include llama.cpp since there were some edits
This commit is contained in:
zefie committed
1 parent
db7f28d087
commit
8c66990853
3918 files changed
+1640170
-1
No files matched your search
@@ -0,0 +1,170 @@
|
||||
#include "models.h"
|
||||
|
||||
void llama_model_stablelm::load_arch_hparams(llama_model_loader & ml) {
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
|
||||
|
||||
switch (hparams.n_layer()) {
|
||||
case 24: type = LLM_TYPE_1B; break;
|
||||
case 32: type = LLM_TYPE_3B; break;
|
||||
case 40: type = LLM_TYPE_12B; break;
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
}
|
||||
|
||||
void llama_model_stablelm::load_arch_tensors(llama_model_loader &) {
|
||||
LLAMA_LOAD_LOCALS;
|
||||
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
|
||||
|
||||
// output
|
||||
output_norm_b = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, 0);
|
||||
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
|
||||
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, 0);
|
||||
|
||||
for (int i = 0; i < n_layer; ++i) {
|
||||
auto & layer = layers[i];
|
||||
|
||||
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
|
||||
layer.attn_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}, 0);
|
||||
|
||||
create_tensor_qkv(layer, i, n_embd, n_embd, n_embd_gqa, n_embd_gqa, 0);
|
||||
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
|
||||
|
||||
// optional q and k layernorms, present in StableLM 2 12B
|
||||
layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd_head_k, n_head}, TENSOR_NOT_REQUIRED);
|
||||
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_k, n_head_kv}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
// optional FFN norm, not present in StableLM 2 12B which uses parallel residual
|
||||
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, TENSOR_NOT_REQUIRED);
|
||||
layer.ffn_norm_b = create_tensor(tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
|
||||
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, 0);
|
||||
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
|
||||
}
|
||||
}
|
||||
|
||||
std::unique_ptr<llm_graph_context> llama_model_stablelm::build_arch_graph(const llm_graph_params & params) const {
|
||||
return std::make_unique<graph>(*this, params);
|
||||
}
|
||||
|
||||
llama_model_stablelm::graph::graph(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_tensor * cur;
|
||||
ggml_tensor * inpL;
|
||||
|
||||
inpL = build_inp_embd(model.tok_embd);
|
||||
|
||||
// inp_pos - contains the positions
|
||||
ggml_tensor * inp_pos = build_inp_pos();
|
||||
|
||||
auto * inp_attn = build_attn_inp_kv();
|
||||
|
||||
ggml_tensor * inp_out_ids = build_inp_out_ids();
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
// norm
|
||||
cur = build_norm(inpL,
|
||||
model.layers[il].attn_norm,
|
||||
model.layers[il].attn_norm_b,
|
||||
LLM_NORM, il);
|
||||
cb(cur, "attn_norm", il);
|
||||
|
||||
ggml_tensor * inpSA = cur;
|
||||
|
||||
// self-attention
|
||||
{
|
||||
// compute Q and K and RoPE them
|
||||
auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur,
|
||||
n_embd_head, n_head, n_head_kv, il);
|
||||
|
||||
if (model.layers[il].attn_q_norm) {
|
||||
Qcur = build_norm(Qcur,
|
||||
model.layers[il].attn_q_norm,
|
||||
NULL,
|
||||
LLM_NORM, il);
|
||||
cb(Qcur, "Qcur", il);
|
||||
}
|
||||
if (model.layers[il].attn_k_norm) {
|
||||
Kcur = build_norm(Kcur,
|
||||
model.layers[il].attn_k_norm,
|
||||
NULL,
|
||||
LLM_NORM, il);
|
||||
cb(Kcur, "Kcur", il);
|
||||
}
|
||||
|
||||
Qcur = ggml_rope_ext(
|
||||
ctx0, Qcur, inp_pos, nullptr,
|
||||
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, nullptr,
|
||||
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
|
||||
ext_factor, attn_factor, beta_fast, beta_slow
|
||||
);
|
||||
|
||||
cb(Qcur, "Qcur", il);
|
||||
cb(Kcur, "Kcur", il);
|
||||
cb(Vcur, "Vcur", il);
|
||||
|
||||
cur = build_attn(inp_attn,
|
||||
model.layers[il].wo, NULL, model.layers[il].wo_s,
|
||||
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
|
||||
}
|
||||
if (il == n_layer - 1 && inp_out_ids) {
|
||||
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
|
||||
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
|
||||
inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
|
||||
}
|
||||
ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpL);
|
||||
cb(ffn_inp, "ffn_inp", il);
|
||||
|
||||
// feed-forward network
|
||||
{
|
||||
if (model.layers[il].ffn_norm) {
|
||||
cur = build_norm(ffn_inp,
|
||||
model.layers[il].ffn_norm,
|
||||
model.layers[il].ffn_norm_b,
|
||||
LLM_NORM, il);
|
||||
cb(cur, "ffn_norm", il);
|
||||
} else {
|
||||
// parallel residual
|
||||
cur = inpSA;
|
||||
}
|
||||
cur = build_ffn(cur,
|
||||
model.layers[il].ffn_up, NULL, NULL,
|
||||
model.layers[il].ffn_gate, NULL, NULL,
|
||||
model.layers[il].ffn_down, NULL, NULL,
|
||||
NULL,
|
||||
LLM_FFN_SILU, LLM_FFN_PAR, il);
|
||||
cb(cur, "ffn_out", il);
|
||||
}
|
||||
cur = ggml_add(ctx0, cur, ffn_inp);
|
||||
|
||||
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,
|
||||
model.output_norm_b,
|
||||
LLM_NORM, -1);
|
||||
|
||||
cb(cur, "result_norm", -1);
|
||||
res->t_embd = cur;
|
||||
|
||||
// lm_head
|
||||
cur = build_lora_mm(model.output, cur, model.output_s);
|
||||
|
||||
cb(cur, "result_output", -1);
|
||||
res->t_logits = cur;
|
||||
}
|
||||
Reference in new issue
Block a user