[doc] Fold long code blocks to improve readability (#19926)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
@@ -43,17 +43,19 @@ llm = LLM(
|
||||
|
||||
## Read gptq format checkpoint
|
||||
|
||||
```python
|
||||
from vllm import LLM
|
||||
import torch
|
||||
??? Code
|
||||
|
||||
# "hxbgsyxh/llama-13b-4bit-g-1" is a pre-quantized checkpoint.
|
||||
model_id = "hxbgsyxh/llama-13b-4bit-g-1"
|
||||
llm = LLM(
|
||||
model=model_id,
|
||||
dtype=torch.float16,
|
||||
trust_remote_code=True,
|
||||
quantization="bitblas",
|
||||
max_model_len=1024
|
||||
)
|
||||
```
|
||||
```python
|
||||
from vllm import LLM
|
||||
import torch
|
||||
|
||||
# "hxbgsyxh/llama-13b-4bit-g-1" is a pre-quantized checkpoint.
|
||||
model_id = "hxbgsyxh/llama-13b-4bit-g-1"
|
||||
llm = LLM(
|
||||
model=model_id,
|
||||
dtype=torch.float16,
|
||||
trust_remote_code=True,
|
||||
quantization="bitblas",
|
||||
max_model_len=1024
|
||||
)
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user