add trainable lora-only model with all big matrices C split into A,B with A*B=C
this is not a lora-finetune, but the whole model changed to have only low-rank "lora" matrices. training this instead of the normal model resulted in much worse results though...
This commit is contained in:
xaedes
parent
e91b83b899
commit
93201abdb7
1 changed files with 503 additions and 1 deletions
|
|
@ -137,6 +137,22 @@ struct llama_hparams {
|
|||
}
|
||||
};
|
||||
|
||||
|
||||
struct llama_hparams_lora {
|
||||
uint32_t n_vocab = 32000;
|
||||
uint32_t n_ctx = 512; // this is provided as user input?
|
||||
uint32_t n_embd = 4096;
|
||||
uint32_t n_mult = 4;
|
||||
uint32_t n_head = 32;
|
||||
uint32_t n_layer = 32;
|
||||
uint32_t n_rot = 64;
|
||||
uint32_t n_lora = 64;
|
||||
|
||||
bool operator!=(const llama_hparams & other) const {
|
||||
return memcmp(this, &other, sizeof(llama_hparams));
|
||||
}
|
||||
};
|
||||
|
||||
struct llama_layer {
|
||||
// normalization
|
||||
struct ggml_tensor * attention_norm;
|
||||
|
|
@ -156,6 +172,29 @@ struct llama_layer {
|
|||
struct ggml_tensor * w3;
|
||||
};
|
||||
|
||||
struct llama_layer_lora {
|
||||
// normalization
|
||||
struct ggml_tensor * attention_norm;
|
||||
|
||||
// attention
|
||||
struct ggml_tensor * wqa;
|
||||
struct ggml_tensor * wqb;
|
||||
struct ggml_tensor * wka;
|
||||
struct ggml_tensor * wkb;
|
||||
struct ggml_tensor * wva;
|
||||
struct ggml_tensor * wvb;
|
||||
struct ggml_tensor * woa;
|
||||
struct ggml_tensor * wob;
|
||||
|
||||
// normalization
|
||||
struct ggml_tensor * ffn_norm;
|
||||
|
||||
// ff
|
||||
struct ggml_tensor * w1;
|
||||
struct ggml_tensor * w2;
|
||||
struct ggml_tensor * w3;
|
||||
};
|
||||
|
||||
|
||||
struct llama_kv_cache {
|
||||
struct ggml_context * ctx = NULL;
|
||||
|
|
@ -181,6 +220,20 @@ struct llama_model {
|
|||
std::vector<llama_layer> layers;
|
||||
};
|
||||
|
||||
struct llama_model_lora {
|
||||
struct ggml_context * ctx = NULL;
|
||||
|
||||
llama_hparams_lora hparams;
|
||||
|
||||
struct ggml_tensor * tok_embeddings;
|
||||
|
||||
struct ggml_tensor * norm;
|
||||
struct ggml_tensor * outputa;
|
||||
struct ggml_tensor * outputb;
|
||||
|
||||
std::vector<llama_layer_lora> layers;
|
||||
};
|
||||
|
||||
void init_model(struct llama_model * model) {
|
||||
const auto & hparams = model->hparams;
|
||||
|
||||
|
|
@ -217,6 +270,49 @@ void init_model(struct llama_model * model) {
|
|||
}
|
||||
}
|
||||
|
||||
|
||||
void init_model_lora(struct llama_model_lora * model) {
|
||||
const auto & hparams = model->hparams;
|
||||
|
||||
const uint32_t n_embd = hparams.n_embd;
|
||||
const uint32_t n_layer = hparams.n_layer;
|
||||
const uint32_t n_vocab = hparams.n_vocab;
|
||||
const uint32_t n_lora = hparams.n_lora;
|
||||
|
||||
uint32_t n_ff = ((2*(4*hparams.n_embd)/3 + hparams.n_mult - 1)/hparams.n_mult)*hparams.n_mult;
|
||||
|
||||
struct ggml_context * ctx = model->ctx;
|
||||
|
||||
model->tok_embeddings = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_vocab); // ("tok_embeddings.weight", {n_embd, n_vocab});
|
||||
model->norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd); // ("norm.weight", {n_embd});
|
||||
model->outputa = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_lora, n_vocab); // ("output.weight", {n_embd, n_vocab});
