File size: 1,926 Bytes
6250780 3201bdd eb50516 |
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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
---
license: apache-2.0
language:
- id
tags:
- mistral
- text-generation-inference
---
### mistral-indo-7b
[Mistral 7b v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) fine-tuned on [Indonesian's instructions dataset](https://huggingface.co/datasets/sarahlintang/Alpaca_indo_instruct).
### Prompt template:
```
### Human: {Instruction}### Assistant: {response}
```
### Example of Usage
```
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer, GenerationConfig
model_id = "sarahlintang/mistral-indo-7b"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(model_id)
def create_instruction(instruction):
prompt = f"### Human: {instruction} ### Assistant: "
return prompt
def generate(
instruction,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
**kwargs
):
prompt = create_instruction(instruction)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to("cuda")
attention_mask = inputs["attention_mask"].to("cuda")
generation_config = GenerationConfig(
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
**kwargs,
)
with torch.no_grad():
generation_output = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=max_new_tokens,
early_stopping=True
)
s = generation_output.sequences[0]
output = tokenizer.decode(s)
return output.split("### Assistant:")[1].strip()
instruction = "Sebutkan lima macam makanan khas Indonesia."
print(generate(instruction))
```
|