Skip to content

Commit

Permalink
Merge branch 'concedo_experimentalMAIN'
Browse files Browse the repository at this point in the history
  • Loading branch information
@YellowRoseCx
YellowRoseCx committed Jul 26, 2023
2 parents cbdc1f3 + 94e0a06 commit f154685
Show file tree
Hide file tree
Showing 21 changed files with 1,642 additions and 654 deletions.
69 changes: 46 additions & 23 deletions convert.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -234,14 +234,21 @@ def load(model_plus: 'ModelPlus') -> 'Params':


class SentencePieceVocab:
def __init__(self, fname_tokenizer: Path, fname_added_tokens: Optional[Path]) -> None:
self.sentencepiece_tokenizer = SentencePieceProcessor(str(fname_tokenizer))
def __init__(self, fname_tokenizer: Path, fname_added_tokens: Optional[Path], vocabtype: Optional[str]) -> None:
self.vocabtype = vocabtype
if self.vocabtype == "bpe":
self.sentencepiece_tokenizer = json.loads(open(str(fname_tokenizer)).read())
else:
self.sentencepiece_tokenizer = SentencePieceProcessor(str(fname_tokenizer))
added_tokens: Dict[str, int]
if fname_added_tokens is not None:
added_tokens = json.load(open(fname_added_tokens))
else:
added_tokens = {}
vocab_size: int = self.sentencepiece_tokenizer.vocab_size()
if self.vocabtype == "bpe":
vocab_size: int = len(self.sentencepiece_tokenizer)
else:
vocab_size: int = self.sentencepiece_tokenizer.vocab_size()
expected_ids = list(range(vocab_size, vocab_size + len(added_tokens)))
actual_ids = sorted(added_tokens.values())
if expected_ids != actual_ids:
Expand All @@ -255,22 +262,32 @@ def __init__(self, fname_tokenizer: Path, fname_added_tokens: Optional[Path]) ->

def sentencepiece_tokens(self) -> Iterable[Tuple[bytes, float]]:
tokenizer = self.sentencepiece_tokenizer
for i in range(tokenizer.vocab_size()):
if self.vocabtype == "bpe":
from transformers.models.gpt2 import tokenization_gpt2
byte_encoder = tokenization_gpt2.bytes_to_unicode()
byte_decoder = {v: k for k, v in byte_encoder.items()}
for i, item in enumerate(tokenizer):
text: bytes
if tokenizer.is_unknown(i):
text = " \u2047 ".encode("utf-8")
elif tokenizer.is_control(i):
text = b""
elif tokenizer.is_byte(i):
piece = tokenizer.id_to_piece(i)
if len(piece) != 6:
raise Exception(f"Invalid token: {piece}")
byte_value = int(piece[3:-1], 16)
text = struct.pack("B", byte_value)
else:
text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
score: float = tokenizer.get_score(i)
text = b''.join([x.to_bytes(1, byteorder='big') for x in [byte_decoder[y] for y in item]])
score: float = -i
yield text, score
else:
for i in range(tokenizer.vocab_size()):
text: bytes
if tokenizer.is_unknown(i):
text = " \u2047 ".encode("utf-8")
elif tokenizer.is_control(i):
text = b""
elif tokenizer.is_byte(i):
piece = tokenizer.id_to_piece(i)
if len(piece) != 6:
raise Exception(f"Invalid token: {piece}")
byte_value = int(piece[3:-1], 16)
text = struct.pack("B", byte_value)
else:
text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
score: float = tokenizer.get_score(i)
yield text, score

def added_tokens(self) -> Iterable[Tuple[bytes, float]]:
for text in self.added_tokens_list:
Expand Down Expand Up @@ -1196,14 +1213,18 @@ def filter_and_sort_tensors(model: LazyModel) -> LazyModel:
return {name: model[name] for name in TENSORS_LIST if name in model}


def load_vocab(path: Path) -> SentencePieceVocab:
def load_vocab(path: Path, vocabtype: Optional[str]) -> SentencePieceVocab:
print(f"vocabtype: {vocabtype}")
# Be extra-friendly and accept either a file or a directory. Also, if it's
# a directory, it might be the model directory, and tokenizer.model might
# be in the parent of that.
if path.is_dir():
path2 = path / "tokenizer.model"
vocab_file = "tokenizer.model"
if vocabtype == 'bpe':
vocab_file = "vocab.json"
path2 = path / vocab_file
# Use `.parent` instead of /.. to handle the symlink case better.
path3 = path.parent / "tokenizer.model"
path3 = path.parent / vocab_file
if path2.exists():
path = path2
elif path3.exists():
Expand All @@ -1214,7 +1235,8 @@ def load_vocab(path: Path) -> SentencePieceVocab:
"if it's in another directory, pass the directory as --vocab-dir")
added_tokens_path = path.parent / "added_tokens.json"
print(f"Loading vocab file {path}")
return SentencePieceVocab(path, added_tokens_path if added_tokens_path.exists() else None)
return SentencePieceVocab(path, added_tokens_path if added_tokens_path.exists() else None,
vocabtype)