|
||||
model->outputb = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_lora); // ("output.weight", {n_embd, n_vocab});
|
||||
|
||||
model->layers.resize(n_layer);
|
||||
for (uint32_t i = 0; i < n_layer; ++i) {
|
||||
auto & layer = model->layers[i];
|
||||
|
||||
// std::string layers_i = "layers." + std::to_string(i);
|
||||
|
||||
layer.attention_norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd); // (layers_i + ".attention_norm.weight", {n_embd});
|
||||
|
||||
layer.wqa = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_lora, n_embd); // (layers_i + ".attention.wq.weight", {n_embd, n_embd});
|
||||
layer.wqb = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_lora); // (layers_i + ".attention.wq.weight", {n_embd, n_embd});
|
||||
layer.wka = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_lora, n_embd); // (layers_i + ".attention.wk.weight", {n_embd, n_embd});
|
||||
layer.wkb = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_lora); // (layers_i + ".attention.wk.weight", {n_embd, n_embd});
|
||||
layer.wva = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_lora, n_embd); // (layers_i + ".attention.wv.weight", {n_embd, n_embd});
|
||||
layer.wvb = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_lora); // (layers_i + ".attention.wv.weight", {n_embd, n_embd});
|
||||
layer.woa = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_lora, n_embd); // (layers_i + ".attention.wo.weight", {n_embd, n_embd});
|
||||
layer.wob = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_lora); // (layers_i + ".attention.wo.weight", {n_embd, n_embd});
|
||||
|
||||
layer.ffn_norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd); // (layers_i + ".ffn_norm.weight", {n_embd});
|
||||
|
||||
layer.w1 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_ff); // (layers_i + ".feed_forward.w1.weight", {n_embd, n_ff});
|
||||
layer.w2 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_ff, n_embd); // (layers_i + ".feed_forward.w2.weight", { n_ff, n_embd});
|
||||
layer.w3 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_ff); // (layers_i + ".feed_forward.w3.weight", {n_embd, n_ff});
|
||||
}
|
||||
}
|
||||
|
||||
void set_param_model(struct llama_model * model) {
|
||||
const auto& hparams = model->hparams;
|
||||
const uint32_t n_layer = hparams.n_layer;
|
||||
|
|
@ -241,6 +337,35 @@ void set_param_model(struct llama_model * model) {
|
|||
}
|
||||
}
|
||||
|
||||
void set_param_model_lora(struct llama_model_lora * model) {
|
||||
const auto& hparams = model->hparams;
|
||||
const uint32_t n_layer = hparams.n_layer;
|
||||
struct ggml_context* ctx = model->ctx;
|
||||
|
||||
ggml_set_param(ctx, model->tok_embeddings);
|
||||
ggml_set_param(ctx, model->norm);
|
||||
ggml_set_param(ctx, model->outputa);
|
||||
ggml_set_param(ctx, model->outputb);
|
||||
|
||||
for (uint32_t i = 0; i < n_layer; ++i) {
|
||||
auto & layer = model->layers[i];
|
||||
|
||||
ggml_set_param(ctx, layer.attention_norm);
|
||||
ggml_set_param(ctx, layer.wqa);
|
||||
ggml_set_param(ctx, layer.wqb);
|
||||
ggml_set_param(ctx, layer.wka);
|
||||
ggml_set_param(ctx, layer.wkb);
|
||||
ggml_set_param(ctx, layer.wva);
|
||||
ggml_set_param(ctx, layer.wvb);
