File size: 3,013 Bytes
eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa be5cf1f eee66aa | 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 | <!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>ClokCEM - Customer Executive Model</title>
<meta name="description" content="354M parameter model for enterprise customer support">
<script type="module" crossorigin src="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.js"></script>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.css" />
<style>
html, body {
margin: 0;
padding: 0;
height: 100%;
}
</style>
</head>
<body>
<gradio-lite>
<gradio-file name="app.py" entrypoint>
import gradio as gr
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
MODEL_REPO = "clokai/CLOK-CEM"
print("Loading model...")
from configuration_clokcem import ClokcemConfig
from modeling_clokcem import ClokcemForCausalLM
from transformers import AutoTokenizer
config = ClokcemConfig()
model = ClokcemForCausalLM(config)
weights_path = hf_hub_download(repo_id=MODEL_REPO, filename="model.safetensors")
sd = load_file(weights_path)
model.load_state_dict(sd, strict=False)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
print("Model ready!")
def chat(message, history, temperature, max_tokens):
device = next(model.parameters()).device
formatted = f"<|system|>You are a helpful customer care assistant.<|user|>{message}<|assistant|>"
inputs = tokenizer(formatted, return_tensors="pt").to(device)
generated = []
input_ids = inputs["input_ids"]
for _ in range(max_tokens):
with torch.no_grad():
logits = model(input_ids).logits
probs = torch.softmax(logits[:, -1, :] / temperature, dim=-1)
next_token = torch.multinomial(probs, num_samples=1)
if next_token.item() == tokenizer.eos_token_id:
break
generated.append(next_token.item())
input_ids = torch.cat([input_ids, next_token], dim=-1)
return tokenizer.decode(generated, skip_special_tokens=True)
demo = gr.ChatInterface(
fn=chat,
title="ClokCEM - Customer Executive Model",
description="354M parameter model for enterprise customer support",
additional_inputs=[
gr.Slider(0.1, 2.0, value=0.6, step=0.1, label="Temperature"),
gr.Slider(50, 500, value=200, step=50, label="Max Tokens"),
],
)
demo.launch()
</gradio-file>
<gradio-file name="configuration_clokcem.py" url="https://huggingface.co/clokai/CLOK-CEM/resolve/main/configuration_clokcem.py" />
<gradio-file name="modeling_clokcem.py" url="https://huggingface.co/clokai/CLOK-CEM/resolve/main/modeling_clokcem.py" />
<gradio-requirements>
torch
transformers
safetensors
huggingface_hub
gradio
</gradio-requirements>
</gradio-lite>
</body>
</html> |