isLinXu
commited on
Commit
·
5a8ea3b
1
Parent(s):
5f7e65c
add nanoVLM-SmolLM2-dinov2
Browse files- config.json +32 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vit_hidden_dim": 768,
|
| 3 |
+
"vit_inter_dim": 3072,
|
| 4 |
+
"vit_patch_size": 14,
|
| 5 |
+
"vit_img_size": 518,
|
| 6 |
+
"vit_n_heads": 12,
|
| 7 |
+
"vit_dropout": 0.0,
|
| 8 |
+
"vit_n_blocks": 12,
|
| 9 |
+
"vit_ln_eps": 1e-06,
|
| 10 |
+
"vit_cls_flag": false,
|
| 11 |
+
"vit_model_type": "facebook/dinov2-base",
|
| 12 |
+
"lm_hidden_dim": 576,
|
| 13 |
+
"lm_inter_dim": 1536,
|
| 14 |
+
"lm_rms_eps": 1e-05,
|
| 15 |
+
"lm_re_base": 100000,
|
| 16 |
+
"lm_max_position_embeddings": 8192,
|
| 17 |
+
"lm_vocab_size": 49152,
|
| 18 |
+
"lm_n_heads": 9,
|
| 19 |
+
"lm_n_kv_heads": 3,
|
| 20 |
+
"lm_dropout": 0.0,
|
| 21 |
+
"lm_n_blocks": 30,
|
| 22 |
+
"lm_attn_scaling": 1.0,
|
| 23 |
+
"lm_max_length": 79,
|
| 24 |
+
"lm_use_tokens": false,
|
| 25 |
+
"lm_tie_weights": true,
|
| 26 |
+
"lm_model_type": "HuggingFaceTB/SmolLM2-135M",
|
| 27 |
+
"lm_tokenizer": "HuggingFaceTB/cosmo2-tokenizer",
|
| 28 |
+
"lm_eos_token_id": 0,
|
| 29 |
+
"mp_pixel_shuffle_factor": 2,
|
| 30 |
+
"vlm_load_backbone_weights": true,
|
| 31 |
+
"vlm_checkpoint_path": "checkpoints/nanoVLM-222M-dinov2-base-epoch5"
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc50308a787a37d6b516fe4ac80bfcb4db467f5d90a3888940561e090a6a7de0
|
| 3 |
+
size 888003824
|