Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ ipt-350m is:
|
|
| 27 |
```python
|
| 28 |
import transformers
|
| 29 |
model = transformers.AutoModelForCausalLM.from_pretrained(
|
| 30 |
-
'efederici/ipt-350m
|
| 31 |
trust_remote_code=True
|
| 32 |
)
|
| 33 |
```
|
|
@@ -38,7 +38,7 @@ To use the optimized [triton implementation](https://github.com/openai/triton) o
|
|
| 38 |
import torch
|
| 39 |
import transformers
|
| 40 |
|
| 41 |
-
name = 'efederici/ipt-350m
|
| 42 |
|
| 43 |
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
|
| 44 |
config.attn_config['attn_impl'] = 'triton'
|
|
@@ -57,7 +57,7 @@ Although the model was trained with a sequence length of 2048, ALiBi enables to
|
|
| 57 |
```python
|
| 58 |
import transformers
|
| 59 |
|
| 60 |
-
name = 'efederici/ipt-350m
|
| 61 |
|
| 62 |
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
|
| 63 |
config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096
|
|
|
|
| 27 |
```python
|
| 28 |
import transformers
|
| 29 |
model = transformers.AutoModelForCausalLM.from_pretrained(
|
| 30 |
+
'efederici/ipt-350m',
|
| 31 |
trust_remote_code=True
|
| 32 |
)
|
| 33 |
```
|
|
|
|
| 38 |
import torch
|
| 39 |
import transformers
|
| 40 |
|
| 41 |
+
name = 'efederici/ipt-350m'
|
| 42 |
|
| 43 |
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
|
| 44 |
config.attn_config['attn_impl'] = 'triton'
|
|
|
|
| 57 |
```python
|
| 58 |
import transformers
|
| 59 |
|
| 60 |
+
name = 'efederici/ipt-350m'
|
| 61 |
|
| 62 |
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
|
| 63 |
config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096
|