Prepare for vanilla HF integration (#1)
Browse files- Add config.json (20a088c9afb59e24087a7a098289ef78ee1c679f)
- Add model.safetensors (bb6ca9d1f3233da80dc8199c0074161497b2da4b)
- Delete nanoVLM-222M.pth with huggingface_hub (09378e56318a4092c7b9d241f07636f0af28d354)
Co-authored-by: Lucain Pouget <[email protected]>
- config.json +22 -24
- nanoVLM-222M.pth → model.safetensors +2 -2
config.json
CHANGED
@@ -1,34 +1,32 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"lm_hidden_dim": 576,
|
7 |
"lm_inter_dim": 1536,
|
|
|
|
|
8 |
"lm_max_position_embeddings": 8192,
|
9 |
-
"
|
10 |
-
"lm_n_blocks": 30,
|
11 |
"lm_n_heads": 9,
|
12 |
"lm_n_kv_heads": 3,
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
|
|
16 |
"lm_use_tokens": false,
|
17 |
-
"
|
18 |
-
"
|
|
|
|
|
19 |
"mp_pixel_shuffle_factor": 2,
|
20 |
-
"vit_cls_flag": false,
|
21 |
-
"vit_dropout": 0.0,
|
22 |
-
"vit_hidden_dim": 768,
|
23 |
-
"vit_img_size": 224,
|
24 |
-
"vit_inter_dim": 3072,
|
25 |
-
"vit_ln_eps": 1e-06,
|
26 |
-
"vit_model_type": "google/siglip-base-patch16-224",
|
27 |
-
"vit_n_blocks": 12,
|
28 |
-
"vit_n_heads": 12,
|
29 |
-
"vit_patch_size": 16,
|
30 |
-
"vlm_checkpoint_path": "vlm_model_0501_untied.pth",
|
31 |
"vlm_load_backbone_weights": true,
|
32 |
-
"
|
33 |
-
}
|
34 |
}
|
|
|
1 |
{
|
2 |
+
"vit_hidden_dim": 768,
|
3 |
+
"vit_inter_dim": 3072,
|
4 |
+
"vit_patch_size": 16,
|
5 |
+
"vit_img_size": 224,
|
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": "google/siglip-base-patch16-224",
|
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": "nanoVLM.pth"
|
|
|
32 |
}
|
nanoVLM-222M.pth → model.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37a5ffc3d2685a5cbb0fe3d214c6c491be9601ec5a0df0bd4976a65cac325418
|
3 |
+
size 888372464
|