File size: 1,396 Bytes
f8df1d2 2c7164b f8df1d2 2c7164b f8df1d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
---
license: other
inference: false
language:
- en
pipeline_tag: text-generation
tags:
- transformers
- stabilityai
- gguf
- imatrix
- stable-code-instruct-3b
---
Quantizations of https://huggingface.co/stabilityai/stable-code-instruct-3b
# From original readme
## Usage
Here's how you can run the model use the model:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stable-code-instruct-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("stabilityai/stable-code-instruct-3b", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.eval()
model = model.cuda()
messages = [
{
"role": "system",
"content": "You are a helpful and polite assistant",
},
{
"role": "user",
"content": "Write a simple website in HTML. When a user clicks the button, it shows a random joke from a list of 4 jokes."
},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
tokens = model.generate(
**inputs,
max_new_tokens=1024,
temperature=0.5,
top_p=0.95,
top_k=100,
do_sample=True,
use_cache=True
)
output = tokenizer.batch_decode(tokens[:, inputs.input_ids.shape[-1]:], skip_special_tokens=False)[0]
```
``` |