Update README.md
Browse files
README.md
CHANGED
@@ -8,12 +8,12 @@ Benchmark results are in progress.
|
|
8 |
I will upload it at a later date.
|
9 |
|
10 |
|
11 |
-
sample code
|
12 |
-
|
13 |
pip install auto-gptq
|
14 |
-
|
15 |
|
16 |
-
|
17 |
from transformers import AutoTokenizer
|
18 |
from auto_gptq import AutoGPTQForCausalLM
|
19 |
|
@@ -34,7 +34,7 @@ prompt_template = f"### Instruction: {prompt}\n### Response:"
|
|
34 |
tokens = tokenizer(prompt_template, return_tensors="pt").to("cuda:0").input_ids
|
35 |
output = model.generate(input_ids=tokens, max_new_tokens=100, do_sample=True, temperature=0.8)
|
36 |
print(tokenizer.decode(output[0]))
|
37 |
-
|
38 |
|
39 |
-
See Also
|
40 |
https://github.com/PanQiWei/AutoGPTQ/blob/main/docs/tutorial/01-Quick-Start.md
|
|
|
8 |
I will upload it at a later date.
|
9 |
|
10 |
|
11 |
+
### sample code
|
12 |
+
```
|
13 |
pip install auto-gptq
|
14 |
+
```
|
15 |
|
16 |
+
```
|
17 |
from transformers import AutoTokenizer
|
18 |
from auto_gptq import AutoGPTQForCausalLM
|
19 |
|
|
|
34 |
tokens = tokenizer(prompt_template, return_tensors="pt").to("cuda:0").input_ids
|
35 |
output = model.generate(input_ids=tokens, max_new_tokens=100, do_sample=True, temperature=0.8)
|
36 |
print(tokenizer.decode(output[0]))
|
37 |
+
```
|
38 |
|
39 |
+
### See Also
|
40 |
https://github.com/PanQiWei/AutoGPTQ/blob/main/docs/tutorial/01-Quick-Start.md
|