Spaces:
Runtime error
Runtime error
File size: 3,369 Bytes
a577106 1262c59 357c504 09a60a0 357c504 09a60a0 1262c59 09a60a0 44732d2 09a60a0 44732d2 a577106 1cd49c7 a577106 fbef86d a577106 e61df2e fbef86d 4e2759c a577106 2f50482 fbef86d |
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 |
"""
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
import os
access_token = os.environ['HF_TOKEN']
config = PeftConfig.from_pretrained("HiTZ/Mistral-7B-MedExpQA-EN")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", token=access_token)
model = PeftModel.from_pretrained(model, "HiTZ/Mistral-7B-MedExpQA-EN", token=access_token)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", token=access_token)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
"""
from huggingface_hub import InferenceClient
import gradio as gr
import os
access_token = os.environ['HF_TOKEN']
import requests
API_URL = "https://api-inference.huggingface.co/models/HiTZ/Mistral-7B-MedExpQA-EN"
headers = {"Authorization": "Bearer "+access_token}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"inputs": "Can you please let us know more details about your ",
})
"""
client = InferenceClient("mistralai/Mistral-7B-v0.1",access_token)
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(prompt, history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
]
gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
additional_inputs=additional_inputs,
title="Mistral 7B fine-tuned on MedExpQA with max RAG 32"
).launch(show_api=False)
""" |