Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ language:
|
|
7 |
- en
|
8 |
---
|
9 |
|
10 |
-
#
|
11 |
|
12 |
- Orginal model : [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
|
13 |
- Quantized using [intel/auto-round](https://github.com/intel/auto-round)
|
@@ -78,12 +78,12 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
|
78 |
torch.random.manual_seed(0)
|
79 |
|
80 |
model = AutoModelForCausalLM.from_pretrained(
|
81 |
-
"ssuncheol/
|
82 |
device_map="cuda",
|
83 |
torch_dtype="auto",
|
84 |
trust_remote_code=True,
|
85 |
)
|
86 |
-
tokenizer = AutoTokenizer.from_pretrained("ssuncheol/
|
87 |
|
88 |
messages = [
|
89 |
{"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
|
|
|
7 |
- en
|
8 |
---
|
9 |
|
10 |
+
# Phi-3-mini-128k-instruct-int4
|
11 |
|
12 |
- Orginal model : [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
|
13 |
- Quantized using [intel/auto-round](https://github.com/intel/auto-round)
|
|
|
78 |
torch.random.manual_seed(0)
|
79 |
|
80 |
model = AutoModelForCausalLM.from_pretrained(
|
81 |
+
"ssuncheol/Phi-3-mini-128k-instruct-int4",
|
82 |
device_map="cuda",
|
83 |
torch_dtype="auto",
|
84 |
trust_remote_code=True,
|
85 |
)
|
86 |
+
tokenizer = AutoTokenizer.from_pretrained("ssuncheol/Phi-3-mini-128k-instruct-int4")
|
87 |
|
88 |
messages = [
|
89 |
{"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
|