Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ In the Transformers library, one can use [chat templates](https://huggingface.co
|
|
| 42 |
```python
|
| 43 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 44 |
|
| 45 |
-
model_id = "AlphaRandy/
|
| 46 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 47 |
|
| 48 |
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
|
@@ -72,7 +72,7 @@ Note `float16` precision only works on GPU devices
|
|
| 72 |
+ import torch
|
| 73 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 74 |
|
| 75 |
-
model_id = "AlphaRandy/
|
| 76 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 77 |
|
| 78 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
|
|
@@ -93,7 +93,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
| 93 |
+ import torch
|
| 94 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 95 |
|
| 96 |
-
model_id = "AlphaRandy/
|
| 97 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 98 |
|
| 99 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
|
|
@@ -121,7 +121,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
| 121 |
+ import torch
|
| 122 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 123 |
|
| 124 |
-
model_id = "AlphaRandy/
|
| 125 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 126 |
|
| 127 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True, device_map="auto")
|
|
|
|
| 42 |
```python
|
| 43 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 44 |
|
| 45 |
+
model_id = "AlphaRandy/WhelanChatBot"
|
| 46 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 47 |
|
| 48 |
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
|
|
|
| 72 |
+ import torch
|
| 73 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 74 |
|
| 75 |
+
model_id = "AlphaRandy/WhelanChatBot"
|
| 76 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 77 |
|
| 78 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
|
|
|
|
| 93 |
+ import torch
|
| 94 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 95 |
|
| 96 |
+
model_id = "AlphaRandy/WhelanChatBot"
|
| 97 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 98 |
|
| 99 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
|
|
|
|
| 121 |
+ import torch
|
| 122 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 123 |
|
| 124 |
+
model_id = "AlphaRandy/WhelanChatBot"
|
| 125 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 126 |
|
| 127 |
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True, device_map="auto")
|