From b83cc3f5b303ff30c52874b2d5864dc6385ebf9f Mon Sep 17 00:00:00 2001 From: Joan Fontanals Date: Sat, 11 May 2024 09:46:09 +0200 Subject: llama : add Jina Embeddings architecture (#6826) * feat: first things to do * feat: create tensors for Jina architecture * fix: use other tensors * feat: embedding gets results * fix: fix usage of ALIBI * fix: clean prints * fix: do some cleanup unused vars * fix: revert changes to Makefile and CMakeLists * fix: revert some changes * fix: fix small detail * fix: fix convert formatting * fix: fix linting and editor * feat: set proper vocab settings * fix: JinaBertForMaskedLM registration * feat: support q_normalization and k_normalization in Jina arch * feat: handle gpt2 tokenizer with Jina architecture * feat: example comments in embedding * feat: rename Jina Bert to Jina Bert V2 * fix: add some changes as per review * feat: proper KQ_pos for Jina embeddings * feat: add capacity to load models ES and DE for Spanish * llama : fix pre-tokenizers * ggml : full ALiBi support * ggml : update ggml_soft_max_ext() CUDA, SYCL * ggml : ggml_flash_attn_ext() support ALiBi (CPU) * ggml : ggml_flash_attn_ext() support ALiBi (Metal) * ggml : fix warning * ggml : ggml_flash_attn_ext() support ALiBi (CUDA) ggml-ci * minor : clean-up * embedding : add warning about missing SEP --------- Co-authored-by: Georgi Gerganov --- examples/embedding/embedding.cpp | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'examples') diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp index 6a93147d..c85a2da5 100644 --- a/examples/embedding/embedding.cpp +++ b/examples/embedding/embedding.cpp @@ -49,6 +49,12 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu } float * out = output + batch.seq_id[i][0] * n_embd; + //TODO: I would also add a parameter here to enable normalization or not. + /*fprintf(stdout, "unnormalized_embedding:"); + for (int hh = 0; hh < n_embd; hh++) { + fprintf(stdout, "%9.6f ", embd[hh]); + } + fprintf(stdout, "\n");*/ llama_embd_normalize(embd, out, n_embd); } } @@ -123,10 +129,12 @@ int main(int argc, char ** argv) { inputs.push_back(inp); } - // add SEP if not present + // check if the last token is SEP + // it should be automatically added by the tokenizer when 'tokenizer.ggml.add_eos_token' is set to 'true' for (auto & inp : inputs) { if (inp.empty() || inp.back() != llama_token_sep(model)) { - inp.push_back(llama_token_sep(model)); + fprintf(stderr, "%s: warning: last token in the prompt is not SEP\n", __func__); + fprintf(stderr, "%s: 'tokenizer.ggml.add_eos_token' should be set to 'true' in the GGUF header\n", __func__); } } -- cgit v1.2.3