Commit
·
53eff1c
1
Parent(s):
4d22a51
device_map
Browse files
README.md
CHANGED
|
@@ -119,6 +119,9 @@ m.save_pretrained("nyc-savvy")
|
|
| 119 |
You might wonder if the model successfully learned anything about NYC or is the same old LLaMa2. With your prompt not adding clues, try this from the `pefttester.py` script in this repo:
|
| 120 |
|
| 121 |
```python
|
|
|
|
|
|
|
|
|
|
| 122 |
messages = "A chat between a curious human and an assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n"
|
| 123 |
messages += "### Human: What museums should I visit? - My kids are aged 12 and 5"
|
| 124 |
messages += "### Assistant: "
|
|
|
|
| 119 |
You might wonder if the model successfully learned anything about NYC or is the same old LLaMa2. With your prompt not adding clues, try this from the `pefttester.py` script in this repo:
|
| 120 |
|
| 121 |
```python
|
| 122 |
+
m = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
| 123 |
+
tok = LlamaTokenizer.from_pretrained(model_name)
|
| 124 |
+
|
| 125 |
messages = "A chat between a curious human and an assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n"
|
| 126 |
messages += "### Human: What museums should I visit? - My kids are aged 12 and 5"
|
| 127 |
messages += "### Assistant: "
|