Spaces:
Sleeping
Sleeping
File size: 3,312 Bytes
b538faf 2ef9ba6 b232ee4 2ef9ba6 78b95a0 b232ee4 2ef9ba6 0f72328 2ef9ba6 b232ee4 2ef9ba6 0f72328 2ef9ba6 fe0550e b232ee4 5d3a921 fe0550e 2ef9ba6 fe0550e 2ef9ba6 78b95a0 b232ee4 b538faf 9f4db35 b538faf fd2ed4e b538faf |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
from transformers import AutoTokenizer, AutoConfig, AutoModelForCausalLM, TextStreamer
from peft import PeftConfig, PeftModel
config = PeftConfig.from_pretrained("jonathanjordan21/mos-mamba-6x130m-trainer")
tokenizer = AutoTokenizer.from_pretrained("jonathanjordan21/mos-mamba-6x130m-trainer", trust_remote_code=True)
# streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
model = AutoModelForCausalLM.from_pretrained(
"jonathanjordan21/mos-mamba-6x130m-trainer",
eos_token_id=tokenizer.eos_token_id,
trust_remote_code=True
)
model = PeftModel.from_pretrained(model, "jonathanjordan21/mos-mamba-6x130m-trainer",)#, adapter_name="norobots")
model = model.merge_and_unload()
print(model.config.eos_token_id)
def invoke(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
tokens = tokenizer.apply_chat_template(messages, return_tensors='pt', add_generation_prompt=True)
response = model.generate(
tokens,
eos_token_id=model.config.eos_token_id,
max_new_tokens=max_tokens,
# temperature=temperature
)
print(response)
res = tokenizer.batch_decode(response)
print(res)
return res[0]
# yield res
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
invoke,
additional_inputs=[
gr.Textbox(value="You are a helpful assistant.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch() |