File size: 2,957 Bytes
889d59b 1aa7d35 9c90ca7 58e687a |
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 74 75 76 77 78 79 80 81 82 83 84 |
---
license: apache-2.0
language:
- id
base_model:
- sarahlintang/mistral-indo-7b
pipeline_tag: text-generation
library_name: transformers
tags:
- mistral
- text-generation-inference
---
# CiptakerLM v1
Dataset used for Fine-Tuning: <a href="https://github.com/Willy030125/LLM_Ciptaker/blob/main/Notebook/Ciptaker-sft-data-preparation.ipynb">Ciptaker-sft-data-preparation.ipynb</a><br>
Base model: <a href="https://huggingface.co/sarahlintang/mistral-indo-7b">sarahlintang/mistral-indo-7b</a><br>
Trained on 1x3090 @ 24 epochs<br>
Train logs, metrics, and params: https://wandb.ai/willy030125/MistralCiptaker_v0.2_SFT/runs/c9so5vf8 <br>
Inference example using Colab T4: <a href="https://github.com/Willy030125/LLM_Ciptaker/blob/main/Notebook/CiptakerLM-fine-tune-inference.ipynb">CiptakerLM-fine-tune-inference.ipynb</a><br>
Eval results using Colab T4: <a href="https://github.com/Willy030125/LLM_Ciptaker/blob/main/Notebook/CiptakerLM-fin-tune-eval.ipynb">CiptakerLM-fine-tune-eval.ipynb</a><br>
### Prompt template:
```
### Human: {Instruction} ### Assistant: {response}
```
### Usage example:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer, GenerationConfig
model_id = "Willy030125/CiptakerLM-v1"
device = "cuda" if torch.cuda.is_available() else "cpu"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to(device)
def create_instruction(instruction):
prompt = f"### Human: {instruction} ### Assistant: "
return prompt
def generate(
instruction,
max_new_tokens=2048,
temperature=0.1,
top_p=0.95,
top_k=40,
num_beams=4,
**kwargs
):
prompt = create_instruction(instruction)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(device)
attention_mask = inputs["attention_mask"].to(device)
generation_config = GenerationConfig(
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
do_sample=True,
**kwargs,
)
with torch.no_grad():
generation_output = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
generation_config=generation_config,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
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, skip_special_tokens=True)
return output.split("### Assistant:")[1].strip()
instruction = "Apa sanksi bagi pengusaha yang melanggar ketentuan dalam Pasal 42 ayat (2) tentang pekerja asing?"
print(generate(instruction))
```
Output:
> Pengusaha dapat dikenai sanksi pidana penjara 1-4 tahun dan/atau denda antara Rp100.000.000 hingga Rp400.000.000. |