vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llm : add Falcon support (#2717)

Browse source 
* llama : refactor GGUF constants into static maps

* llama : check if model architecture is known

* llama : refactor llama_model_load_internal()

* gguf : add KV constant maps

* llm : read arch-specific KVs

* convert : add dummy scores + types

* falcon : load tensor data (CPU only)

* llama : fix loading progress bar

* llama : add arch member to llama_model

* falcon : CPU inference working

* falcon : support non-40B models

* falcon : minor

* llama : minor updates

ggml-ci

* convert-falcon-hf-to-gguf.py : fix special token mapping

* llama.cpp : llama default UNK token = id 0

* llama.cpp : fix bpe tokenizer

* llama.cpp : fix the fix of bpe tokenizer

* ggml : pass eps to ggml_norm

* metal : implement RoPE (mode = 2) + avoid ggml_repeat

* ggml : ggml_repeat always creates new tensor

* falcon : copy-paste self-attention from LLaMA

* metal : print extra compute pipeline info

* falcon : minor changes (still chasing the Metal problem)

* llama.cpp : fix linefeed token

* metal : fix GELU kernel numerical stability by using precise::tanh

* metal : temporary workaround for the concurrency optimization bug

* falcon : add CUDA offloading (#2739)

* llama : better model naming and size reporting

* llama : prep new tokenizer support

* llama : advanced BPE tokenizer based on ggllm.cpp imlpementation

* llama : remove oboslete comment

ggml-ci

* common : remove obsolete BPE API + disable test-tokenizer-1

* llama : revert BPE special-case in llama_byte_to_token()

* cuda : add TODOs for RoPE NeoX implementation

* llama : default special tokens based on vocab type

* perplexity : add log for start of tokenization

---------

Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2023-08-23 23:08:04 +03:00 • committed by GitHub
parent a192860cfe
commit cf658adc83
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
18 changed files with 1596 additions and 668 deletions
Download patch file Download diff file Expand all files Collapse all files

16
tests/test-tokenizer-1.cpp
View file

@ -67,11 +67,13 @@ int main(int argc, char **argv) {
}
}
GGML_ASSERT(llama_vocab_type(ctx) == LLAMA_VOCAB_TYPE_BPE);
const int n_vocab = llama_n_vocab(ctx);
for (int i = 0; i < n_vocab; ++i) {
std::string forward = llama_token_to_str_bpe(ctx, i);
std::vector<llama_token> tokens = llama_tokenize_bpe(ctx, forward, false);
std::string forward = llama_token_to_str(ctx, i);
std::vector<llama_token> tokens = llama_tokenize(ctx, forward, false);
if (tokens.size() == 1) {
if (i != tokens[0]) {
std::string backward = llama_token_to_str(ctx, tokens[0]);
@ -79,16 +81,6 @@ int main(int argc, char **argv) {
__func__, i, llama_token_to_str(ctx, i).c_str(), tokens[0], backward.c_str());
return 2;
}
} else {
llama_token_type type = llama_token_get_type(ctx, i);
if (type == LLAMA_TOKEN_TYPE_UNKNOWN || type == LLAMA_TOKEN_TYPE_CONTROL || type == LLAMA_TOKEN_TYPE_BYTE) {
fprintf(stderr, "%s : info: token %d is string %s and bpe returns tokens %s\n",
__func__, i, llama_token_to_str(ctx, i).c_str(), unescape_whitespace(ctx, tokens).c_str());
} else {
fprintf(stderr, "%s : error: token %d is string %s but bpe returns tokens %s\n",
__func__, i, llama_token_to_str(ctx, i).c_str(), unescape_whitespace(ctx, tokens).c_str());
return 2;
}
}
}