File size: 7,827 Bytes
0c6d13f | 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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
from langchain import HuggingFacePipeline
from transformers import pipeline
import transformers
import torch
from transformers import T5Tokenizer
from transformers import T5ForConditionalGeneration
def zepyhr_model(model_info,quanization):
path=f"models/{model_info}"
tokenizer = AutoTokenizer.from_pretrained(path,
use_auth_token=True,)
if quanization=="8":
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_8bit=True,
)
else:
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_4bit=True
)
pipe = pipeline("text-generation",
model=model,
tokenizer= tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
max_new_tokens = 512,
do_sample=True,
top_k=30,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipe, model_kwargs = {'temperature':0})
return llm
def llama_model(model_info,quanization):
path=f"models/{model_info}"
tokenizer = AutoTokenizer.from_pretrained(path,
use_auth_token=True,)
if quanization=="8":
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_8bit=True,
)
else:
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_4bit=True
)
pipe = pipeline("text-generation",
model=model,
tokenizer= tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
max_new_tokens = 512,
do_sample=True,
top_k=30,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipe, model_kwargs = {'temperature':0})
return llm
def mistral_model(model_info,quanization):
path=f"models/{model_info}"
tokenizer = AutoTokenizer.from_pretrained(path,
use_auth_token=True,)
if quanization=="8":
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_8bit=True,
)
else:
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_4bit=True
)
pipe = pipeline("text-generation",
model=model,
tokenizer= tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
max_new_tokens = 512,
do_sample=True,
top_k=30,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipe, model_kwargs = {'temperature':0})
return llm
def phi_model(model_info,quanization):
path=f"models/{model_info}"
tokenizer = AutoTokenizer.from_pretrained(path,
use_auth_token=True,)
if quanization=="8":
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_8bit=True,
trust_remote_code=True
)
else:
model = AutoModelForCausalLM.from_pretrained(path,
device_map='auto',
torch_dtype=torch.float16,
use_auth_token=True,
load_in_4bit=True,
trust_remote_code=True
)
pipe = pipeline("text-generation",
model=model,
tokenizer= tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
max_new_tokens = 512,
do_sample=True,
top_k=30,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipe, model_kwargs = {'temperature':0})
return llm
def flant5_model(model_info):
path=f"models/{model_info}"
model = T5ForConditionalGeneration.from_pretrained(path)
MODEL_NAME = "google/flan-t5-base"
tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME)
pipe = pipeline("text-generation",
model=model,
tokenizer= tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
max_new_tokens = 512,
do_sample=True,
top_k=30,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipe, model_kwargs = {'temperature':0})
return tokenizer,model,llm
# model = AutoModelForCausalLM.from_pretrained(
# path,
# # quantization_config=bnb_config,
# device_map="auto",
# trust_remote_code=True,
# attn_implementation="flash_attention_2",
# torch_dtype=torch.bfloat16,
# ) |