Update README.md
Browse files
README.md
CHANGED
@@ -58,18 +58,16 @@ You can run the smashed model with these steps:
|
|
58 |
pip install autoawq
|
59 |
```
|
60 |
2. Load & run the model.
|
61 |
-
```python
|
62 |
-
|
63 |
-
|
64 |
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
input_ids = tokenizer("Quelle est la couleur des pruneaux?", return_tensors='pt').to(next(model.parameters()).device)["input_ids"]
|
69 |
-
|
70 |
-
outputs = model.generate(input_ids, max_new_tokens=216)
|
71 |
-
tokenizer.decode(outputs[0])
|
72 |
|
|
|
|
|
|
|
73 |
```
|
74 |
|
75 |
## Configurations
|
|
|
58 |
pip install autoawq
|
59 |
```
|
60 |
2. Load & run the model.
|
61 |
+
```python
|
62 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
63 |
+
from awq import AutoAWQForCausalLM
|
64 |
|
65 |
+
model = AutoAWQForCausalLM.from_quantized("PrunaAI/OpenLLM-France-Lucie-7B-AWQ-4bit-smashed", trust_remote_code=True, device_map='auto')
|
66 |
+
tokenizer = AutoTokenizer.from_pretrained("OpenLLM-France/Lucie-7B")
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
+
input_ids = tokenizer("Quelle est la couleur des pruneaux?", return_tensors='pt').to(next(model.parameters()).device)["input_ids"]
|
69 |
+
outputs = model.generate(input_ids, max_new_tokens=216)
|
70 |
+
tokenizer.decode(outputs[0])
|
71 |
```
|
72 |
|
73 |
## Configurations
|