Spaces:
Running
Running
File size: 1,019 Bytes
bca5262 |
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 |
import os
import gradio as gr
import copy
import llama_cpp
from llama_cpp import Llama
import random
from huggingface_hub import hf_hub_download
import time
def load_model(path, n_ctx, n_gpu_layers, n_threads, verbose, f16_kv, logits_all, vocab_only, use_mmap, use_mlock, n_batch, last_n_tokens_size, low_vram, rope_freq_base, rope_freq_scale):
try:
dir = os.getcwd()
global llm
llm = Llama(
model_path=f"{dir}\models\{path}",
n_ctx=n_ctx,
n_gpu_layers=n_gpu_layers,
n_threads=n_threads,
verbose=verbose,
f16_kv=f16_kv,
logits_all=logits_all,
vocab_only=vocab_only,
use_mmap=use_mmap,
use_mlock=use_mlock,
n_batch=n_batch,
last_n_tokens_size=last_n_tokens_size,
low_vram=low_vram,
rope_freq_base=rope_freq_base,
rope_freq_scale=rope_freq_scale,
)
return path
except:
return "" |