Skip to content

issue/417 - GLM4 and ChatGLM use layers::attention #418

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pengcheng888 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

issue/417 - GLM4 and ChatGLM use layers::attention #418

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions csrc/models/chatglm/chatglm_for_causal_lm.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,13 @@
#pragma once

#include "../../layers/common_modules.hpp"
#include "../glm4/glm4_attention.hpp"
#include <memory>

namespace infinilm::models::chatglm {

using ChatglmMLP = infinilm::layers::MLP;

// Reuse Glm4Attention as ChatGLM and GLM4 share the identical attention layer
using ChatglmAttention = infinilm::models::glm4::Glm4Attention;
using ChatglmAttention = infinilm::layers::attention::Attention;

using ChatglmDecoderLayer = infinilm::layers::causal_lm_templates::TextDecoderLayer<ChatglmAttention, ChatglmMLP>;

Expand Down
183 changes: 0 additions & 183 deletions csrc/models/glm4/glm4_attention.cpp
View file
Open in desktop

This file was deleted.

50 changes: 0 additions & 50 deletions csrc/models/glm4/glm4_attention.hpp
View file
Open in desktop

This file was deleted.

5 changes: 3 additions & 2 deletions csrc/models/glm4/glm4_decoder_layer.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,14 @@
#include "../../backends/attention_backends.hpp"
#include "../../config/model_config.hpp"
#include "../../engine/distributed/distributed.hpp"
#include "../../layers/mlp/mlp.hpp"
#include "glm4_attention.hpp"
#include "../../layers/common_modules.hpp"
#include "infinicore/nn/module.hpp"
#include "infinicore/nn/rmsnorm.hpp"

namespace infinilm::models::glm4 {

using Glm4Attention = infinilm::layers::attention::Attention;

class Glm4DecoderLayer : public infinicore::nn::Module {
public:
Glm4DecoderLayer(std::shared_ptr<infinilm::config::ModelConfig> model_config,
Expand Down