vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

k_quants tuning for Falcon-7b

Browse source
This commit is contained in:
Iwan Kawrakow 2023-08-27 11:33:19 +03:00
parent 18a131d5e3
commit 061f777de0
1 changed files with 34 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

37
llama.cpp
View file

@ -4762,7 +4762,10 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
if (name == tn(LLM_TENSOR_OUTPUT, "weight")) { if (name == tn(LLM_TENSOR_OUTPUT, "weight")) {
int nx = tensor->ne[0]; int nx = tensor->ne[0];
if (nx % QK_K == 0) { if (model.arch == LLM_ARCH_FALCON || nx % QK_K != 0) {
new_type = GGML_TYPE_Q8_0;
}
else if (new_type != GGML_TYPE_Q8_0) {
new_type = GGML_TYPE_Q6_K; new_type = GGML_TYPE_Q6_K;
} }
} else if (name.find("attn_v.weight") != std::string::npos) { } else if (name.find("attn_v.weight") != std::string::npos) {
@ -4786,17 +4789,39 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
} else if (name.find("ffn_down.weight") != std::string::npos) { } else if (name.find("ffn_down.weight") != std::string::npos) {
if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K; if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) { else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) {
new_type = i_feed_forward_w2 < 2 ? GGML_TYPE_Q5_K : GGML_TYPE_Q4_K; new_type = i_feed_forward_w2 < 2 ? GGML_TYPE_Q5_K
: model.arch != LLM_ARCH_FALCON || use_more_bits(i_feed_forward_w2, n_feed_forward_w2) ? GGML_TYPE_Q4_K
: GGML_TYPE_Q3_K;
}
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) {
new_type = model.arch == LLM_ARCH_FALCON ? GGML_TYPE_Q4_K : GGML_TYPE_Q5_K;
}
else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M) {
if (model.arch == LLM_ARCH_FALCON) {
new_type = i_feed_forward_w2 < 2 ? GGML_TYPE_Q6_K :
use_more_bits(i_feed_forward_w2, n_feed_forward_w2) ? GGML_TYPE_Q5_K : GGML_TYPE_Q4_K;
} else {
if (use_more_bits(i_feed_forward_w2, n_feed_forward_w2)) new_type = GGML_TYPE_Q6_K;
}
}
else if (ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M && use_more_bits(i_feed_forward_w2, n_feed_forward_w2)) new_type = GGML_TYPE_Q6_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_S && model.arch != LLM_ARCH_FALCON && i_feed_forward_w2 < 4) {
new_type = GGML_TYPE_Q5_K;
} }
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&
use_more_bits(i_feed_forward_w2, n_feed_forward_w2)) new_type = GGML_TYPE_Q6_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_S && i_feed_forward_w2 < 4) new_type = GGML_TYPE_Q5_K;
++i_feed_forward_w2; ++i_feed_forward_w2;
} else if (name.find("attn_output.weight") != std::string::npos) { } else if (name.find("attn_output.weight") != std::string::npos) {
if (model.arch != LLM_ARCH_FALCON) {
if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K ) new_type = GGML_TYPE_Q3_K; if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K ) new_type = GGML_TYPE_Q3_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) new_type = GGML_TYPE_Q4_K; else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M) new_type = GGML_TYPE_Q4_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K; else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
} else {
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q4_K;
}
}
else if (name.find("attn_qkv.weight") != std::string::npos) {
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q4_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M) new_type = GGML_TYPE_Q5_K;
else if (ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) new_type = GGML_TYPE_Q6_K;
} }
else if (name.find("ffn_gate.weight") != std::string::npos || name.find("ffn_up.weight") != std::string::npos) { else if (name.find("ffn_gate.weight") != std::string::npos || name.find("ffn_up.weight") != std::string::npos) {
if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K; if (ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q3_K;