gpt2 : Add gpt2 architecture integration (#4555)
This commit is contained in:
manikbhandari
GitHub
parent
f6793491b5
commit
ea5497df5d
7 changed files with 281 additions and 14 deletions
206
llama.cpp
206
llama.cpp
|
|
@ -423,6 +423,15 @@ static std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NAMES =
|
|||
LLM_ARCH_GPT2,
|
||||
{
|
||||
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
||||
{ LLM_TENSOR_POS_EMBD, "position_embd" },
|
||||
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
|
||||
{ LLM_TENSOR_OUTPUT, "output" },
|
||||
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
|
||||
{ LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" },
|
||||
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
|
||||
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
|
||||
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
|
||||
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
|
||||
},
|
||||
},
|
||||
{
|
||||
|
|
@ -1256,6 +1265,10 @@ enum e_model {
|
|||
MODEL_40B,
|
||||
MODEL_65B,
|
||||
MODEL_70B,
|
||||
MODEL_SMALL,
|
||||
MODEL_MEDIUM,
|
||||
MODEL_LARGE,
|
||||
MODEL_XL,
|
||||
};
|
||||
|
||||
static const size_t kiB = 1024;
|
||||
|
|
@ -2552,18 +2565,22 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
|
|||
|
||||
static const char * llama_model_type_name(e_model type) {
|
||||
switch (type) {
|
||||
case MODEL_1B: return "1B";
|
||||
case MODEL_3B: return "3B";
|
||||
case MODEL_7B: return "7B";
|
||||
case MODEL_8B: return "8B";
|
||||
case MODEL_13B: return "13B";
|
||||
case MODEL_15B: return "15B";
|
||||
case MODEL_30B: return "30B";
|
||||
case MODEL_34B: return "34B";
|
||||
case MODEL_40B: return "40B";
|
||||
case MODEL_65B: return "65B";
|
||||
case MODEL_70B: return "70B";
|
||||
default: return "?B";
|
||||
case MODEL_1B: return "1B";
|
||||
case MODEL_3B: return "3B";
|
||||
case MODEL_7B: return "7B";
|
||||
case MODEL_8B: return "8B";
|
||||
case MODEL_13B: return "13B";
|
||||
case MODEL_15B: return "15B";
|
||||
case MODEL_30B: return "30B";
|
||||
case MODEL_34B: return "34B";
|
||||
case MODEL_40B: return "40B";
|
||||
case MODEL_65B: return "65B";
|
||||
case MODEL_70B: return "70B";
|
||||
case MODEL_SMALL: return "0.1B";
|
||||
case MODEL_MEDIUM: return "0.4B";
|
||||
case MODEL_LARGE: return "0.8B";
|
||||
case MODEL_XL: return "1.5B";
|
||||
default: return "?B";
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -2782,6 +2799,17 @@ static void llm_load_hparams(
|
|||
default: model.type = e_model::MODEL_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_GPT2:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
|
||||
switch (hparams.n_layer) {
|
||||
case 12: model.type = e_model::MODEL_SMALL; break;
|
||||
case 24: model.type = e_model::MODEL_MEDIUM; break;
|
||||
case 36: model.type = e_model::MODEL_LARGE; break;
|
||||
case 48: model.type = e_model::MODEL_XL; break;
|
||||
default: model.type = e_model::MODEL_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
|
||||
default: (void)0;
|
||||
}
|
||||
|
|
@ -3710,6 +3738,60 @@ static bool llm_load_tensors(
|
|||
layer.ffn_up = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, backend_split);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_GPT2:
|
||||
{
|
||||
model.tok_embd = ml.create_tensor(ctx, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, GGML_BACKEND_CPU);
|
||||
model.pos_embd = ml.create_tensor(ctx, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}, GGML_BACKEND_CPU);
|
||||
|
||||
// output
|
||||
{
|
||||
ggml_backend_type backend_norm;
|
||||
ggml_backend_type backend_output;
|
||||
|
||||
if (n_gpu_layers > int(n_layer)) {
|
||||
backend_norm = llama_backend_offload;
|
||||
backend_output = llama_backend_offload_split;
|
||||
} else {
|
||||
backend_norm = GGML_BACKEND_CPU;
|
||||
backend_output = GGML_BACKEND_CPU;
|
||||
}
|
||||
|
||||
model.output_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, backend_norm);
|
||||
model.output_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, backend_norm);
|
||||
model.output = ml.create_tensor(ctx, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, backend_output);
|
||||
}
|
||||
|
||||
const uint32_t n_ff = hparams.n_ff;
|
||||
|
||||
const int i_gpu_start = n_layer - n_gpu_layers;
|
||||
|
||||
model.layers.resize(n_layer);
|
||||
|
||||
for (uint32_t i = 0; i < n_layer; ++i) {
|
||||
const ggml_backend_type backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : llama_backend_offload; // NOLINT
|
||||
const ggml_backend_type backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : llama_backend_offload_split; // NOLINT
|
||||
|
||||
auto & layer = model.layers[i];
|
||||
|
||||
layer.attn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, backend);
