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

llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)

Browse source 
* add glm edge chat model

* use config partial_rotary_factor as rope ratio

* support for glm edge model

* vision model support

* remove debug info

* fix format

* llava.cpp trailing whitespace

* remove unused AutoTokenizer

* Update src/llama.cpp for not contain <|end|> or </s>

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* add edge template

* fix chat template

* fix confict

* fix confict

* fix ci err

* fix format err

* fix template err

* 9b hf chat support

* format

* format clip.cpp

* fix format

* Apply suggestions from code review

* Apply suggestions from code review

* Update examples/llava/clip.cpp

* fix format

* minor : style

---------

Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
piDack 2025-02-02 15:48:46 +08:00 • committed by GitHub
parent 53debe6f3c
commit 0cec062a63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 568 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

28
src/llama-model.cpp
View file

@ -1093,8 +1093,20 @@ void llama_model::load_hparams(llama_model_loader & ml) {
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 28: type = LLM_TYPE_6B; break;
case 40: type = LLM_TYPE_9B; break;
case 28: {
if (hparams.n_head(0) == 16) {
type = LLM_TYPE_1_5B;
} else {
type = LLM_TYPE_6B;
}
} break;
case 40: {
if (hparams.n_head(0) == 24) {
type = LLM_TYPE_4B;
} else {
type = LLM_TYPE_9B;
}
} break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
@ -3068,9 +3080,17 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
auto & layer = layers[i];
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.bqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, 0);
layer.bqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, 0);
if (layer.wqkv == nullptr) {
layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa}, 0);
layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_v_gqa}, 0);
layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
}
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);