|
||||
ggml_set_param(ctx, layer.woa);
|
||||
ggml_set_param(ctx, layer.wob);
|
||||
ggml_set_param(ctx, layer.ffn_norm);
|
||||
ggml_set_param(ctx, layer.w1);
|
||||
ggml_set_param(ctx, layer.w2);
|
||||
ggml_set_param(ctx, layer.w3);
|
||||
}
|
||||
}
|
||||
|
||||
void randomize_model(struct llama_model * model, int seed, float mean, float std, float min, float max) {
|
||||
const auto & hparams = model->hparams;
|
||||
|
||||
|
|
@ -273,6 +398,44 @@ void randomize_model(struct llama_model * model, int seed, float mean, float std
|
|||
}
|
||||
}
|
||||
|
||||
|
||||
void randomize_model_lora(struct llama_model_lora * model, int seed, float mean, float std, float min, float max) {
|
||||
const auto & hparams = model->hparams;
|
||||
|
||||
const uint32_t n_embd = hparams.n_embd;
|
||||
const uint32_t n_layer = hparams.n_layer;
|
||||
const uint32_t n_vocab = hparams.n_vocab;
|
||||
|
||||
uint32_t n_ff = ((2*(4*hparams.n_embd)/3 + hparams.n_mult - 1)/hparams.n_mult)*hparams.n_mult;
|
||||
|
||||
struct random_normal_distribution rnd;
|
||||
init_random_normal_distribution(&rnd, seed, mean, std, min, max);
|
||||
randomize_tensor_normal(model->tok_embeddings, model->tok_embeddings->n_dims, model->tok_embeddings->ne, &rnd);
|
||||
randomize_tensor_normal(model->norm, model->norm->n_dims, model->norm->ne, &rnd);
|
||||
randomize_tensor_normal(model->outputa, model->outputa->n_dims, model->outputa->ne, &rnd);
|
||||
randomize_tensor_normal(model->outputb, model->outputb->n_dims, model->outputb->ne, &rnd);
|
||||
|
||||
for (uint32_t i = 0; i < n_layer; ++i) {
|
||||
auto & layer = model->layers[i];
|
||||
randomize_tensor_normal(layer.attention_norm, layer.attention_norm->n_dims, layer.attention_norm->ne, &rnd);
|
||||
|
||||
randomize_tensor_normal(layer.wqa, layer.wqa->n_dims, layer.wqa->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wqb, layer.wqb->n_dims, layer.wqb->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wka, layer.wka->n_dims, layer.wka->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wkb, layer.wkb->n_dims, layer.wkb->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wva, layer.wva->n_dims, layer.wva->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wvb, layer.wvb->n_dims, layer.wvb->ne, &rnd);
|
||||
randomize_tensor_normal(layer.woa, layer.woa->n_dims, layer.woa->ne, &rnd);
|
||||
randomize_tensor_normal(layer.wob, layer.wob->n_dims, layer.wob->ne, &rnd);
|
||||
|
||||
randomize_tensor_normal(layer.ffn_norm, layer.ffn_norm->n_dims, layer.ffn_norm->ne, &rnd);
|
||||
|
||||
randomize_tensor_normal(layer.w1, layer.w1->n_dims, layer.w1->ne, &rnd);
|
||||
randomize_tensor_normal(layer.w2, layer.w2->n_dims, layer.w2->ne, &rnd);
|
||||
randomize_tensor_normal(layer.w3, layer.w3->n_dims, layer.w3->ne, &rnd);
|
||||
}
|
||||
}
|
||||
|
||||
bool init_kv_cache(struct llama_kv_cache* cache, struct llama_model * model) {
|
||||
const auto & hparams = model->hparams;
|
||||
const int n_ctx = hparams.n_ctx;
|
||||
|
|
@ -308,6 +471,41 @@ bool init_kv_cache(struct llama_kv_cache* cache, struct llama_model * model) {
|
|||
return true;
|
||||
}
|
||||
|
||||
bool init_kv_cache_lora(struct llama_kv_cache* cache, struct llama_model_lora * model) {
|
||||
const auto & hparams = model->hparams;
