abetlen

from __future__ import annotations

import os
import ctypes
import contextlib

import numpy as np

import llama_cpp
import llama_cpp.llava_cpp as llava_cpp

abetlen

import os
import json
import typing
import pathlib
import argparse

import numpy as np
import numpy.typing as npt
import gguf
from gguf import KEY_ATTENTION_HEAD_COUNT, KEY_ATTENTION_LAYERNORM_EPS, KEY_BLOCK_COUNT, KEY_EMBEDDING_LENGTH, KEY_FEED_FORWARD_LENGTH, GGUFWriter, TokenType, SpecialVocab

abetlen

"""Copyright (c) 2024 Andrei Betlen

Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE

abetlen

from llama_cpp import Llama
from llama_cpp.llama_chat_format import Llava15ChatHandler
chat_handler = Llava15ChatHandler(clip_model_path="llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf")
llm = Llama(
  model_path="llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q4_K_M.gguf",
  chat_handler=chat_handler,
  n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
  logits_all=True,# needed to make llava work
  n_gpu_layers=-1
)