Skip to content
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

Support for Yi-VL and a templating addon/fix for mobileVLM #5093

Merged
merged 5 commits into from
Jan 27, 2024
Merged

Support for Yi-VL and a templating addon/fix for mobileVLM #5093

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8f39716
Support for Yi-VL, templating fix for mobileVLM
cmp-nct Jan 23, 2024
ffcd8e7
ws
cmp-nct Jan 23, 2024
51462f1
Update examples/llava/clip.cpp
cmp-nct Jan 23, 2024
0dbd295
Update llava-cli.cpp
cmp-nct Jan 23, 2024
fccab82
Update clip.cpp
cmp-nct Jan 24, 2024
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
70 changes: 63 additions & 7 deletions examples/llava/clip.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,7 @@ static std::string format(const char * fmt, ...) {

enum projector_type {
PROJECTOR_TYPE_MLP,
PROJECTOR_TYPE_MLP_NORM,
PROJECTOR_TYPE_LDP,
PROJECTOR_TYPE_UNKNOWN,
};
Expand Down Expand Up @@ -303,10 +304,18 @@ struct clip_vision_model {
struct ggml_tensor * projection;

// LLaVA projection
struct ggml_tensor * mm_0_w;
struct ggml_tensor * mm_0_b;
struct ggml_tensor * mm_2_w;
struct ggml_tensor * mm_2_b;
struct ggml_tensor * mm_0_w = NULL;
struct ggml_tensor * mm_0_b = NULL;
struct ggml_tensor * mm_2_w = NULL;
struct ggml_tensor * mm_2_b = NULL;

// Yi type models with mlp+normalization projection
struct ggml_tensor * mm_1_w = NULL; // Yi type models have 0, 1, 3, 4
struct ggml_tensor * mm_1_b = NULL;
struct ggml_tensor * mm_3_w = NULL;
struct ggml_tensor * mm_3_b = NULL;
struct ggml_tensor * mm_4_w = NULL;
struct ggml_tensor * mm_4_b = NULL;

// MobileVLM projection
struct ggml_tensor * mm_model_mlp_1_w;
Expand Down Expand Up @@ -459,6 +468,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
// pre-layernorm
{
embeddings = ggml_norm(ctx0, embeddings, eps);
ggml_set_name(embeddings, "pre_ln");

embeddings = ggml_add(ctx0, ggml_mul(ctx0, embeddings, model.pre_ln_w), model.pre_ln_b);
}
Expand Down Expand Up @@ -574,6 +584,27 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32

embeddings = ggml_mul_mat(ctx0, model.mm_2_w, embeddings);
embeddings = ggml_add(ctx0, embeddings, model.mm_2_b);

} else if (ctx->proj_type == PROJECTOR_TYPE_MLP_NORM) {
embeddings = ggml_mul_mat(ctx0, model.mm_0_w, embeddings);
embeddings = ggml_add(ctx0, embeddings, model.mm_0_b);
// ggml_tensor_printf(embeddings, "mm_0_w",0,true,false);
// First LayerNorm
embeddings = ggml_norm(ctx0, embeddings, eps);
embeddings = ggml_add(ctx0, ggml_mul(ctx0, embeddings, model.mm_1_w),
model.mm_1_b);

// GELU activation
embeddings = ggml_gelu(ctx0, embeddings);

// Second linear layer
embeddings = ggml_mul_mat(ctx0, model.mm_3_w, embeddings);
embeddings = ggml_add(ctx0, embeddings, model.mm_3_b);

// Second LayerNorm
embeddings = ggml_norm(ctx0, embeddings, eps);
embeddings = ggml_add(ctx0, ggml_mul(ctx0, embeddings, model.mm_4_w),
model.mm_4_b);
}
else if (ctx->proj_type == PROJECTOR_TYPE_LDP) {
// MobileVLM projector
Expand Down Expand Up @@ -817,6 +848,11 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
else {
new_clip->proj_type = PROJECTOR_TYPE_MLP;
}
if (new_clip->proj_type == PROJECTOR_TYPE_MLP) {
if (gguf_find_tensor(ctx, format(TN_LLAVA_PROJ, 3, "weight").c_str()) != -1) {
new_clip->proj_type = PROJECTOR_TYPE_MLP_NORM;
}
}
}

#ifdef GGML_USE_CUBLAS
Expand Down Expand Up @@ -965,11 +1001,29 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
vision_model.pre_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "bias"));

