Fabio
c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
100 lines
2.7 KiB
C++
100 lines
2.7 KiB
C++
#pragma once
|
|
|
|
#include "engine/framework/assets/resource_bundle.h"
|
|
#include "engine/framework/assets/tensor_source.h"
|
|
|
|
#include <cstdint>
|
|
#include <filesystem>
|
|
#include <memory>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
namespace engine::community_models::voxcpm1 {
|
|
|
|
struct VoxCPM1RopeScalingConfig {
|
|
std::string type;
|
|
std::vector<float> long_factor;
|
|
std::vector<float> short_factor;
|
|
int64_t original_max_position_embeddings = 0;
|
|
};
|
|
|
|
struct VoxCPM1MiniCPMConfig {
|
|
int64_t bos_token_id = 1;
|
|
int64_t eos_token_id = 2;
|
|
int64_t hidden_size = 0;
|
|
int64_t intermediate_size = 0;
|
|
int64_t max_position_embeddings = 0;
|
|
int64_t num_attention_heads = 0;
|
|
int64_t num_hidden_layers = 0;
|
|
int64_t num_key_value_heads = 0;
|
|
int64_t kv_channels = 0;
|
|
int64_t vocab_size = 0;
|
|
int64_t scale_emb = 1;
|
|
int64_t dim_model_base = 0;
|
|
float rms_norm_eps = 1.0e-5F;
|
|
float rope_theta = 10000.0F;
|
|
float scale_depth = 1.0F;
|
|
bool use_mup = false;
|
|
bool no_rope = false;
|
|
VoxCPM1RopeScalingConfig rope_scaling;
|
|
};
|
|
|
|
struct VoxCPM1LocalTransformerConfig {
|
|
int64_t hidden_dim = 0;
|
|
int64_t ffn_dim = 0;
|
|
int64_t num_heads = 0;
|
|
int64_t num_layers = 0;
|
|
int64_t kv_channels = 0;
|
|
};
|
|
|
|
struct VoxCPM1CFMConfig {
|
|
float sigma_min = 1.0e-6F;
|
|
std::string solver = "euler";
|
|
std::string t_scheduler = "log-norm";
|
|
float inference_cfg_rate = 2.0F;
|
|
};
|
|
|
|
struct VoxCPM1DiTConfig : VoxCPM1LocalTransformerConfig {
|
|
bool mean_mode = false;
|
|
VoxCPM1CFMConfig cfm;
|
|
};
|
|
|
|
struct VoxCPM1AudioVAEConfig {
|
|
int64_t encoder_dim = 0;
|
|
std::vector<int64_t> encoder_rates;
|
|
int64_t latent_dim = 0;
|
|
int64_t decoder_dim = 0;
|
|
std::vector<int64_t> decoder_rates;
|
|
std::vector<int64_t> sample_rate_bin_boundaries;
|
|
int sample_rate = 0;
|
|
int output_sample_rate = 0;
|
|
};
|
|
|
|
struct VoxCPM1Config {
|
|
std::string architecture;
|
|
VoxCPM1MiniCPMConfig lm;
|
|
int64_t patch_size = 4;
|
|
int64_t feat_dim = 64;
|
|
int64_t residual_lm_num_layers = 8;
|
|
bool residual_lm_no_rope = false;
|
|
int64_t scalar_quantization_latent_dim = 512;
|
|
int64_t scalar_quantization_scale = 9;
|
|
VoxCPM1LocalTransformerConfig encoder;
|
|
VoxCPM1DiTConfig dit;
|
|
VoxCPM1AudioVAEConfig audio_vae;
|
|
int64_t max_length = 8192;
|
|
std::string device = "cuda";
|
|
std::string dtype = "bfloat16";
|
|
bool v1 = false;
|
|
};
|
|
|
|
struct VoxCPM1Assets {
|
|
assets::ResourceBundle resources;
|
|
VoxCPM1Config config;
|
|
std::shared_ptr<const assets::TensorSource> model_weights;
|
|
std::shared_ptr<const assets::TensorSource> audiovae_weights;
|
|
};
|
|
|
|
std::shared_ptr<const VoxCPM1Assets> load_voxcpm1_assets(const std::filesystem::path & model_path);
|
|
|
|
} // namespace engine::community_models::voxcpm1
|