File size: 1,424 Bytes
59bb219 |
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 |
"""Module containing the SimpleShareGPTPromptTokenizingStrategy class"""
from axolotl.prompt_tokenizers import ShareGPTPromptTokenizingStrategy
from axolotl.prompters import PromptStyle, ShareGPTPrompter
def load(tokenizer, cfg):
return SimpleShareGPTPromptTokenizingStrategy(
ShareGPTPrompter(PromptStyle.CHAT.value),
tokenizer,
cfg.train_on_inputs,
cfg.sequence_len,
)
def load_guanaco(tokenizer, cfg):
return GuanacoShareGPTPromptTokenizingStrategy(
ShareGPTPrompter(PromptStyle.CHAT.value),
tokenizer,
cfg.train_on_inputs,
cfg.sequence_len,
)
class SimpleShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
"""
basic sharegpt strategy to grab conversations from the sample row
"""
def get_conversation_thread(self, prompt):
return prompt["conversations"]
class GuanacoShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
"""
sharegpt strategy that remaps oasst data to sharegpt format
"""
def get_conversation_thread(self, prompt):
conversations = prompt["conversations"]
# remap role: prompter/assistant, text: ... => from: human/gpt, value: ...
role_map = {"prompter": "human", "assistant": "gpt"}
turns = [
{"from": role_map[t["role"]], "value": t["text"]} for t in conversations
]
return turns
|