// LLaVA projection
if (new_clip->proj_type == PROJECTOR_TYPE_MLP) {
if (new_clip->proj_type == PROJECTOR_TYPE_MLP || new_clip->proj_type == PROJECTOR_TYPE_MLP_NORM) {
vision_model.mm_0_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 0, "weight"));
vision_model.mm_0_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 0, "bias"));
vision_model.mm_2_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "weight"));
vision_model.mm_2_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "bias"));
try {
// Yi-type llava
vision_model.mm_1_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 1, "weight"));
vision_model.mm_1_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 1, "bias"));
} catch (std::runtime_error & e) { }
try {
// missing in Yi-type llava
vision_model.mm_2_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "weight"));
vision_model.mm_2_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 2, "bias"));
} catch (std::runtime_error & e) { }
try {
// Yi-type llava
vision_model.mm_3_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 3, "weight"));
vision_model.mm_3_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 3, "bias"));
} catch (std::runtime_error & e) { }
try {
// Yi-type llava
vision_model.mm_4_w = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 4, "weight"));
vision_model.mm_4_b = get_tensor(new_clip->ctx_data, format(TN_LLAVA_PROJ, 4, "bias"));
} catch (std::runtime_error & e) { }
}
else if (new_clip->proj_type == PROJECTOR_TYPE_LDP) {
// MobileVLM projection
Expand Down Expand Up @@ -1442,6 +1496,8 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx) {
}
else if (ctx->proj_type == PROJECTOR_TYPE_MLP) {
return ctx->vision_model.mm_2_b->ne[0];
} else if (ctx->proj_type == PROJECTOR_TYPE_MLP_NORM) {
return ctx->vision_model.mm_3_b->ne[0];
}
else {
std::string proj_type = PROJECTOR_TYPE_NAMES[ctx->proj_type];
Expand Down
32 changes: 29 additions & 3 deletions examples/llava/llava-cli.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,10 +148,35 @@ static void process_prompt(struct llava_context * ctx_llava, struct llava_image_
const int max_tgt_len = params->n_predict < 0 ? 256 : params->n_predict;
const bool add_bos = llama_should_add_bos_token(llama_get_model(ctx_llava->ctx_llama));

// llava chat format is "<system_prompt>\nUSER:<image_embeddings>\n<textual_prompt>\nASSISTANT:"
eval_string(ctx_llava->ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:", params->n_batch, &n_past, add_bos);
std::string system_prompt, user_prompt;
size_t image_pos = prompt.find("<image>");
if (image_pos != std::string::npos) {
// new templating mode: Provide the full prompt including system message and use <image> as a placeholder for the image

system_prompt = prompt.substr(0, image_pos);
user_prompt = prompt.substr(image_pos + std::string("<image>").length());
// We replace \n with actual newlines in user_prompt, just in case -e was not used in templating string
size_t pos = 0;
while ((pos = user_prompt.find("\\n", pos)) != std::string::npos) {
user_prompt.replace(pos, 2, "\n");
pos += 1; // Advance past the replaced newline
}
while ((pos = system_prompt.find("\\n", pos)) != std::string::npos) {
system_prompt.replace(pos, 2, "\n");
pos += 1; // Advance past the replaced newline
}

printf("system_prompt: %s\n", system_prompt.c_str());
printf("user_prompt: %s\n", user_prompt.c_str());
} else {
// llava-1.5 native mode
system_prompt = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:";
user_prompt = prompt + "\nASSISTANT:";
}

eval_string(ctx_llava->ctx_llama, system_prompt.c_str(), params->n_batch, &n_past, add_bos);
llava_eval_image_embed(ctx_llava->ctx_llama, image_embed, params->n_batch, &n_past);
eval_string(ctx_llava->ctx_llama, (prompt + "\nASSISTANT:").c_str(), params->n_batch, &n_past, false);
eval_string(ctx_llava->ctx_llama, user_prompt.c_str(), params->n_batch, &n_past, false);

// generate the response

Expand All @@ -162,6 +187,7 @@ static void process_prompt(struct llava_context * ctx_llava, struct llava_image_
for (int i = 0; i < max_tgt_len; i++) {
const char * tmp = sample(ctx_sampling, ctx_llava->ctx_llama, &n_past);
if (strcmp(tmp, "</s>") == 0) break;
if (strstr(tmp, "###")) break; // Yi-VL behavior

printf("%s", tmp);
fflush(stdout);
Expand Down
Loading