|
||||
const int n_ctx = hparams.n_ctx;
|
||||
const int n_embd = hparams.n_embd;
|
||||
const int n_layer = hparams.n_layer;
|
||||
|
||||
const int64_t n_mem = n_layer*n_ctx;
|
||||
const int64_t n_elements = n_embd*n_mem;
|
||||
|
||||
// cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*MB);
|
||||
|
||||
// struct ggml_init_params params;
|
||||
// params.mem_size = cache.buf.size;
|
||||
// params.mem_buffer = cache.buf.addr;
|
||||
// params.no_alloc = false;
|
||||
if (!cache->ctx) {
|
||||
struct ggml_init_params params;
|
||||
params.mem_size = 2u*n_elements*ggml_type_size(GGML_TYPE_F32) + 2u*1024*1024;
|
||||
params.mem_buffer = NULL;
|
||||
params.no_alloc = false;
|
||||
|
||||
cache->ctx = ggml_init(params);
|
||||
|
||||
if (!cache->ctx) {
|
||||
fprintf(stderr, "%s: failed to allocate memory for kv cache\n", __func__);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
cache->k = ggml_new_tensor_1d(cache->ctx, GGML_TYPE_F32, n_elements);
|
||||
cache->v = ggml_new_tensor_1d(cache->ctx, GGML_TYPE_F32, n_elements);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
struct ggml_tensor * forward(
|
||||
struct llama_model * model,
|
||||
struct llama_kv_cache * cache,
|
||||
|
|
@ -452,6 +650,7 @@ struct ggml_tensor * forward(
|
|||
// ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, N));
|
||||
|
||||
// projection (no bias)
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].wo,
|
||||
cur);
|
||||
|
|
@ -459,50 +658,62 @@ struct ggml_tensor * forward(
|
|||
|
||||
// lctx.use_buf(ctx0, 1);
|
||||
|
||||
// inpFF shape [n_embd,N,1,1]
|
||||
struct ggml_tensor * inpFF = ggml_add(ctx0, cur, inpSA);
|
||||
|
||||
// feed-forward network
|
||||
{
|
||||
// norm
|
||||
{
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_rms_norm(ctx0, inpFF);
|
||||
|
||||
// cur = ffn_norm*cur
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->layers[il].ffn_norm, cur),
|
||||
cur);
|
||||
}
|
||||
|
||||
// tmp shape [n_ff,N,1,1]
|
||||
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w3,
|
||||
cur);
|
||||
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w1,
|
||||
cur);
|
||||
|
||||
// SILU activation
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_silu(ctx0, cur);
|
||||
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_mul(ctx0, cur, tmp);
|
||||
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w2,
|
||||
cur);
|
||||
}
|
||||
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_add(ctx0, cur, inpFF);
|
||||
|
||||
// input for next layer
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = cur;
|
||||
}
|
||||
|
||||
// norm
|
||||
{
|
||||
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
// inpL = norm*inpL
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->norm, inpL),
|
||||
inpL);
|
||||
|
|
@ -511,6 +722,7 @@ struct ggml_tensor * forward(
|
|||
}
|
||||
|
||||
// lm_head
|
||||
// inpL shape [n_vocab,N,1,1]
|
||||
inpL = ggml_mul_mat(ctx0, model->output, inpL);
|
||||
|
||||
// run the computation
|
||||
|
|
@ -519,6 +731,261 @@ struct ggml_tensor * forward(
|
|||
return inpL;
|
||||
}
|
||||
|
||||
|
||||
struct ggml_tensor * forward_lora(
|
||||
struct llama_model_lora * model,
|
||||
struct llama_kv_cache * cache,
|
||||
struct ggml_context * ctx0,
|
||||
struct ggml_cgraph * gf,
|
||||
struct ggml_tensor * tokens_input,
|
||||
const int n_tokens,
|
||||
const int n_past) {
|
||||
|
||||
const int N = n_tokens;
|
||||
|
||||
struct llama_kv_cache& kv_self = *cache;
|
||||
const auto & hparams = model->hparams;
|
||||
const int n_ctx = hparams.n_ctx;
|
||||
const int n_embd = hparams.n_embd;
|
||||
const int n_layer = hparams.n_layer;
|
||||
const int n_head = hparams.n_head;
|
||||
const int n_rot = hparams.n_rot;
|
||||
const int n_lora = hparams.n_lora;
|
||||
|
||||
struct ggml_tensor * tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
|
||||
memcpy(tokens->data, tokens_input->data, N*ggml_element_size(tokens));
|
||||
|
||||
struct ggml_tensor * kc = kv_self.k;
|
||||
struct ggml_tensor * vc = kv_self.v;
|
||||
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
struct ggml_tensor * inpL = ggml_get_rows(ctx0, model->tok_embeddings, tokens);
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
struct ggml_tensor * inpSA = inpL;
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
|
||||
// norm
|
||||
{
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
// cur = attention_norm*cur
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->layers[il].attention_norm, cur),
|
||||
cur);
|
||||
}
|
||||
|
||||
// self-attention
|
||||
{
|
||||
// compute Q and K and RoPE them
|
||||
// wq shape [n_embd, n_embd, 1, 1]
|
||||
// wk shape [n_embd, n_embd, 1, 1]
|
||||
// Qcur shape [n_embd/n_head, n_head, N, 1]
|
||||
// Kcur shape [n_embd/n_head, n_head, N, 1]
|
||||
struct ggml_tensor * Qcur = ggml_rope(ctx0,
|
||||
ggml_reshape_3d(ctx0,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wqa,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wqb,
|
||||
cur)),
|
||||
n_embd/n_head, n_head, N),
|
||||
n_past, n_rot, 0);
|
||||
struct ggml_tensor * Kcur = ggml_rope(ctx0,
|
||||
ggml_reshape_3d(ctx0,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wka,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wkb,
|
||||
cur)),
|
||||
n_embd/n_head, n_head, N),
|
||||
n_past, n_rot, 0);
|
||||
|
||||
// store key and value to memory
|
||||
{
|
||||
// compute the transposed [N, n_embd] V matrix
|
||||
// wv shape [n_embd, n_embd, 1, 1]
|
||||
// Vcur shape [n_embd, N, 1, 1]
|
||||
struct ggml_tensor * Vcur = ggml_cont(ctx0,
|
||||
ggml_transpose(ctx0,
|
||||
ggml_reshape_2d(ctx0,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wva,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wvb,
|
||||
cur)),
|
||||
n_embd, N)));
|
||||
|
||||
// kv_self.k shape [n_embd * n_ctx * n_layer, 1]
|
||||
// kv_self.v shape [n_embd * n_ctx * n_layer, 1]
|
||||
// k shape [n_embd * N, 1] == kv_self.k[:,n_past:n_past+N,il,0]
|
||||
// v shape [N, n_embd, 1, 1] == kv_self.v[:,n_past:n_past+N,il,0]
|
||||
|
||||
/* {
|
||||
struct ggml_tensor * k = ggml_view_1d(ctx0, kv_self.k, N*n_embd, (ggml_element_size(kv_self.k)*n_embd)*(il*n_ctx + n_past));
|
||||
struct ggml_tensor * v = ggml_view_2d(ctx0, kv_self.v, N, n_embd,
|
||||
( n_ctx)*ggml_element_size(kv_self.v),
|
||||
(il*n_ctx)*ggml_element_size(kv_self.v)*n_embd + n_past*ggml_element_size(kv_self.v));
|
||||
|
||||
// important: storing RoPE-ed version of K in the KV cache!
|
||||
ggml_build_forward_expand(gf, ggml_cpy(ctx0, Kcur, k));
|
||||
ggml_build_forward_expand(gf, ggml_cpy(ctx0, Vcur, v));
|
||||
} //*/
|
||||
|
||||
kc = ggml_set_1d(ctx0, kc, ggml_reshape_1d(ctx0, Kcur, n_embd*N), (ggml_element_size(kv_self.k)*n_embd)*(il*n_ctx + n_past));
|
||||
vc = ggml_set_2d(ctx0, vc, Vcur, ( n_ctx)*ggml_element_size(kv_self.v),
|
||||
(il*n_ctx)*ggml_element_size(kv_self.v)*n_embd + n_past*ggml_element_size(kv_self.v));
|
||||
}
|
||||
|
||||
// Qcur shape [n_embd/n_head, n_head, N, 1]
|
||||
// Q shape [n_embd/n_head, N, n_head, 1]
|
||||
struct ggml_tensor * Q =
|
||||
ggml_permute(ctx0,
|
||||
Qcur,
|
||||
0, 2, 1, 3);
|
||||
|
||||
// kv_self.k shape [n_embd * n_ctx * n_layer, 1]
|
||||
// K shape [n_embd/n_head, n_past + N, n_head, 1]
|
||||
struct ggml_tensor * K =
|
||||
ggml_permute(ctx0,
|
||||
ggml_reshape_3d(ctx0,
|
||||
ggml_view_1d(ctx0, kc, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(kc)*n_embd),
|
||||
n_embd/n_head, n_head, n_past + N),
|
||||
0, 2, 1, 3);
|
||||
|
||||
// K * Q
|
||||
// KQ shape [n_past + N, N, n_head, 1]
|
||||
struct ggml_tensor * KQ = ggml_mul_mat(ctx0, K, Q);
|
||||
|
||||
// KQ_scaled = KQ / sqrt(n_embd/n_head)
|
||||
// KQ_scaled shape [n_past + N, N, n_head, 1]
|
||||
struct ggml_tensor * KQ_scaled =
|
||||
ggml_scale(ctx0,
|
||||
KQ,
|
||||
ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head)));
|
||||
|
||||
// KQ_masked = mask_past(KQ_scaled)
|
||||
// KQ_masked shape [n_past + N, N, n_head, 1]
|
||||
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
|
||||
|
||||
// KQ = soft_max(KQ_masked)
|
||||
// KQ_soft_max shape [n_past + N, N, n_head, 1]
|
||||
struct ggml_tensor * KQ_soft_max = ggml_soft_max(ctx0, KQ_masked);
|
||||
|
||||
// split cached V into n_head heads
|
||||
//// V shape [n_past + N, n_embd/n_head, n_head, 1]
|
||||
// V shape [n_past + N, n_embd/n_head, n_head, 1] == kv_self.v[:,:(n_past+N),il,1]
|
||||
struct ggml_tensor * V =
|
||||
ggml_view_3d(ctx0, vc,
|
||||
n_past + N, n_embd/n_head, n_head,
|
||||
n_ctx*ggml_element_size(vc),
|
||||
n_ctx*ggml_element_size(vc)*n_embd/n_head,
|
||||
il*n_ctx*ggml_element_size(vc)*n_embd);
|
||||
|
||||
// KQV shape [n_embd/n_head, N, n_head, 1]
|
||||
struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V, KQ_soft_max);
|
||||
|
||||
// KQV_merged = KQV.permute(0, 2, 1, 3)
|
||||
// KQV_merged shape [n_embd/n_head, n_head, N, 1]
|
||||
struct ggml_tensor * KQV_merged = ggml_permute(ctx0, KQV, 0, 2, 1, 3);
|
||||
// KQV_merged shape
|
||||
|
||||
// cur = KQV_merged.contiguous().view(n_embd, N)
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_reshape_2d(ctx0, ggml_cont(ctx0, KQV_merged), n_embd, N);
|
||||
// cur = ggml_cpy(ctx0,
|
||||
// KQV_merged,
|
||||
// ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, N));
|
||||
|
||||
// projection (no bias)
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].woa,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wob,
|
||||
cur));
|
||||
}
|
||||
|
||||
// inpFF shape [n_embd,N,1,1]
|
||||
struct ggml_tensor * inpFF = ggml_add(ctx0, cur, inpSA);
|
||||
|
||||
// feed-forward network
|
||||
{
|
||||
// norm
|
||||
{
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_rms_norm(ctx0, inpFF);
|
||||
|
||||
// cur = ffn_norm*cur
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->layers[il].ffn_norm, cur),
|
||||
cur);
|
||||
}
|
||||
|
||||
// tmp shape [n_ff,N,1,1]
|
||||
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w3,
