File size: 1,384 Bytes
bff1360 |
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 |
import gradio as gr
import ctransformers
class Z(object):
def __init__(self):
self.llm = None
def init(self):
pass
def greet(self, txt0, paramTemp):
prompt0 = txt0
# for Wizard-Vicuna-13B
prompt00 = f'''USER: {prompt0}
ASSISTANT:'''
prompt00 = f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt0}
### Response:'''
response0 = llm(prompt00, max_new_tokens=198, temperature=paramTemp) # 0.5, 0.3
return f'{response0}'
from ctransformers import AutoModelForCausalLM
# wizzard vicuna
# see https://github.com/melodysdreamj/WizardVicunaLM
llm = AutoModelForCausalLM.from_pretrained('TheBloke/Wizard-Vicuna-13B-Uncensored-GGML', model_file='Wizard-Vicuna-13B-Uncensored.ggmlv3.q4_0.bin', model_type='llama')
#llm = AutoModelForCausalLM.from_pretrained('mverrilli/dolly-v2-12b-ggml', model_file='ggml-model-q5_0.bin', model_type='dolly-v2')
#llm = AutoModelForCausalLM.from_pretrained('mverrilli/dolly-v2-7b-ggml', model_file='ggml-model-q5_0.bin', model_type='dolly-v2')
z = Z()
z.llm = llm
z.init()
def greet(prompt, temperature):
global z
return z.greet(prompt, temperature)
iface = gr.Interface(fn=greet, inputs=["text", gr.Slider(0.0, 1.0, value=0.41)], outputs="text")
iface.launch() |