def default_outfile(model_paths: List[Path], file_type: GGMLFileType) -> Path:
Expand Down Expand Up @@ -1252,14 +1274,15 @@ def main(args_in: Optional[List[str]] = None) -> None:
parser.add_argument("--outfile", type=Path, help="path to write to; default: based on input")
parser.add_argument("model", type=Path,
help="directory containing model file, or model file itself (*.pth, *.pt, *.bin)")
parser.add_argument("--vocabtype", default='spm', choices=["spm", "bpe"], help="vocab format (default: spm)")
args = parser.parse_args(args_in)

vocab: Vocab
if args.dump_single:
model_plus = lazy_load_file(args.model)
do_dump_model(model_plus)
elif args.vocab_only:
vocab = load_vocab(args.vocab_dir or args.model)
vocab = load_vocab(args.vocab_dir or args.model, args.vocabtype)
assert args.outfile, "need --outfile if using --vocab-only"
outfile = args.outfile
OutputFile.write_vocab_only(outfile, vocab)
Expand All @@ -1273,7 +1296,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
vocab = model_plus.vocab
else:
vocab_dir = args.vocab_dir if args.vocab_dir else model_plus.paths[0].parent
vocab = load_vocab(vocab_dir)
vocab = load_vocab(vocab_dir, args.vocabtype)
params = Params.load(model_plus)
model = model_plus.model
model = do_necessary_conversions(model, params)
Expand Down
24 changes: 15 additions & 9 deletions examples/baby-llama/baby-llama.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,12 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif

#ifdef LLAMA_DEFAULT_RMS_EPS
static const float rms_norm_eps = LLAMA_DEFAULT_RMS_EPS;
#else
static const float rms_norm_eps = 5e-6f;
#endif

float frand() {
return (float)rand()/(float)RAND_MAX;
}
Expand Down Expand Up @@ -562,7 +568,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);

// cur = attention_norm*cur
cur = ggml_mul(ctx0,
Expand Down Expand Up @@ -685,7 +691,7 @@ struct ggml_tensor * forward(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);

// cur = ffn_norm*cur
// cur shape [n_embd,N,1,1]
Expand Down Expand Up @@ -729,7 +735,7 @@ struct ggml_tensor * forward(
{

// inpL shape [n_embd,N,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);

// inpL = norm*inpL
// inpL shape [n_embd,N,1,1]
Expand Down Expand Up @@ -817,7 +823,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);

// cur = attention_norm*cur
Expand Down Expand Up @@ -981,7 +987,7 @@ struct ggml_tensor * forward_batch(
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
assert_shape_2d(cur, n_embd, N*n_batch);

// cur = ffn_norm*cur
Expand Down Expand Up @@ -1034,7 +1040,7 @@ struct ggml_tensor * forward_batch(
{

// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
assert_shape_2d(inpL, n_embd, N*n_batch);

// inpL = norm*inpL
Expand Down Expand Up @@ -1104,7 +1110,7 @@ struct ggml_tensor * forward_lora(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpL);
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);

// cur = attention_norm*cur
cur = ggml_mul(ctx0,
Expand Down Expand Up @@ -1251,7 +1257,7 @@ struct ggml_tensor * forward_lora(
// norm
{
// cur shape [n_embd,N,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);

// cur = ffn_norm*cur
// cur shape [n_embd,N,1,1]
Expand Down Expand Up @@ -1295,7 +1301,7 @@ struct ggml_tensor * forward_lora(
{

// inpL shape [n_embd,N,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);

