llm : add Falcon support (#2717)

* 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>

1 files changed, 0 insertions, 32 deletions

diff --git a/common/common.cpp b/common/common.cpp
index 88a962ae..53002ba3 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -744,35 +744,3 @@ std::string llama_token_to_str(const struct llama_context * ctx, llama_token tok
 
     return std::string(result.data(), result.size());
 }
-
-std::vector<llama_token> llama_tokenize_bpe(
-        struct llama_context * ctx,
-           const std::string & text,
-                        bool   add_bos) {
-    int n_tokens = text.length() + add_bos;
-    std::vector<llama_token> result(n_tokens);
-    n_tokens = llama_tokenize_bpe(ctx, text.c_str(), result.data(), result.size(), add_bos);
-    if (n_tokens < 0) {
-        result.resize(-n_tokens);
-        int check = llama_tokenize_bpe(ctx, text.c_str(), result.data(), result.size(), add_bos);
-        GGML_ASSERT(check == -n_tokens);
-    } else {
-        result.resize(n_tokens);
-    }
-    return result;
-}
-
-std::string llama_token_to_str_bpe(const struct llama_context * ctx, llama_token token) {
-    std::vector<char> result(8, 0);
-    const int n_tokens = llama_token_to_str_bpe(ctx, token, result.data(), result.size());
-    if (n_tokens < 0) {
-        result.resize(-n_tokens);
-        const int check = llama_token_to_str_bpe(ctx, token, result.data(), result.size());
-        GGML_ASSERT(check == -n_tokens);
-    } else {
-        result.resize(n_tokens);
-    }
-
-    return std::string(result.data(), result.size());
-}
-