File size: 2,434 Bytes
540441b bb3dd1e 540441b bb3dd1e db3dc65 bb3dd1e |
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 85 86 87 88 89 90 91 92 93 94 95 96 |
---
base_model: llm-jp/llm-jp-3-13b
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
datasets:
- kinokokoro/ichikara-instruction-003
---
# Uploaded model
- **Developed by:** Rumi
- **License:** apache-2.0
- **Finetuned from model :** llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
# How to conduct inference
```
from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re
# Base model id and LoRA adapter ID
base_model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "Rumi/llm-jp_SFT_rn_2024-12-14_06"
# Log in with your Hugging Face token
HF_TOKEN = "hogehoge"
from huggingface_hub import login
login(HF_TOKEN)
# Download the original model
dtype = None
load_in_4bit = True
base_model, tokenizer = FastLanguageModel.from_pretrained(
model_name=base_model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
# Merge adapter to the base model
model = PeftModel.from_pretrained(base_model, adapter_id, token = HF_TOKEN)
# Read evaluation dataset
datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
item = ""
for line in f:
line = line.strip()
item += line
if item.endswith("}"):
datasets.append(json.loads(item))
item = ""
# Change the format and conduct the evaluation
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input = dt["input"]
prompt = f"""### 指示\n{input}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
# Save result in the jsonl format
json_file_id = re.sub(".*/", "", adapter_id)
with open(f"/content/{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
```
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |