aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-14 17:09:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama.cpp/examples/baby-llama/baby-llama.cpp
xaedes e32089b2c2
train : improved training-from-scratch example (#1652) 
* add python wrapper

https://gist.github.com/abetlen/2b90e5f153f6efd00931d098de5c73ce

* fix decoding error. adds errors=ignore parameter

* add python bindings for functions to get and set the whole llama state
(rng, logits, embedding and kv_cache)

* update python bindings

* add text generating baby-llama from scratch example

* fix race condition bug in ggml_compute_forward_diag_mask_f32

* implement ggml_soft_max_back for more performant backward pass of soft_max

avoids creating big intermediate matrices of size n_embd x n_embd for llama layers and n_vocab x n_vocab for cross entropy loss

* improve softmax backward pass

go from quadratic runtime to linear runtime by simplifying the formulas

* fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32

memcpy needs to be synchronized across threads to avoid race conditions.
=> do it in INIT phase

* fix bug in ggml_compute_forward_soft_max_back_f32 on DEBUG build

* improve performance of mul_mat backward pass

avoid transpose by using mul_mat with swapped arguments

* avoid printing too much newlines in baby-llama-text

* activate threading in baby-llama-text

* add ggml_out_prod and use it for mul_mat backward pass for improved performance

performance stats report improvement from 37 seconds to 16 seconds runtime during my training tests

* better weight initialization improves training convergence at start

* better weight initialization improves training convergence at start

* improve ggml_out_prod performance

- change iteration order (>15s -> 10s runtime)
- parallelize over one more dimension: over dst matrix rows (10s -> <5s runtime)

* add llama sampler, shuffle samples and constrain sampling to tokens occurring in train data

* fix get_samples call, add model tensor names, increase model size, start training samples after newline

* save train trained model to checkpoint and load model to be trained from checkpoint

* use inplace functions where possible

* initialize rng with srand

* use different arguments for input and output checkpoint

* ggml fixes to support backward pass on inplace operations

* remove duplicate include

* fix cross entropy loss

- add target probabilities for each sample which is then used in cross entropy loss

* print used memory before and after optimization

* sample with non-greedy sampling parameters at the end of training

* add cmake target for baby-llama-text

* add ggml_add1_inplace to header

* enable gradient propagation for inplace add1 and scale operations

those functions backward passes don't need the original src0, so they also work when forward is inplace

* implement AdamW in ggml_opt_adam by adding weight decay parameter (default 0.001f)

also add a schedule parameter (default 1.0f) that can be used to scale alpha and decay according to learning schedule.
setting the decay parameter to zero disables AdamW resulting in normal Adam optimizer.

since the difference between Adam and AdamW is minimal it is not implemented as another optimizer, but integrated into the existing Adam optimizer.

* use inplace operations in cross_entropy_loss

* fix random weight initialization scale

* add missing default parameters for adam optimizer

* add ggml_opt_context, so that we can properly resume training

otherwise the optimizer states, tracking statistics about the error function and its derivates,
will reset to zero each time ggml_opt is called, hindering convergence on resumed training.

now the optimizer context and all its memory is stored in a separate struct.

* fix bug in llama_sample_token_mirostat_v2

when all candidates are filtered out through mu threshold, the following soft_max operation will fail.
so keep at least one.

* add forward function without using cache, for more performant training

during training on whole samples no cache is required.
removing the cache and simplifying the remaining code results in performance and memory usage improvement.

* print suppressed newline tokens as string "\n"

printing too much actual newlines is suppressed to avoid flooding the console.

* store optimizer state in training checkpoint and add learning schedule

persistent optimizer state allows to resume training without resetting the optimizer
learning schedule consists of linear warmup ramp followed by cosine decay with restarts

* remove unused functions

* fix bug in get_samples which corrupted training targets

* save checkpoint only when it was trained

* simplify code

* remove trailing whitespace

* simplify backward pass for SQRT

* replace inefficient repeat backward pass with dedicated repeat_back operation

* add ggml_cross_entropy_loss with backward pass for faster training

cross entropy loss can also be implemented using softmax and log, but as dedicated operation it is faster and especially avoids unnecessary memory overhead.

* add tests for cross_entropy_loss backward pass

finite differences regularly results in estimated gradient of zero, despite the backward pass giving non zero gradient.
_probably_ the finite differences fails due to numerical issues

* use ggml_cross_entropy_loss in text training example

* remove trailing whitespace

* slightly improve how cross entropy loss is compute

btw: directly implemented cross entropy loss seems to have way lower magnitudes than when implemented with softmax and log.
probably the input to log gets closer to zero due to float numerics.
maybe the multiplication by (1.0-eps)/sum is more accurate..

* add llama_get_vocab to get the vocabulary as output parameters

* set default model.type for unknown models with few layers

* add export of training checkpoint to llama compatible model file

* get vocabulary for exporting training checkpoint to llama compatible model file

* implement backward pass of flash attention

* bugfixes for backward pass of flash attention

* test flash attention backward pass

need to set loose error bounds to pass.
the finitie differences are close to numeric limits and often return quite different values than the backward pass.
reducing eps further lets the gradients vanish completely.
likewise setting eps to big results in wronger values.
the softmax in the middle of the function is probably the most responsible for the numeric issues using finite differences.

* add option to train with flash attention and move options to the top of the main function

training from scratch also works with flash attention
training convergence and generation results after fix number of iterations are worse than when not using flash attention.
maybe there still lingers a bug in the flash attention backward pass?
but training works, just with slower convergence.

flash attention is still worth to use, because it requires way less memory and is faster with high n_ctx

* add train_params and command line option parser

* remove unnecessary comments

* add train params to specify memory size

* remove python bindings

* rename baby-llama-text to train-text-from-scratch

* replace auto parameters in lambda function

* add #include <climits>

* add explicit cast to fix compile error

"error: non-constant-expression cannot be narrowed from type 'int64_t' (aka 'long long') to 'uint32_t' (aka 'unsigned int') in initializer list [-Wc++11-narrowing]"

* remove trailing whitespace

* add ggml_opt_resume_g which accepts forward and backward cgraphs

* fix formulas in comments

* bug fix for ggml_compute_forward_get_rows_back_f32

the result should be set to zero, not to whatever data is in opt0

* improve training memory usage with scratch buffers

instead of relying on the automatic backward pass, we manually create the graph for the backward pass.
it turns out that all backward pass operations need only temporary memory which can be reused after each layer.

will compute backward pass for ALL model parameters

* add option to use scratch buffers in training or not

make it configurable because currently training with scratch buffers implies flash attention and optimization over all parameters.

* ci : disable temporary

* store view offset and permute axes in opt[0] instead of storing it in padding

use memcpy to store offset, because offset is of type size_t.
when storing it as int32_t offset would have to be smaller than 2^31 which is not necessarily true.

* minor : fix compile warnings + minor style changes

* fix bug in threaded indices calculation of ggml_compute_forward_flash_attn_back_f32

* store view offset like in master branch

* bug fix in forward_batch_wo_cache_flash_attn_train

* scratch buffer bug fixes in forward_batch_wo_cache_flash_attn_train

data of permute and reshape is the same as their input.
if we want to preserve the output of permute/reshape, we also need to preserve their inputs.

replace reshape(src0, src1) with reshape_nd calls so that we don't need src1.

replace (temporary) t03 with ggml_repeat(ctx0, layer.attention_norm, t02).
in the future we could also use the new broadcasting ggml_mul to avoid these repeat calls.
for this we need backward pass of broadcasting ggml_mul.

* remove unnecessary scratch buffer 0

buf 0 is persistent memory, so we can just disable scratch for this by using buf -1

* avoid creating unnecessary grad tensors

previously we need to create grads for model parameters, so that expand(..) correctly populates cgraph->leafs & cgraph->grads
this wasted memory, because unnecessary grad for each op were automatically created:
the automatically generated grad was unnecessary because we later manually set the grad (e.g. t35->grad = expand(gb, ...) ).
this discarded the automatically generated grad resulting in wasted memory.

improved this by changing expand(..) to not use ggml_build_forward_expand.
expand set cgraph->nodes but not the leafs.
cgraph->leafs & cgraph->grads are set in another pass after the last expand call.

* print used training seed

* zero initialize gfbuf and gbbuf

* ci : re-enable workflows + add README for training

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-13 22:04:40 +03:00

1692 lines
64 KiB
C++
Raw Blame History

#include "ggml.h"
#include <vector>
#include <cassert>
#include <random>
#include <cstring>
float frand() {
return (float)rand()/(float)RAND_MAX;
}
struct random_normal_distribution {
std::mt19937 gen;
std::normal_distribution<float> nd;
float min;
float max;
};
void init_random_normal_distribution(struct random_normal_distribution * rnd, int seed, float mean, float std, float min, float max) {
rnd->gen = std::mt19937(seed);
rnd->nd = std::normal_distribution<float>{mean, std};
rnd->min = min;
rnd->max = max;
}
float frand_normal(struct random_normal_distribution * rnd) {
const float r = rnd->nd(rnd->gen);
return ((r < rnd->min) ? (rnd->min) : (r > rnd->max) ? (rnd->max) : r);
}
struct ggml_tensor * randomize_tensor(
struct ggml_tensor * tensor,
int ndims,
const int64_t ne[],
float fmin,
float fmax) {
switch (ndims) {
case 1:
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i0] = frand()*(fmax - fmin) + fmin;
}
break;
case 2:
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
}
}
break;
case 3:
for (int i2 = 0; i2 < ne[2]; i2++) {
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i2*ne[1]*ne[0] + i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
}
}
}
break;
case 4:
for (int i3 = 0; i3 < ne[3]; i3++) {
for (int i2 = 0; i2 < ne[2]; i2++) {
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i3*ne[2]*ne[1]*ne[0] + i2*ne[1]*ne[0] + i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
}
}
}
}
break;
default:
assert(false);
};
return tensor;
}
struct ggml_tensor * randomize_tensor_normal(
struct ggml_tensor * tensor,
int ndims,
const int64_t ne[],
struct random_normal_distribution * rnd) {
float scale = 1.0; // xavier
switch (ndims) {
case 1:
scale /= sqrtf(ne[0]);
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i0] = scale * frand_normal(rnd);
}
break;
case 2:
scale /= sqrtf(ne[0]+ne[1]);
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i1*ne[0] + i0] = scale * frand_normal(rnd);
}
}
break;
case 3:
scale /= sqrtf(ne[0]+ne[1]);
for (int i2 = 0; i2 < ne[2]; i2++) {
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i2*ne[1]*ne[0] + i1*ne[0] + i0] = scale * frand_normal(rnd);
}
}
}
break;
case 4:
scale /= sqrtf(ne[0]+ne[1]);
for (int i3 = 0; i3 < ne[3]; i3++) {
for (int i2 = 0; i2 < ne[2]; i2++) {
for (int i1 = 0; i1 < ne[1]; i1++) {
for (int i0 = 0; i0 < ne[0]; i0++) {
((float *)tensor->data)[i3*ne[2]*ne[1]*ne[0] + i2*ne[1]*ne[0] + i1*ne[0] + i0] = scale * frand_normal(rnd);
}
}
}
}
break;
default:
assert(false);
};
return tensor;
}
struct llama_hparams {
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;
bool operator!=(const llama_hparams & other) const {
return memcmp(this, &other, sizeof(llama_hparams));
}
};
uint32_t get_n_ff(const struct llama_hparams* hparams) {
const uint32_t n_ff = ((2*(4*hparams->n_embd)/3 + hparams->n_mult - 1)/hparams->n_mult)*hparams->n_mult;
return n_ff;
}
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;
// attention
struct ggml_tensor * wq;
struct ggml_tensor * wk;
struct ggml_tensor * wv;
struct ggml_tensor * wo;
// normalization
struct ggml_tensor * ffn_norm;
// ff
struct ggml_tensor * w1;
struct ggml_tensor * w2;
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;
struct ggml_tensor * k;
struct ggml_tensor * v;
// llama_ctx_buffer buf;
int n; // number of tokens currently in the cache
};
struct llama_model {
struct ggml_context * ctx = NULL;
llama_hparams hparams;
struct ggml_tensor * tok_embeddings;
struct ggml_tensor * norm;
struct ggml_tensor * output;
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;
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_ff = get_n_ff(&hparams);
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->output = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_vocab); // ("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.wq = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_embd); // (layers_i + ".attention.wq.weight", {n_embd, n_embd});
layer.wk = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_embd); // (layers_i + ".attention.wk.weight", {n_embd, n_embd});
layer.wv = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_embd); // (layers_i + ".attention.wv.weight", {n_embd, n_embd});
layer.wo = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, n_embd, n_embd); // (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 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_mult = hparams.n_mult;
const uint32_t n_layer = hparams.n_layer;
const uint32_t n_vocab = hparams.n_vocab;
const uint32_t n_lora = hparams.n_lora;
const uint32_t n_ff = ((2*(4*n_embd)/3 + n_mult - 1)/n_mult)*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;
struct ggml_context* ctx = model->ctx;
ggml_set_param(ctx, model->tok_embeddings);
ggml_set_param(ctx, model->norm);
ggml_set_param(ctx, model->output);
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.wq);
ggml_set_param(ctx, layer.wk);
ggml_set_param(ctx, layer.wv);
ggml_set_param(ctx, layer.wo);
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 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;
const uint32_t n_layer = hparams.n_layer;
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->output, model->output->n_dims, model->output->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.wq, layer.wq->n_dims, layer.wq->ne, &rnd);
randomize_tensor_normal(layer.wk, layer.wk->n_dims, layer.wk->ne, &rnd);
randomize_tensor_normal(layer.wv, layer.wv->n_dims, layer.wv->ne, &rnd);
randomize_tensor_normal(layer.wo, layer.wo->n_dims, layer.wo->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);
}
}
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_layer = hparams.n_layer;
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, int n_batch) {
const auto & hparams = model->hparams;
const uint32_t n_ctx = hparams.n_ctx;
const uint32_t n_embd = hparams.n_embd;
const uint32_t n_layer = hparams.n_layer;
const int64_t n_mem = n_layer*n_ctx*n_batch;
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;
}
bool init_kv_cache_lora(struct llama_kv_cache* cache, struct llama_model_lora * model, int n_batch) {
const auto & hparams = model->hparams;
const uint32_t n_ctx = hparams.n_ctx;
const uint32_t n_embd = hparams.n_embd;
const uint32_t n_layer = hparams.n_layer;
const int64_t n_mem = n_layer*n_ctx*n_batch;
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,
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;
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;
// lctx.use_buf(ctx0, 0);
// 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].wq, 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].wk, 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].wv, 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].wo,
cur);
}
// 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);
//embeddings = inpL;
}
// lm_head
// inpL shape [n_vocab,N,1,1]
inpL = ggml_mul_mat(ctx0, model->output, inpL);
// run the computation
ggml_build_forward_expand(gf, inpL);
return inpL;
}
void assert_shape_1d(struct ggml_tensor * tensor, int64_t ne0) {
GGML_ASSERT(tensor->n_dims == 1);
GGML_ASSERT(tensor->ne[0] == ne0);
}
void assert_shape_2d(struct ggml_tensor * tensor, int64_t ne0, int64_t ne1) {
GGML_ASSERT(tensor->n_dims == 2);
GGML_ASSERT(tensor->ne[0] == ne0);
GGML_ASSERT(tensor->ne[1] == ne1);
}
void assert_shape_3d(struct ggml_tensor * tensor, int64_t ne0, int64_t ne1, int64_t ne2) {
GGML_ASSERT(tensor->n_dims == 3);
GGML_ASSERT(tensor->ne[0] == ne0);
GGML_ASSERT(tensor->ne[1] == ne1);
GGML_ASSERT(tensor->ne[2] == ne2);
}
void assert_shape_4d(struct ggml_tensor * tensor, int64_t ne0, int64_t ne1, int64_t ne2, int64_t ne3) {
GGML_ASSERT(tensor->n_dims == 4);
GGML_ASSERT(tensor->ne[0] == ne0);
GGML_ASSERT(tensor->ne[1] == ne1);
GGML_ASSERT(tensor->ne[2] == ne2);
GGML_ASSERT(tensor->ne[3] == ne3);
}
struct ggml_tensor * forward_batch(
struct llama_model * 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_batch) {
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_vocab = hparams.n_vocab;
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_ff = get_n_ff(&hparams);
struct ggml_tensor * tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N*n_batch);
memcpy(tokens->data, tokens_input->data, ggml_element_size(tokens)*N*n_batch);
struct ggml_tensor * kc = kv_self.k;
struct ggml_tensor * vc = kv_self.v;
// inpL shape [n_embd,N*n_batch,1]
struct ggml_tensor * inpL = ggml_get_rows(ctx0, model->tok_embeddings, tokens);
assert_shape_2d(inpL, n_embd, N*n_batch);
for (int il = 0; il < n_layer; ++il) {
struct ggml_tensor * inpSA = inpL;
struct ggml_tensor * cur;
// lctx.use_buf(ctx0, 0);
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpL);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = attention_norm*cur
cur = ggml_mul(ctx0,
ggml_repeat(ctx0, model->layers[il].attention_norm, cur),
cur);
assert_shape_2d(cur, n_embd, N*n_batch);
}
// 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, n_batch]
// Kcur shape [n_embd/n_head, n_head, N, n_batch]
struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N, n_batch), n_past, n_rot, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N, n_batch), n_past, n_rot, 0);
assert_shape_4d(Qcur, n_embd/n_head, n_head, N, n_batch);
assert_shape_4d(Kcur, n_embd/n_head, n_head, N, n_batch);
// 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, n_embd, n_batch, 1]
struct ggml_tensor * Vcur = ggml_cont(ctx0,
ggml_permute(ctx0,
ggml_reshape_3d(ctx0,
ggml_mul_mat(ctx0,
model->layers[il].wv,
cur),
n_embd, N, n_batch),
1, 0, 2, 3));
assert_shape_3d(Vcur, N, n_embd, n_batch);
// kv_self.k shape [n_embd * n_ctx * n_batch * n_layer]
// kv_self.v shape [n_ctx * n_embd * n_batch * n_layer]
// k shape [n_embd * N, n_batch] == kv_self.k[:,n_past:n_past+N,:,il]
// v shape [N, n_embd, n_batch, 1] == kv_self.v[:,n_past:n_past+N,:,il]
/* {
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_2d(ctx0, kc,
ggml_reshape_2d(ctx0, Kcur, n_embd*N, n_batch),
ggml_element_size(kc)*n_embd*n_ctx,
(ggml_element_size(kc)*n_embd)*(il*n_batch*n_ctx + n_past));
vc = ggml_set_2d(ctx0, vc,
ggml_reshape_2d(ctx0, Vcur, N*n_embd, n_batch),
ggml_element_size(vc)*n_ctx*n_embd,
ggml_element_size(vc)*(n_past + il*n_embd*n_batch*n_ctx));
assert_shape_1d(kc, n_embd * n_ctx * n_batch * n_layer);
assert_shape_1d(vc, n_embd * n_ctx * n_batch * n_layer);
}
// Qcur shape [n_embd/n_head, n_head, N, n_batch]
// Q shape [n_embd/n_head, N, n_head, n_batch]
struct ggml_tensor * Q =
ggml_permute(ctx0,
Qcur,
0, 2, 1, 3);
assert_shape_4d(Q, n_embd/n_head, N, n_head, n_batch);
// kv_self.k shape [n_embd * n_ctx * n_batch * n_layer]
// K shape [n_embd/n_head, n_past + N, n_head, n_batch]
struct ggml_tensor * K =
ggml_permute(ctx0,
ggml_reshape_4d(ctx0,
ggml_view_3d(ctx0,
kc,
n_embd,
(n_past + N),
n_batch,
n_embd*ggml_element_size(kc),
n_ctx*n_embd*ggml_element_size(kc),
il*n_batch*n_ctx*n_embd*ggml_element_size(kc)),
n_embd/n_head, n_head, n_past + N, n_batch),
0, 2, 1, 3);
assert_shape_4d(K, n_embd/n_head, n_past + N, n_head, n_batch);
// K * Q
// KQ shape [n_past + N, N, n_head, n_batch]
struct ggml_tensor * KQ = ggml_mul_mat(ctx0, K, Q);
assert_shape_4d(KQ, n_past + N, N, n_head, n_batch);
// KQ_scaled = KQ / sqrt(n_embd/n_head)
// KQ_scaled shape [n_past + N, N, n_head, n_batch]
struct ggml_tensor * KQ_scaled =
ggml_scale(ctx0,
KQ,
ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head)));
assert_shape_4d(KQ_scaled, n_past + N, N, n_head, n_batch);
// KQ_masked = mask_past(KQ_scaled)
// KQ_masked shape [n_past + N, N, n_head, n_batch]
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
assert_shape_4d(KQ_masked, n_past + N, N, n_head, n_batch);
// KQ = soft_max(KQ_masked)
// KQ_soft_max shape [n_past + N, N, n_head, n_batch]
struct ggml_tensor * KQ_soft_max = ggml_soft_max(ctx0, KQ_masked);
assert_shape_4d(KQ_soft_max, n_past + N, N, n_head, n_batch);
// split cached V into n_head heads
// kv_self.v shape [n_ctx * n_embd * n_batch * n_layer]
// V shape [n_past + N, n_embd/n_head, n_head, n_batch] == kv_self.v[:(n_past+N),:,:,il]
struct ggml_tensor * V =
ggml_view_4d(ctx0, vc,
n_past + N, n_embd/n_head, n_head, n_batch,
ggml_element_size(vc)*n_ctx,
ggml_element_size(vc)*n_ctx*n_embd/n_head,
ggml_element_size(vc)*n_ctx*n_embd,
il*n_batch*n_ctx*n_embd*ggml_element_size(vc));
assert_shape_4d(V, n_past + N, n_embd/n_head, n_head, n_batch);
// KQV shape [n_embd/n_head, N, n_head, n_batch]
struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V, KQ_soft_max);
assert_shape_4d(KQV, n_embd/n_head, N, n_head, n_batch);
// KQV_merged = KQV.permute(0, 2, 1, 3)
// KQV_merged shape [n_embd/n_head, n_head, N, n_batch]
struct ggml_tensor * KQV_merged = ggml_permute(ctx0, KQV, 0, 2, 1, 3);
assert_shape_4d(KQV_merged, n_embd/n_head, n_head, N, n_batch);
// KQV_merged shape
// cur = KQV_merged.contiguous().view(n_embd, N)
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_reshape_2d(ctx0, ggml_cont(ctx0, KQV_merged), n_embd, N*n_batch);
assert_shape_2d(cur, n_embd, N*n_batch);
// 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*n_batch,1,1]
cur = ggml_mul_mat(ctx0,
model->layers[il].wo,
cur);
assert_shape_2d(cur, n_embd, N*n_batch);
}
// lctx.use_buf(ctx0, 1);
// inpFF shape [n_embd,N*n_batch,1,1]
struct ggml_tensor * inpFF = ggml_add(ctx0, cur, inpSA);
assert_shape_2d(inpFF, n_embd, N*n_batch);
// feed-forward network
{
// norm
{
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_rms_norm(ctx0, inpFF);
assert_shape_2d(cur, n_embd, N*n_batch);
// cur = ffn_norm*cur
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_mul(ctx0,
ggml_repeat(ctx0, model->layers[il].ffn_norm, cur),
cur);
assert_shape_2d(cur, n_embd, N*n_batch);
}
// tmp shape [n_ff,N*n_batch,1,1]
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
model->layers[il].w3,
cur);
assert_shape_2d(tmp, n_ff, N*n_batch);
// cur shape [n_ff,N*n_batch,1,1]
cur = ggml_mul_mat(ctx0,
model->layers[il].w1,
cur);
assert_shape_2d(cur, n_ff, N*n_batch);
// SILU activation
// cur shape [n_ff,N*n_batch,1,1]
cur = ggml_silu(ctx0, cur);
assert_shape_2d(cur, n_ff, N*n_batch);
// cur shape [n_ff,N*n_batch,1,1]
cur = ggml_mul(ctx0, cur, tmp);
assert_shape_2d(cur, n_ff, N*n_batch);
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_mul_mat(ctx0,
model->layers[il].w2,
cur);
assert_shape_2d(cur, n_embd, N*n_batch);
}
// cur shape [n_embd,N*n_batch,1,1]
cur = ggml_add(ctx0, cur, inpFF);
assert_shape_2d(cur, n_embd, N*n_batch);
// input for next layer
// inpL shape [n_embd,N*n_batch,1,1]
inpL = cur;
assert_shape_2d(inpL, n_embd, N*n_batch);
}
// norm
{
// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_rms_norm(ctx0, inpL);
assert_shape_2d(inpL, n_embd, N*n_batch);
// inpL = norm*inpL
// inpL shape [n_embd,N*n_batch,1,1]
inpL = ggml_mul(ctx0,
ggml_repeat(ctx0, model->norm, inpL),
inpL);
assert_shape_2d(inpL, n_embd, N*n_batch);
//embeddings = inpL;
}
// lm_head
// inpL shape [n_vocab,N*n_batch,1,1]
inpL = ggml_mul_mat(ctx0, model->output, inpL);
assert_shape_2d(inpL, n_vocab, N*n_batch);
{
// inpL shape [n_vocab,N,n_batch,1]
inpL = ggml_reshape_3d(ctx0,
inpL,
n_vocab, N, n_batch);
assert_shape_3d(inpL, n_vocab, N, n_batch);
}
// run the computation
ggml_build_forward_expand(gf, inpL);
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;
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);
assert(best_samples->n_dims == 1);
assert(logits->ne[1] == best_samples->ne[0]);
assert(logits->ne[0] == probs->ne[0]);
assert(logits->ne[1] == probs->ne[1]);
for (int i = 0; i < logits->ne[1]; ++i) {
float max_logit = ggml_get_f32_1d(logits, i * logits->ne[0]);
ggml_set_i32_1d(best_samples, i, 0);
for (int k = 0; k < logits->ne[0]; ++k) {
float logit = ggml_get_f32_1d(logits, i * logits->ne[0] + k);
if (logit > max_logit) {
max_logit = logit;
ggml_set_i32_1d(best_samples, i, k);
}
}
float psum = 0;
for (int k = 0; k < logits->ne[0]; ++k) {
float logit = ggml_get_f32_1d(logits, i * logits->ne[0] + k);
float p = (logit == -INFINITY) ? 0 : expf(logit - max_logit);
psum += p;
ggml_set_f32_1d(probs, i * probs->ne[0] + k, p);
}
for (int k = 0; k < logits->ne[0]; ++k) {
float p = ggml_get_f32_1d(probs, i*probs->ne[0] + k);
ggml_set_f32_1d(probs, i * probs->ne[0] + k, p / psum);
}
}
}
void sample_softmax_batch(struct ggml_context * ctx, struct ggml_tensor * logits, struct ggml_tensor * probs, struct ggml_tensor * best_samples) {
GGML_ASSERT(best_samples->n_dims == 2);
GGML_ASSERT(logits->n_dims == 3);
GGML_ASSERT(probs->n_dims == 3);
int n_tokens = best_samples->ne[0];
int n_batch = best_samples->ne[1];
int n_vocab = logits->ne[0];
GGML_ASSERT(n_tokens == logits->ne[1]);
GGML_ASSERT(n_batch == logits->ne[2]);
GGML_ASSERT(n_vocab == probs->ne[0]);
GGML_ASSERT(n_tokens == probs->ne[1]);
GGML_ASSERT(n_batch == probs->ne[2]);
for (int k = 0; k < n_batch; ++k) {
struct ggml_tensor * best_samples_k = ggml_view_1d(ctx,
best_samples,
best_samples->ne[0],
k*best_samples->nb[1]);
struct ggml_tensor * logits_k = ggml_view_2d(ctx,
logits,
logits->ne[0],
logits->ne[1],
logits->nb[1],
k*logits->nb[2]);
struct ggml_tensor * probs_k = ggml_view_2d(ctx,
probs,
probs->ne[0],
probs->ne[1],
probs->nb[1],
k*probs->nb[2]);
sample_softmax(logits_k, probs_k, best_samples_k);
}
}
void print_row(struct ggml_tensor * probs, int i) {
for (int k = 0; k < probs->ne[0]; ++k) {
float p = ggml_get_f32_1d(probs, i*probs->ne[0] + k);
printf(" %.2f", p);
}
printf("\n");
}
void print_matrix(struct ggml_tensor * probs) {
assert(probs->n_dims == 2);
for (int i = 0; i < probs->ne[1]; ++i) {
for (int k = 0; k < probs->ne[0]; ++k) {
float p = ggml_get_f32_1d(probs, i*probs->ne[0] + k);
printf(" %.2f", p);
}
printf("\n");
}
}
void print_token(int token, int n_vocab) {
for (int k = 0; k < token; ++k) {
printf(" ");
}
printf("X");
for (int k = token+1; k < n_vocab; ++k) {
printf(" ");
}
printf("\n");
}
void print_tokens(struct ggml_tensor * tokens, int n_vocab) {
for (int i=0; i<tokens->ne[0]; ++i) {
int token = ggml_get_i32_1d(tokens, i);
print_token(token, n_vocab);
}
}
void get_example_targets(int example_id, struct ggml_tensor * tokens_input, struct ggml_tensor * targets) {
int n_tokens = tokens_input->ne[0];
int n_vocab = targets->ne[0];
float randomness = 0.0f;
// ggml_set_zero(targets);
ggml_set_f32(targets, -1.0f);
ggml_set_i32_1d(tokens_input, 0, 0);
for (int i=1; i<n_tokens+1; ++i) {
float x = example_id + i * 3.14159f * 2.0f * 1.0f * 0.5f / n_tokens;
float y = sinf(x);//*cosf(x*1.1f+1.0f);
float z = (y+1.0f)*0.5f; // scale to [0..1]
z += (frand()-0.5f)*(randomness/n_vocab);
z = (z < 0.0f) ? 0.0f : (z > 1.0f) ? 1.0f : z; // clamp to [0..1]
int token = std::max(1,std::min(1+(int)(z*(float)(n_vocab-1)), n_vocab-1));
ggml_set_f32_1d(targets, (i-1)*n_vocab + token, +1.0f);
if (i<n_tokens) {
ggml_set_i32_1d(tokens_input, i, token);
}
}
}
void get_example_targets_batch(struct ggml_context * ctx, int example_id, struct ggml_tensor * tokens_input, struct ggml_tensor * targets) {
GGML_ASSERT(tokens_input->n_dims == 2);
GGML_ASSERT( targets->n_dims == 3);
int n_tokens = tokens_input->ne[0];
int n_batch = tokens_input->ne[1];
GGML_ASSERT(n_tokens == targets->ne[1]);
GGML_ASSERT(n_batch == targets->ne[2]);
for (int k=0; k<n_batch; ++k) {
struct ggml_tensor * tokens_input_k = ggml_view_1d(ctx,
tokens_input,
tokens_input->ne[0],
k*tokens_input->nb[1]);
struct ggml_tensor * targets_k = ggml_view_2d(ctx,
targets,
targets->ne[0],
targets->ne[1],
targets->nb[1],
k*targets->nb[2]);
get_example_targets(example_id*n_batch + k, tokens_input_k, targets_k);
}
}
void lshift_examples(struct ggml_tensor * tokens_input, struct ggml_tensor * targets, int n_shift) {
int n_tokens = tokens_input->ne[0];
int n_vocab = targets->ne[0];
for (int i=0; i<n_tokens-n_shift; ++i) {
ggml_set_i32_1d(tokens_input, i, ggml_get_i32_1d(tokens_input, i + n_shift));
for (int k=0; k<n_vocab; ++k) {
ggml_set_f32_1d(targets, i*n_vocab + k, ggml_get_f32_1d(targets, (i + n_shift)*n_vocab + k));
}
}
}
struct ggml_tensor * square_error_loss(struct ggml_context * ctx, struct ggml_tensor * a, struct ggml_tensor * b) {
// todo: instead of a-b: a[1:]-b[:-1]
return ggml_sum(ctx, ggml_sqr(ctx, ggml_sub(ctx, a, b)));
}
struct ggml_tensor * cross_entropy_loss(struct ggml_context * ctx, struct ggml_tensor * a, struct ggml_tensor * b) {
const float eps = 1e-3;
return
ggml_sum(ctx,
ggml_neg(ctx,
ggml_sum_rows(ctx,
ggml_mul(ctx,
ggml_soft_max(ctx, a),
ggml_log(ctx,
ggml_add1(ctx,
ggml_soft_max(ctx, b),
ggml_new_f32(ctx, eps)))))));
}
int main(int argc, char ** argv) {
if (argc < 1) {
fprintf(stderr, "usage: %s\n", argv[0]);
return 1;
}
struct ggml_init_params lcparams;
lcparams.mem_size = 1024ll*1024ll*1024ll;
lcparams.mem_buffer = NULL;
lcparams.no_alloc = false;
struct llama_model model;
model.hparams.n_vocab = 8;
model.hparams.n_ctx = 8;
model.hparams.n_embd = 32;
model.hparams.n_mult = 2;
model.hparams.n_head = 8;
model.hparams.n_layer = 1;
model.hparams.n_rot = std::min(16u, model.hparams.n_embd / model.hparams.n_head);
// 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.ctx = ggml_init(lcparams);
printf("init model\n");
init_model(&model);
set_param_model(&model);
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);
*/
int n_batch = 8;
// 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, n_batch);
//init_kv_cache_lora(&kv_self, &model_lora);
size_t compute_size = 1024ll*1024ll*1024ll;
uint8_t * compute_addr = new uint8_t[compute_size];
int n_examples = 256;
int n_tokens = model.hparams.n_ctx;
int n_vocab = model.hparams.n_vocab;
for (int ex=0; ex<n_examples; ++ex) {
struct ggml_init_params params = {
/*.mem_size =*/ compute_size,
/*.mem_buffer =*/ compute_addr,
/*.no_alloc =*/ false,
};
struct ggml_context * ctx0 = ggml_init(params);
struct ggml_tensor * after_opt_best_samples = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_tokens, n_batch);
struct ggml_tensor * after_opt_probs = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_vocab, n_tokens, n_batch);
struct ggml_tensor * tokens_input = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_tokens, n_batch);
struct ggml_tensor * targets = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_vocab, n_tokens, n_batch);
int n_past = 0;
ggml_cgraph gf = {};
gf.n_threads = 1;
get_example_targets_batch(ctx0, 64*ex+0, tokens_input, targets);
struct ggml_tensor * logits = forward_batch(&model, &kv_self, ctx0, &gf, tokens_input, n_tokens, n_past, n_batch);
// struct ggml_tensor * e = cross_entropy_loss(ctx0, targets, logits);
struct ggml_tensor * e = square_error_loss(ctx0, targets, logits);
ggml_build_forward_expand(&gf, e);
ggml_graph_compute(ctx0, &gf);
float error_before_opt = ggml_get_f32_1d(e, 0);
struct ggml_opt_params opt_params_adam = ggml_opt_default_params(GGML_OPT_ADAM);
struct ggml_opt_params opt_params_lbfgs = ggml_opt_default_params(GGML_OPT_LBFGS);
opt_params_adam.print_forward_graph = false;
opt_params_adam.print_backward_graph = false;
opt_params_lbfgs.print_forward_graph = false;
opt_params_lbfgs.print_backward_graph = false;
opt_params_adam.adam.n_iter = 16;
opt_params_lbfgs.lbfgs.n_iter = 16;
// ggml_opt(ctx0, opt_params_adam, e);
ggml_opt(ctx0, opt_params_lbfgs, e);
//
ggml_build_forward_expand(&gf, e);
ggml_graph_compute(ctx0, &gf);
float error_after_opt = ggml_get_f32_1d(e, 0);
if (ex % 8 == 0) {
printf("Example %d\n", (ex+1));
printf("error_before_opt: %.2f\n", error_before_opt);
printf("error_after_opt: %.2f\n", error_after_opt);
}
if (ex % 64 == 0) {
sample_softmax_batch(ctx0, logits, after_opt_probs, after_opt_best_samples);
// printf("probabilities after optimization:\n");
// print_matrix(after_opt_probs);
printf("best samples after optimization:\n");
print_tokens(after_opt_best_samples, n_vocab);
}
ggml_free(ctx0);
}
{
int n_gen = 128;
int sample_ctx = n_tokens-n_tokens/8;
printf("Generating %d tokens.\n", n_gen);
struct ggml_tensor * tokens_input = ggml_new_tensor_1d(model.ctx, GGML_TYPE_I32, n_tokens);
struct ggml_tensor * targets = ggml_new_tensor_2d(model.ctx, GGML_TYPE_F32, n_vocab, n_tokens);
get_example_targets(137, tokens_input, targets);
for (int i=sample_ctx; i<n_tokens; ++i) {
ggml_set_i32_1d(tokens_input, i, n_vocab/2);
}
for (int i=0; i<sample_ctx-1; ++i) {
print_token(ggml_get_i32_1d(tokens_input, i), n_vocab);
}
printf("---\n");
for (int i=0; i<n_gen; ++i) {
struct ggml_init_params params = {
/*.mem_size =*/ compute_size,
/*.mem_buffer =*/ compute_addr,
/*.no_alloc =*/ false,
};
struct ggml_context * ctx0 = ggml_init(params);
ggml_cgraph gf = {};
gf.n_threads = 1;
int n_past = 0;
struct ggml_tensor * logits = forward(&model, &kv_self, ctx0, &gf, tokens_input, sample_ctx, n_past);
ggml_build_forward_expand(&gf, logits);
ggml_graph_compute(ctx0, &gf);
struct ggml_tensor * best_samples = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, sample_ctx);
struct ggml_tensor * probs = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_vocab, sample_ctx);
sample_softmax(logits, probs, best_samples);
// int sample_at = n_tokens-1;
int token = ggml_get_i32_1d(best_samples, sample_ctx-1);
// print_row(probs, sample_at);
print_token(token, n_vocab);
lshift_examples(tokens_input, targets, 1);
ggml_set_i32_1d(tokens_input, 0, 0);
ggml_set_i32_1d(tokens_input, sample_ctx-1, token);
ggml_free(ctx0);
}
}
print_matrix(model.tok_embeddings);
printf("done\n");
// ggml_free(kv_self.ctx);
// ggml_free(model_lora.ctx);
ggml_free(model.ctx);
return 0;
}
Reference in a new issue View git blame Copy permalink