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 --- ggml-alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'ggml-alloc.c') diff --git a/ggml-alloc.c b/ggml-alloc.c index f06f9a3c..547ec039 100644 --- a/ggml-alloc.c +++ b/ggml-alloc.c @@ -238,7 +238,7 @@ static void ggml_allocator_free_tensor(struct ggml_allocr * alloc, struct ggml_t alloc->n_free_blocks++; } -void ggml_allocr_set_parse_seq(struct ggml_allocr * alloc, int * list, int n) { +void ggml_allocr_set_parse_seq(struct ggml_allocr * alloc, const int * list, int n) { int pos = 0; for (int i = 0; i < n; i++) { if (list[i] != -1) { @@ -547,7 +547,7 @@ static size_t ggml_allocator_alloc_graph_tensors_n( struct ggml_tensor * view_src = get_view_source(parent); struct hash_node * view_src_hn = hash_get(ht, view_src); view_src_hn->n_views -= 1; - AT_PRINTF("view_src %s: %d children, %d views\n", view_src->name, view_src->n_children, view_src->n_views); + AT_PRINTF("view_src %s\n", view_src->name); if (view_src_hn->n_views == 0 && view_src_hn->n_children == 0 && view_src->data != node->data) { ggml_allocator_free_tensor(alloc, view_src); } -- cgit v1.2.3