llama.cpp/convert-persimmon-to-gguf.py

134 lines
4.7 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
import torch
import os
from pprint import pprint
import sys
import argparse
from pathlib import Path
from sentencepiece import SentencePieceProcessor
if 'NO_LOCAL_GGUF' not in os.environ:
gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) * gguf-py: Refactor and add file reading support * Replay changes from #3871 Credit to @cebtenzzre for that pull * Various type annotation fixes. * sort imports with isort (again) * Fix missing return statement in add_tensor * style cleanup with flake8 * fix NamedTuple and Enum usage * Fix an issue with state init in GGUFReader Move examples to an examples/ directory Clean up examples Add an example of modifying keys in a GGUF file Update documentation with info on examples Try to support people importing gguf/gguf.py directly * Damagage is not a word. * Clean up gguf-py/examples/modify_gguf.py whitespace Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update gguf-py/examples/modify_gguf.py formatting Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update gguf-py/gguf/gguf_reader.py type hint Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Make examples executable, formatting changes * Add more information to GGUFReader and examples comments * Include a gguf Python package version bump * Add convert-gguf-endian.py script * cleanup * gguf-py : bump minor version * Reorganize scripts * Make GGUFReader endian detection less arbitrary * Add JSON dumping support to gguf-dump.py Which I kind of regret now * A few for gguf-dump.py cleanups * Murder accidental tuple in gguf-py/scripts/gguf-dump.py Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * cleanup * constants : remove unneeded type annotations * fix python 3.8 compat * Set up gguf- scripts in pyproject.toml * And include scripts/__init__.py, derp * convert.py: We can't currently support Q8_0 on big endian. * gguf-py: SpecialVocab: Always try available sources for special token ids gguf-py: SpecialVocab: Try to load merges from merges.txt if not in tokenizer.json gguf-py: SpecialVocab: Add 'add_bos_token' type bools to GGUF metadata u * cleanup * Promote add_X_token to GGUF metadata for BOS and EOS --------- Co-authored-by: Jared Van Bortel <jared@nomic.ai> Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2023-11-11 06:04:50 +01:00
sys.path.insert(1, str(Path(__file__).parent / 'gguf-py'))
import gguf
def _flatten_dict(dct, tensors, prefix=None):
assert isinstance(dct, dict)
for key in dct.keys():
new_prefix = prefix + '.' + key if prefix is not None else key
if isinstance(dct[key], torch.Tensor):
tensors[new_prefix] = dct[key]
elif isinstance(dct[key], dict):
_flatten_dict(dct[key], tensors, new_prefix)
else:
raise ValueError(type(dct[key]))
return None
def _get_sentencepiece_tokenizer_info(dir_model: Path):
tokenizer_path = dir_model / 'adept_vocab.model'
print('gguf: getting sentencepiece tokenizer from', tokenizer_path)
tokenizer = SentencePieceProcessor(str(tokenizer_path))
print('gguf: adding tokens')
tokens: list[bytes] = []
scores: list[float] = []
toktypes: list[int] = []
for i in range(tokenizer.vocab_size()):
text: bytes
score: float
piece = tokenizer.id_to_piece(i)
text = piece.encode("utf-8")
score = tokenizer.get_score(i)
toktype = 1
if tokenizer.is_unknown(i):
toktype = 2
if tokenizer.is_control(i):
toktype = 3
if tokenizer.is_unused(i):
toktype = 5
if tokenizer.is_byte(i):
toktype = 6
tokens.append(text)
scores.append(score)
toktypes.append(toktype)
pass
return tokens, scores, toktypes
def main():
parser = argparse.ArgumentParser(description="Convert a Persimmon model from Adept (e.g. Persimmon 8b chat) to a GGML compatible file")
parser.add_argument("--outfile", type=Path, help="path to write to; default: based on input")
parser.add_argument("--ckpt-path", type=Path, help="path to persimmon checkpoint .pt file")
parser.add_argument("--model-dir", type=Path, help="directory containing model e.g. 8b_chat_model_release")
parser.add_argument("--adept-inference-dir", type=str, help="path to adept-inference code directory")
args = parser.parse_args()
sys.path.append(str(args.adept_inference_dir))
persimmon_model = torch.load(args.ckpt_path)
hparams = persimmon_model['args']
pprint(hparams)
tensors = {}
_flatten_dict(persimmon_model['model'], tensors, None)
arch = gguf.MODEL_ARCH.PERSIMMON
gguf_writer = gguf.GGUFWriter(args.outfile, gguf.MODEL_ARCH_NAMES[arch])
block_count = hparams.num_layers
head_count = hparams.num_attention_heads
head_count_kv = head_count
ctx_length = hparams.seq_length
hidden_size = hparams.hidden_size
gguf_writer.add_name('persimmon-8b-chat')
gguf_writer.add_context_length(ctx_length)
gguf_writer.add_embedding_length(hidden_size)
gguf_writer.add_block_count(block_count)
gguf_writer.add_feed_forward_length(hparams.ffn_hidden_size)
gguf_writer.add_rope_dimension_count(hidden_size // head_count)
gguf_writer.add_head_count(head_count)
gguf_writer.add_head_count_kv(head_count_kv)
gguf_writer.add_rope_freq_base(hparams.rotary_emb_base)
gguf_writer.add_layer_norm_eps(hparams.layernorm_epsilon)
tokens, scores, toktypes = _get_sentencepiece_tokenizer_info(args.model_dir)
gguf_writer.add_tokenizer_model('llama')
gguf_writer.add_token_list(tokens)
gguf_writer.add_token_scores(scores)
gguf_writer.add_token_types(toktypes)
gguf_writer.add_bos_token_id(71013)
gguf_writer.add_eos_token_id(71013)
tensor_map = gguf.get_tensor_name_map(arch, block_count)
print(tensor_map)
for name in tensors.keys():
data = tensors[name]
if name.endswith(".self_attention.rotary_emb.inv_freq"):
continue
old_dtype = data.dtype
# TODO: FP16 conversion produces garbage outputs. (Q8_0 does not, so..?)
data = data.to(torch.float32).squeeze().numpy()
new_name = tensor_map.get_name(name, try_suffixes = (".weight", ".bias"))
if new_name is None:
print("Can not map tensor '" + name + "'")
sys.exit()
n_dims = len(data.shape)
print(new_name + ", n_dims = " + str(n_dims) + ", " + str(old_dtype) + " --> " + str(data.dtype))
gguf_writer.add_tensor(new_name, data)
print("gguf: write header")
gguf_writer.write_header_to_file()
print("gguf: write metadata")
gguf_writer.write_kv_data_to_file()
print("gguf: write tensors")
gguf_writer.write_tensors_to_file()
gguf_writer.close()
print(f"gguf: model successfully exported to '{args.outfile}'")
print("")
if __name__ == '__main__':
main()