model is an INT4 quantized version of the meta-llama/Llama-3.3-70B-Instruct, offering maximum compression for specialized hardware environments, supported languages : English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
|
9 |
|
|
|
30 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
31 |
|
32 |
# Load the fine-tuned model and tokenizer
|
33 |
+
model_path = "MISHANM/meta-llama-Llama-3.3-70B-Instruct-int4"
|
34 |
|
35 |
model = AutoModelForCausalLM.from_pretrained(model_path,device_map="auto")
|
36 |
|
|
|
68 |
|
69 |
## Citation Information
|
70 |
```
|
71 |
+
@misc{MISHANM/meta-llama-Llama-3.3-70B-Instruct-int4,
|
72 |
author = {Mishan Maurya},
|
73 |
title = {Introducing INT4 quantized version of meta-llama/Llama-3.3-70B-Instruct},
|
74 |
year = {2024},
|