From 56e8e63cb0a23721474da8d29cc3787f65928ff1 Mon Sep 17 00:00:00 2001 From: bryan Date: Tue, 2 Apr 2024 15:58:17 +0800 Subject: [PATCH] add sealion support --- convert-hf-to-gguf.py | 15 ++++++++++++- llama.cpp | 51 ++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 62 insertions(+), 4 deletions(-) diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py index 18337839a..a4e8ea2a5 100755 --- a/convert-hf-to-gguf.py +++ b/convert-hf-to-gguf.py @@ -511,6 +511,16 @@ class BloomModel(Model): class MPTModel(Model): model_arch = gguf.MODEL_ARCH.MPT + def set_vocab(self): + try: + self._set_vocab_gpt2() + except AttributeError as e: + self._set_vocab_sentencepiece() + self.gguf_writer.add_add_bos_token(False) + self.gguf_writer.add_pad_token_id(3) + self.gguf_writer.add_eos_token_id(1) + self.gguf_writer.add_unk_token_id(0) + def set_gguf_parameters(self): block_count = self.hparams["n_layers"] self.gguf_writer.add_name(self.dir_model.name) @@ -524,7 +534,10 @@ class MPTModel(Model): self.gguf_writer.add_layer_norm_eps(1e-5) if self.hparams["attn_config"]["clip_qkv"] is not None: self.gguf_writer.add_clamp_kqv(self.hparams["attn_config"]["clip_qkv"]) - self.gguf_writer.add_max_alibi_bias(self.hparams["attn_config"]["alibi_bias_max"]) + if self.hparams["attn_config"]["alibi"]: + self.gguf_writer.add_max_alibi_bias(self.hparams["attn_config"]["alibi_bias_max"]) + else: + self.gguf_writer.add_max_alibi_bias(0.0) def write_tensors(self): block_count = self.hparams.get("n_layers", self.hparams.get("num_hidden_layers")) diff --git a/llama.cpp b/llama.cpp index 21e7a067a..cc8b2ac40 100644 --- a/llama.cpp +++ b/llama.cpp @@ -585,6 +585,9 @@ static const std::map> LLM_TENSOR_NA { LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" }, { LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" }, { LLM_TENSOR_FFN_ACT, "blk.%d.ffn.act" }, + { LLM_TENSOR_POS_EMBD, "position_embd" }, + { LLM_TENSOR_ATTN_Q_NORM, "blk.%d.attn_q_norm"}, + { LLM_TENSOR_ATTN_K_NORM, "blk.%d.attn_k_norm"}, }, }, { @@ -4743,6 +4746,7 @@ static bool llm_load_tensors( case LLM_ARCH_MPT: { model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); + model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); // output { @@ -4781,6 +4785,12 @@ static bool llm_load_tensors( layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, false); + layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd}); + layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias", i), {n_embd}); + + layer.attn_k_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd}); + layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {n_embd}); + // AWQ ScaleActivation layer layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); } @@ -7595,6 +7605,7 @@ struct llm_build_context { GGML_ASSERT(n_embd_head == hparams.n_embd_head_k); struct ggml_tensor * cur; + struct ggml_tensor * pos; struct ggml_tensor * inpL; inpL = llm_build_inp_embd(ctx0, lctx, hparams, batch, model.tok_embd, cb); @@ -7605,6 +7616,16 @@ struct llm_build_context { // positions of the tokens in the KV cache struct ggml_tensor * KQ_pos = build_inp_KQ_pos(); + if (model.pos_embd){ + // inp_pos - contains the positions + struct ggml_tensor * inp_pos = build_inp_pos(); + pos = ggml_get_rows(ctx0, model.pos_embd, inp_pos); + cb(pos, "pos_embd", -1); + + inpL = ggml_add(ctx0, inpL, pos); + cb(inpL, "inpL", -1); + } + for (int il = 0; il < n_layer; ++il) { struct ggml_tensor * attn_norm; @@ -7639,11 +7660,35 @@ struct llm_build_context { cb(Kcur, "Kcur", il); cb(Vcur, "Vcur", il); - Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); + // Q/K Layernorm + if (model.layers[il].attn_q_norm){ + Qcur = llm_build_norm(ctx0, Qcur, hparams, + model.layers[il].attn_q_norm, + model.layers[il].attn_q_norm_b, + LLM_NORM, cb, il); + cb(Qcur, "Qcur", il); - cur = llm_build_kv(ctx0, model, hparams, kv_self, gf, + Kcur = llm_build_norm(ctx0, Kcur, hparams, + model.layers[il].attn_k_norm, + model.layers[il].attn_k_norm_b, + LLM_NORM, cb, il); + cb(Kcur, "Kcur", il); + + Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); + Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens); + + cur = llm_build_kv(ctx0, model, hparams, kv_self, gf, model.layers[il].wo, model.layers[il].bo, - Kcur, Vcur, Qcur, KQ_mask, KQ_pos, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il); + Kcur, Vcur, Qcur, KQ_mask, nullptr, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il); + + } + + else{ + Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); + cur = llm_build_kv(ctx0, model, hparams, kv_self, gf, + model.layers[il].wo, model.layers[il].bo, + Kcur, Vcur, Qcur, KQ_mask, KQ_pos, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il); + } } if (il == n_layer - 1) {