// inpL = norm*inpL
// inpL shape [n_embd,N,1,1]
Expand Down
11 changes: 11 additions & 0 deletions examples/common.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -177,6 +177,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
break;
}
params.n_gqa = std::stoi(argv[i]);
} else if (arg == "-eps" || arg == "--rms-norm-eps") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.rms_norm_eps = std::stof(argv[i]);
} else if (arg == "--rope-freq-base") {
if (++i >= argc) {
invalid_param = true;
Expand Down Expand Up @@ -426,6 +432,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
exit(0);
} else if (arg == "--random-prompt") {
params.random_prompt = true;
} else if (arg == "--in-prefix-bos") {
params.input_prefix_bos = true;
} else if (arg == "--in-prefix") {
if (++i >= argc) {
invalid_param = true;
Expand Down Expand Up @@ -511,6 +519,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stdout, " not supported with --interactive or other interactive options\n");
fprintf(stdout, " --prompt-cache-ro if specified, uses the prompt cache but does not update it.\n");
fprintf(stdout, " --random-prompt start with a randomized prompt.\n");
fprintf(stdout, " --in-prefix-bos prefix BOS to user inputs, preceding the `--in-prefix` string\n");
fprintf(stdout, " --in-prefix STRING string to prefix user inputs with (default: empty)\n");
fprintf(stdout, " --in-suffix STRING string to suffix after user inputs with (default: empty)\n");
fprintf(stdout, " -f FNAME, --file FNAME\n");
Expand All @@ -519,6 +528,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stdout, " -eps N, --rms-norm-eps N rms norm eps (TEMP!!! use 1e-5 for LLaMAv2) (default: %.1e)\n", params.rms_norm_eps);
fprintf(stdout, " --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
fprintf(stdout, " --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);
fprintf(stdout, " --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z);
Expand Down Expand Up @@ -615,6 +625,7 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
lparams.n_ctx = params.n_ctx;
lparams.n_batch = params.n_batch;
lparams.n_gqa = params.n_gqa;
lparams.rms_norm_eps = params.rms_norm_eps;
lparams.n_gpu_layers = params.n_gpu_layers;
lparams.main_gpu = params.main_gpu;
lparams.tensor_split = params.tensor_split;
Expand Down
24 changes: 13 additions & 11 deletions examples/common.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,18 +22,19 @@
int32_t get_num_physical_cores();

struct gpt_params {
uint32_t seed = -1; // RNG seed
uint32_t seed = -1; // RNG seed
int32_t n_threads = get_num_physical_cores();
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_gqa = 1; // grouped-query attention factor (TODO: move to hparams)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_gpu_layers = 0; // number of layers to store in VRAM
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_gqa = 1; // grouped-query attention factor (TODO: move to hparams)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_gpu_layers = 0; // number of layers to store in VRAM
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs
int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens.
float rms_norm_eps = LLAMA_DEFAULT_RMS_EPS; // rms norm epsilon
float rope_freq_base = 10000.0f; // RoPE base frequency
float rope_freq_scale = 1.0f; // RoPE frequency scaling factor

Expand Down Expand Up @@ -81,6 +82,7 @@ struct gpt_params {
bool interactive_first = false; // wait for user input immediately
bool multiline_input = false; // reverse the usage of `\`

bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool instruct = false; // instruction mode (used for Alpaca models)
bool penalize_nl = true; // consider newlines as a repeatable token
bool perplexity = false; // compute perplexity over the prompt
Expand Down
47 changes: 30 additions & 17 deletions examples/main/main.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,10 @@ int main(int argc, char ** argv) {
}
}

if (params.input_prefix_bos) {
fprintf(stderr, "Input prefix with BOS\n");
}

if (!params.input_prefix.empty()) {
fprintf(stderr, "Input prefix: '%s'\n", params.input_prefix.c_str());
}
Expand Down Expand Up @@ -633,16 +637,6 @@ int main(int argc, char ** argv) {
last_n_tokens.push_back(id);
}

// replace end of text token with newline token when in interactive mode
if (id == llama_token_eos() && params.interactive && !params.instruct) {
id = llama_token_newline.front();
if (params.antiprompt.size() != 0) {
// tokenize and inject first reverse prompt
const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
}
}

// add it to the context
embd.push_back(id);

Expand Down Expand Up @@ -708,11 +702,34 @@ int main(int argc, char ** argv) {
}
}

// deal with end of text token in interactive mode
if (last_n_tokens.back() == llama_token_eos()) {
if (params.interactive) {
if (params.antiprompt.size() != 0) {
// tokenize and inject first reverse prompt
const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
is_antiprompt = true;
}

is_interacting = true;
printf("\n");
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
fflush(stdout);
} else if (params.instruct) {
is_interacting = true;
}
}

if (n_past > 0 && is_interacting) {
if (params.instruct) {
printf("\n> ");
}

if (params.input_prefix_bos) {
embd_inp.push_back(llama_token_bos());
}

std::string buffer;
if (!params.input_prefix.empty()) {
buffer += params.input_prefix;
Expand Down Expand Up @@ -776,13 +793,9 @@ int main(int argc, char ** argv) {
}

// end of text token
if (!embd.empty() && embd.back() == llama_token_eos()) {
if (params.instruct) {
is_interacting = true;
} else {
fprintf(stderr, " [end of text]\n");
break;
}
if (!embd.empty() && embd.back() == llama_token_eos() && !(params.instruct || params.interactive)) {
fprintf(stderr, " [end of text]\n");
break;
}

// In interactive mode, respect the maximum number of tokens and drop back to user input when reached.
Expand Down
Loading

0 comments on commit f154685

Please sign in to comment.