Skip to content

add support for moondream vision language model #6899

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

Merged
merged 3 commits into from
Apr 25, 2024
Merged

add support for moondream vision language model #6899

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7c50cb0
add support for moondream vision language model
vikhyat Apr 25, 2024
d1d176e
Merge branch 'master' into master
vikhyat Apr 25, 2024
3d77120
Update examples/llava/clip.cpp
ggerganov Apr 25, 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
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,7 @@ Typically finetunes of the base models below are supported as well.
- [x] [MobileVLM 1.7B/3B models](https://huggingface.co/models?search=mobileVLM)
- [x] [Yi-VL](https://huggingface.co/models?search=Yi-VL)
- [x] [Mini CPM](https://huggingface.co/models?search=MiniCPM)
- [x] [Moondream](https://huggingface.co/vikhyatk/moondream2)

**HTTP server**

Expand Down
71 changes: 60 additions & 11 deletions examples/llava/clip.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,7 @@ static std::string format(const char * fmt, ...) {
#define TN_POS_EMBD "%s.position_embd.weight"
#define TN_CLASS_EMBD "v.class_embd"
#define TN_PATCH_EMBD "v.patch_embd.weight"
#define TN_PATCH_BIAS "v.patch_embd.bias"
#define TN_ATTN_K "%s.blk.%d.attn_k.%s"
#define TN_ATTN_Q "%s.blk.%d.attn_q.%s"
#define TN_ATTN_V "%s.blk.%d.attn_v.%s"
Expand Down Expand Up @@ -425,6 +426,7 @@ struct clip_vision_model {
// embeddings
struct ggml_tensor * class_embedding;
struct ggml_tensor * patch_embeddings;
struct ggml_tensor * patch_bias;
struct ggml_tensor * position_embeddings;

struct ggml_tensor * pre_ln_w;
Expand Down Expand Up @@ -501,6 +503,11 @@ struct clip_ctx {
bool use_gelu = false;
int32_t ftype = 1;

bool has_class_embedding = true;
bool has_pre_norm = true;
bool has_post_norm = false;
bool has_patch_bias = false;

struct gguf_context * ctx_gguf;
struct ggml_context * ctx_data;

Expand All @@ -526,7 +533,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
const int patch_size = hparams.patch_size;
const int num_patches = ((image_size / patch_size) * (image_size / patch_size));
const int num_patches_per_side = image_size / patch_size; GGML_UNUSED(num_patches_per_side);
const int num_positions = num_patches + 1;
const int num_positions = num_patches + (ctx->has_class_embedding ? 1 : 0);
const int hidden_size = hparams.hidden_size;
const int n_head = hparams.n_head;
const int d_head = hidden_size / n_head;
Expand Down Expand Up @@ -557,16 +564,23 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
inp = ggml_reshape_3d(ctx0, inp, num_patches, hidden_size, batch_size);
inp = ggml_cont(ctx0, ggml_permute(ctx0, inp, 1, 0, 2, 3));

if (ctx->has_patch_bias) {
// inp = ggml_add(ctx0, inp, ggml_repeat(ctx0, model.patch_bias, inp));
inp = ggml_add(ctx0, inp, model.patch_bias);
}

// concat class_embeddings and patch_embeddings
struct ggml_tensor * embeddings = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, hidden_size, num_positions, batch_size);
struct ggml_tensor * embeddings = inp;
if (ctx->has_class_embedding) {
embeddings = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, hidden_size, num_positions, batch_size);
embeddings = ggml_acc(ctx0, embeddings, model.class_embedding,
embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], 0);
embeddings = ggml_acc(ctx0, embeddings, inp,
embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], model.class_embedding->nb[1]);
}
ggml_set_name(embeddings, "embeddings");
ggml_set_input(embeddings);

embeddings = ggml_acc(ctx0, embeddings, model.class_embedding,
embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], 0);

embeddings = ggml_acc(ctx0, embeddings, inp,
embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], model.class_embedding->nb[1]);

struct ggml_tensor * positions = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, num_positions);
ggml_set_name(positions, "positions");
Expand All @@ -576,7 +590,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
ggml_add(ctx0, embeddings, ggml_get_rows(ctx0, model.position_embeddings, positions));

// pre-layernorm
{
if (ctx->has_pre_norm) {
embeddings = ggml_norm(ctx0, embeddings, eps);
ggml_set_name(embeddings, "pre_ln");

Expand Down Expand Up @@ -664,6 +678,14 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
embeddings = cur;
}

// post-layernorm
if (ctx->has_post_norm) {
embeddings = ggml_norm(ctx0, embeddings, eps);
ggml_set_name(embeddings, "post_ln");

embeddings = ggml_add(ctx0, ggml_mul(ctx0, embeddings, model.post_ln_w), model.post_ln_b);
}

// llava projector
{
embeddings = ggml_reshape_2d(ctx0, embeddings, embeddings->ne[0], embeddings->ne[1]);
Expand Down Expand Up @@ -1148,12 +1170,39 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {

}

try {
vision_model.class_embedding = get_tensor(new_clip->ctx_data, TN_CLASS_EMBD);
new_clip->has_class_embedding = true;
} catch (const std::exception& e) {
new_clip->has_class_embedding = false;
}

try {
vision_model.pre_ln_w = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "weight"));
vision_model.pre_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "bias"));
new_clip->has_pre_norm = true;
} catch (std::exception & e) {
new_clip->has_pre_norm = false;
}

try {
vision_model.post_ln_w = get_tensor(new_clip->ctx_data, format(TN_LN_POST, "v", "weight"));
vision_model.post_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_POST, "v", "bias"));
new_clip->has_post_norm = true;
} catch (std::exception & e) {
new_clip->has_post_norm = false;
}

try {
vision_model.patch_bias = get_tensor(new_clip->ctx_data, TN_PATCH_BIAS);
new_clip->has_patch_bias = true;
} catch (std::exception & e) {
new_clip->has_patch_bias = false;
}

try {
vision_model.patch_embeddings = get_tensor(new_clip->ctx_data, TN_PATCH_EMBD);
vision_model.class_embedding = get_tensor(new_clip->ctx_data, TN_CLASS_EMBD);
vision_model.position_embeddings = get_tensor(new_clip->ctx_data, format(TN_POS_EMBD, "v"));
vision_model.pre_ln_w = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "weight"));
vision_model.pre_ln_b = get_tensor(new_clip->ctx_data, format(TN_LN_PRE, "v", "bias"));
} catch(const std::exception& e) {
LOG_TEE("%s: failed to load vision model tensors\n", __func__);
}
Expand Down
Loading