|
||||
cur);
|
||||
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w1,
|
||||
cur);
|
||||
|
||||
// SILU activation
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_silu(ctx0, cur);
|
||||
|
||||
// cur shape [n_ff,N,1,1]
|
||||
cur = ggml_mul(ctx0, cur, tmp);
|
||||
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w2,
|
||||
cur);
|
||||
}
|
||||
|
||||
// cur shape [n_embd,N,1,1]
|
||||
cur = ggml_add(ctx0, cur, inpFF);
|
||||
|
||||
// input for next layer
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = cur;
|
||||
}
|
||||
|
||||
// norm
|
||||
{
|
||||
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
// inpL = norm*inpL
|
||||
// inpL shape [n_embd,N,1,1]
|
||||
inpL = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->norm, inpL),
|
||||
inpL);
|
||||
|
||||
//embeddings = inpL;
|
||||
}
|
||||
|
||||
|
||||
// lm_head
|
||||
// inpL shape [n_vocab,N,1,1]
|
||||
inpL = ggml_mul_mat(ctx0,
|
||||
model->outputa,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->outputb,
|
||||
inpL));
|
||||
|
||||
// ggml_set_scratch(ctx0, { 0, 0, nullptr, });
|
||||
// run the computation
|
||||
ggml_build_forward_expand(gf, inpL);
|
||||
|
||||
return inpL;
|
||||
}
|
||||
|
||||
void sample_softmax(struct ggml_tensor * logits, struct ggml_tensor * probs, struct ggml_tensor * best_samples) {
|
||||
assert(logits->n_dims == 2);
|
||||
assert(probs->n_dims == 2);
|
||||
|
|
@ -665,12 +1132,46 @@ int main(int argc, char ** argv) {
|
|||
|
||||
randomize_model(&model, 1337, 0.0f, 1.0f, -1.0f, +1.0f);
|
||||
|
||||
/*
|
||||
struct llama_model_lora model_lora;
|
||||
// model.hparams.n_vocab = 6;
|
||||
// model.hparams.n_ctx = 64;
|
||||
// model.hparams.n_embd = 128;
|
||||
// model.hparams.n_mult = 2;
|
||||
// model.hparams.n_head = 8;
|
||||
// model.hparams.n_layer = 6;
|
||||
// model.hparams.n_rot = model.hparams.n_embd / model.hparams.n_head;
|
||||
|
||||
model_lora.hparams.n_vocab = 16;
|
||||
model_lora.hparams.n_ctx = 32;
|
||||
model_lora.hparams.n_embd = 256;
|
||||
model_lora.hparams.n_mult = 2;
|
||||
model_lora.hparams.n_head = 16;
|
||||
model_lora.hparams.n_layer = 1;
|
||||
model_lora.hparams.n_lora = 64;
|
||||
model_lora.hparams.n_rot = MIN(16, model_lora.hparams.n_embd / model_lora.hparams.n_head);
|
||||
// model.hparams.n_rot = (model.hparams.n_embd / model.hparams.n_head) / 2;
|
||||
|
||||
// model.hparams.n_embd = 32;
|
||||
// model.hparams.n_mult = 2;
|
||||
// model.hparams.n_head = 4;
|
||||
// model.hparams.n_layer = 8;
|
||||
// model.hparams.n_rot = 8;
|
||||
|
||||
model_lora.ctx = ggml_init(lcparams);
|
||||
printf("init model_lora\n");
|
||||
init_model_lora(&model_lora);
|
||||
set_param_model_lora(&model_lora);
|
||||
|
||||
randomize_model_lora(&model_lora, 1337, 0.0f, 1.0f, -1.0f, +1.0f);
|
||||
*/
|
||||
|
||||
// key + value cache for the self attention
|
||||
struct llama_kv_cache kv_self;
|
||||
printf("init_kv_cache\n");
|
||||
kv_self.ctx = model.ctx;
|
||||
init_kv_cache(&kv_self, &model);
|
||||
|
||||
//init_kv_cache_lora(&kv_self, &model_lora);
|
||||
|
||||
size_t compute_size = 1024ll*1024ll*1024ll;
|
||||
uint8_t * compute_addr = new uint8_t[compute_size];
|
||||
|
|
@ -842,6 +1343,7 @@ int main(int argc, char ** argv) {
|
|||
|
||||
printf("done\n");
|
||||
// ggml_free(kv_self.ctx);
|
||||
// ggml_free(model_lora.ctx);
|
||||
ggml_free(model.ctx);
|
||||
return 0;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue