Spaces:
Runtime error
Runtime error
File size: 3,747 Bytes
69698e1 d889050 ced196e 69698e1 d889050 69698e1 d889050 |
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 |
import gradio as gr
import os, gc
from datetime import datetime
from huggingface_hub import hf_hub_download
ctx_limit = 3500
title = "rwkv1b5-vitl336p14-577token_mix665k_rwkv"
os.environ["RWKV_JIT_ON"] = '1'
os.environ["RWKV_CUDA_ON"] = '0' # if '1' then use CUDA kernel for seq mode (much faster)
from rwkv.model import RWKV
model_path = hf_hub_download(repo_id="howard-hou/visualrwkv-5", filename=f"{title}.pth")
model = RWKV(model=model_path, strategy='cpu fp32')
from rwkv.utils import PIPELINE, PIPELINE_ARGS
pipeline = PIPELINE(model, "rwkv_vocab_v20230424")
##########################################################################
from modeling import VisualEncoder, EmbeddingMixer, VisualEncoderConfig
emb_mixer = EmbeddingMixer(model.w["emb.weight"], num_image_embeddings=4096)
config = VisualEncoderConfig(n_embd=model.args.n_embd,
vision_tower_name='openai/clip-vit-large-patch14-336',
grid_size=-1)
visual_encoder = VisualEncoder(config)
##########################################################################
def generate_prompt(instruction, input=""):
instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
if input:
return f"""Instruction: {instruction}
Input: {input}
Response:"""
else:
return f"""User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: {instruction}
Assistant:"""
def evaluate(
ctx,
token_count=200,
temperature=1.0,
top_p=0.7,
presencePenalty = 0.1,
countPenalty = 0.1,
):
args = PIPELINE_ARGS(temperature = max(0.2, float(temperature)), top_p = float(top_p),
alpha_frequency = countPenalty,
alpha_presence = presencePenalty,
token_ban = [], # ban the generation of some tokens
token_stop = [0]) # stop generation whenever you see any token here
ctx = ctx.strip()
all_tokens = []
out_last = 0
out_str = ''
occurrence = {}
state = None
for i in range(int(token_count)):
out, state = model.forward(pipeline.encode(ctx)[-ctx_limit:] if i == 0 else [token], state)
for n in occurrence:
out[n] -= (args.alpha_presence + occurrence[n] * args.alpha_frequency)
token = pipeline.sample_logits(out, temperature=args.temperature, top_p=args.top_p)
if token in args.token_stop:
break
all_tokens += [token]
for xxx in occurrence:
occurrence[xxx] *= 0.996
if token not in occurrence:
occurrence[token] = 1
else:
occurrence[token] += 1
tmp = pipeline.decode(all_tokens[out_last:])
if '\ufffd' not in tmp:
out_str += tmp
yield out_str.strip()
out_last = i + 1
del out
del state
gc.collect()
yield out_str.strip()
##########################################################################
examples = [
[
"./extreme_ironing.jpg",
"What is unusual about this image?",
],
[
"./waterview.jpg",
"What are the things I should be cautious about when I visit here?",
]
]
def test(image, question):
return question
demo = gr.Interface(fn=test,
inputs=["image", "text"],
outputs="text",
examples=examples,
title=title,
description="VisualRWKV-v5.0")
demo.queue(concurrency_count=1, max_size=10)
demo.launch(share=False) |