|
||||
layer.attn_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}, backend);
|
||||
|
||||
layer.wqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, backend_split);
|
||||
layer.bqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, backend);
|
||||
|
||||
layer.wo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, backend_split);
|
||||
layer.bo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, backend);
|
||||
|
||||
layer.ffn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, backend);
|
||||
layer.ffn_norm_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}, backend);
|
||||
|
||||
layer.ffn_down = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, backend_split);
|
||||
layer.ffn_down_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, backend);
|
||||
|
||||
layer.ffn_up = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, backend_split);
|
||||
layer.ffn_up_b = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, backend);
|
||||
}
|
||||
} break;
|
||||
default:
|
||||
throw std::runtime_error("unknown architecture");
|
||||
}
|
||||
|
|
@ -5754,6 +5836,102 @@ struct llm_build_context {
|
|||
|
||||
return gf;
|
||||
}
|
||||
|
||||
struct ggml_cgraph * build_gpt2() {
|
||||
struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false);
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
struct ggml_tensor * pos;
|
||||
struct ggml_tensor * inpL;
|
||||
|
||||
inpL = llm_build_inp_embd(ctx0, hparams, batch, model.tok_embd, cb);
|
||||
cb(inpL, "inp_embd", -1);
|
||||
|
||||
// inp_pos - contains the positions
|
||||
struct ggml_tensor * inp_pos = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
|
||||
cb(inp_pos, "inp_pos", -1);
|
||||
|
||||
// KQ_mask (mask for 1 head, it will be broadcasted to all heads)
|
||||
struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, n_tokens, 1);
|
||||
cb(KQ_mask, "KQ_mask", -1);
|
||||
|
||||
pos = ggml_get_rows(ctx0, model.pos_embd, inp_pos);
|
||||
cb(pos, "pos_embd", -1);
|
||||
|
||||
inpL = ggml_add(ctx0, inpL, pos);
|
||||
cb(inpL, "inpL", -1);
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
cur = llm_build_norm(ctx0, inpL, hparams,
|
||||
model.layers[il].attn_norm,
|
||||
model.layers[il].attn_norm_b,
|
||||
LLM_NORM, cb, il);
|
||||
cb(cur, "attn_norm", il);
|
||||
|
||||
// self-attention
|
||||
{
|
||||
cur = ggml_mul_mat(ctx0, model.layers[il].wqkv, cur);
|
||||
cb(cur, "wqkv", il);
|
||||
|
||||
cur = ggml_add(ctx0, cur, model.layers[il].bqkv);
|
||||
cb(cur, "bqkv", il);
|
||||
|
||||
struct ggml_tensor * Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd, n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
|
||||
struct ggml_tensor * Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
|
||||
struct ggml_tensor * Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
|
||||
|
||||
cb(Qcur, "Qcur", il);
|
||||
cb(Kcur, "Kcur", il);
|
||||
cb(Vcur, "Vcur", il);
|
||||
|
||||
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
|
||||
|
||||
llm_build_kv_store(ctx0, hparams, kv_self, gf, Kcur, Vcur, n_ctx, n_tokens, kv_head, cb, il);
|
||||
|
||||
cur = llm_build_kqv(ctx0, model, hparams, kv_self,
|
||||
model.layers[il].wo, model.layers[il].bo,
|
||||
Qcur, KQ_mask, n_ctx, n_tokens, n_kv, -1.0f, 1.0f/sqrtf(float(n_embd_head)), cb, il);
|
||||
cb(cur, "kqv_out", il);
|
||||
}
|
||||
|
||||
// add the input
|
||||
struct ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpL);
|
||||
cb(ffn_inp, "ffn_inp", il);
|
||||
|
||||
// FF
|
||||
{
|
||||
cur = llm_build_norm(ctx0, ffn_inp, hparams,
|
||||
model.layers[il].ffn_norm,
|
||||
model.layers[il].ffn_norm_b,
|
||||
LLM_NORM, cb, il);
|
||||
cb(cur, "ffn_norm", il);
|
||||
|
||||
cur = llm_build_ffn(ctx0, cur,
|
||||
model.layers[il].ffn_up, model.layers[il].ffn_up_b,
|
||||
NULL, NULL,
|
||||
model.layers[il].ffn_down, model.layers[il].ffn_down_b,
|
||||
NULL,
|
||||
LLM_FFN_GELU, LLM_FFN_SEQ, cb, il);
|
||||
cb(cur, "ffn_out", il);
|
||||
}
|
||||
|
||||
inpL = ggml_add(ctx0, cur, ffn_inp);
|
||||
cb(inpL, "l_out", il);
|
||||
}
|
||||
|
||||
cur = llm_build_norm(ctx0, inpL, hparams,
|
||||
model.output_norm,
|
||||
model.output_norm_b,
|
||||
LLM_NORM, cb, -1);
|
||||
cb(cur, "result_norm", -1);
|
||||
|
||||
cur = ggml_mul_mat(ctx0, model.output, cur);
|
||||
cb(cur, "result_output", -1);
|
||||
|
||||
ggml_build_forward_expand(gf, cur);
|
||||
|
||||
return gf;
|
||||
}
|
||||
};
|
||||
|
||||
//
|
||||
|
|
@ -6269,6 +6447,10 @@ static struct ggml_cgraph * llama_build_graph(
|
|||
{
|
||||
result = llm.build_plamo();
|
||||
} break;
|
||||
case LLM_ARCH_GPT2:
|
||||
{
|
||||
result = llm.build_gpt2();
|
||||
} break;
|
||||
default:
|
||||
GGML_ASSERT(false);
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue