-
Notifications
You must be signed in to change notification settings - Fork 10.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
llm : support Adept Persimmon 8B (#3410)
* Produces garbage output * wip: correct tensors up to RoPE * correct tensors thru RoPE * Correct outputs through masked & softmax'd KQ * fp32 works * Rename adept->persimmon * Produces correct outputs * clean up convert scripts * remove printing logic from ggml.c * remove prints from llama.cpp & fix merge * trivial cleanups * Add offload funcs * update conversion script to directly take adept artifacts rather than .saftensors file * Fix norm eps bug * Support sqr and concat on metal, persimmon-8b-q4 runs correctly * Small changes from review * Formatting changes * Minor changes to conversion script * Remove old script * Fix editorconfig formatting * Fix build * add overlooked offload code ggml-ci
- Loading branch information
1 parent
3a716b4
commit 0e797c2
Showing
5 changed files
with
854 additions
and
76 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,130 @@ | ||
| 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: | ||
| sys.path.insert(1, str(Path(__file__).parent / 'gguf-py' / 'gguf')) | ||
| 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() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.