126 lines
4.2 KiB
C++
126 lines
4.2 KiB
C++
#include "models.h"
|
|
|
|
|
|
|
|
llm_build_apertus::llm_build_apertus(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
|
|
const int64_t n_embd_head = hparams.n_embd_head_v;
|
|
|
|
GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
|
|
GGML_ASSERT(n_embd_head == hparams.n_rot);
|
|
|
|
ggml_tensor * cur;
|
|
ggml_tensor * inpL;
|
|
|
|
inpL = build_inp_embd(model.tok_embd);
|
|
|
|
ggml_tensor * inp_pos = build_inp_pos();
|
|
auto * inp_attn = build_attn_inp_kv();
|
|
|
|
const float kq_scale =
|
|
hparams.f_attention_scale == 0.0f ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;
|
|
|
|
ggml_tensor * inp_out_ids = build_inp_out_ids();
|
|
|
|
for (int il = 0; il < n_layer; ++il) {
|
|
ggml_tensor * inpSA = inpL;
|
|
|
|
cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);
|
|
cb(cur, "attn_norm", il);
|
|
|
|
// self-attention
|
|
{
|
|
ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);
|
|
|
|
// compute Q and K and RoPE them
|
|
ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
|
|
cb(Qcur, "Qcur", il);
|
|
|
|
ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
|
|
cb(Kcur, "Kcur", il);
|
|
|
|
ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
|
|
cb(Vcur, "Vcur", il);
|
|
|
|
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
|
|
Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM_RMS, il);
|
|
cb(Qcur, "Qcur_normed", il);
|
|
|
|
Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
|
|
Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM_RMS, il);
|
|
cb(Kcur, "Kcur_normed", il);
|
|
|
|
Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
|
|
|
|
Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, rope_factors, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
|
|
ext_factor, attn_factor, beta_fast, beta_slow);
|
|
|
|
Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, rope_factors, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
|
|
ext_factor, attn_factor, beta_fast, beta_slow);
|
|
|
|
cb(Qcur, "Qcur_pos", il);
|
|
cb(Kcur, "Kcur_pos", il);
|
|
cb(Vcur, "Vcur_pos", il);
|
|
|
|
cur = build_attn(inp_attn,
|
|
model.layers[il].wo, model.layers[il].bo,
|
|
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
|
|
cb(cur, "attn_out", il);
|
|
}
|
|
|
|
if (il == n_layer - 1 && inp_out_ids) {
|
|
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
|
|
inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
|
|
}
|
|
|
|
ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
|
|
cb(ffn_inp, "ffn_inp", il);
|
|
|
|
// feed-forward network with xIELU activation
|
|
{
|
|
cur = build_norm(ffn_inp, model.layers[il].ffn_norm, nullptr, LLM_NORM_RMS, il);
|
|
cb(cur, "ffn_norm", il);
|
|
|
|
// Up projection
|
|
ggml_tensor * up = build_lora_mm(model.layers[il].ffn_up, cur);
|
|
cb(up, "ffn_up", il);
|
|
|
|
float alpha_n_val = hparams.xielu_alpha_n[il];
|
|
float alpha_p_val = hparams.xielu_alpha_p[il];
|
|
float beta_val = hparams.xielu_beta[il];
|
|
float eps_val = hparams.xielu_eps[il];
|
|
|
|
// Apply xIELU activation
|
|
ggml_tensor * activated = ggml_xielu(ctx0, up, alpha_n_val, alpha_p_val, beta_val, eps_val);
|
|
cb(activated, "ffn_xielu", il);
|
|
|
|
// Down projection
|
|
cur = build_lora_mm(model.layers[il].ffn_down, activated);
|
|
cb(cur, "ffn_down", il);
|
|
}
|
|
|
|
cur = ggml_add(ctx0, cur, ffn_inp);
|
|
cb(cur, "ffn_out", il);
|
|
|
|
cur = build_cvec(cur, il);
|
|
cb(cur, "l_out", il);
|
|
|
|
// input for next layer
|
|
inpL = cur;
|
|
}
|
|
|
|
cur = inpL;
|
|
|
|
cur = build_norm(cur, model.output_norm, nullptr, LLM_NORM_RMS, -1);
|
|
|
|
cb(cur, "result_norm", -1);
|
|
res->t_embd = cur;
|
|
|
|
// lm_head
|
|
cur = build_lora_mm(model.output, cur);
|
|
|
|
cb(cur, "result_output", -1);
|
|
res->t_logits = cur;
|
|
|
|
ggml_build_forward_expand(gf, cur);
|
|
}
|