From cf658adc832badaaa2ca119fe86070e5a830f8f6 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 23 Aug 2023 23:08:04 +0300 Subject: 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 --- convert.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'convert.py') diff --git a/convert.py b/convert.py index a701ab41..8d34d5f2 100755 --- a/convert.py +++ b/convert.py @@ -733,7 +733,11 @@ class OutputFile: self.gguf = gguf.GGUFWriter(fname_out, gguf.MODEL_ARCH_NAMES[ARCH]) def add_meta_arch(self, params: Params) -> None: - self.gguf.add_name ("LLaMA") + ver = None + if (params.n_ctx == 4096): + ver = "v2" + + self.gguf.add_name ("LLaMA" if ver == None else "LLaMA " + ver) self.gguf.add_context_length (params.n_ctx) self.gguf.add_embedding_length (params.n_embd) self.gguf.add_block_count (params.n_layer) -- cgit v1.2.3