Upload LlavaNextForConditionalGeneration
Browse files- config.json +21 -6
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"LlavaNextForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"ignore_index": -100,
|
| 6 |
"image_grid_pinpoints": [
|
| 7 |
[
|
| 8 |
336,
|
|
@@ -28,28 +27,44 @@
|
|
| 28 |
"image_seq_length": 576,
|
| 29 |
"image_token_index": 32000,
|
| 30 |
"model_type": "llava_next",
|
|
|
|
| 31 |
"projector_hidden_act": "gelu",
|
| 32 |
"text_config": {
|
|
|
|
|
|
|
| 33 |
"head_dim": 2,
|
|
|
|
| 34 |
"hidden_size": 8,
|
|
|
|
| 35 |
"intermediate_size": 32,
|
| 36 |
-
"max_position_embeddings":
|
| 37 |
-
"
|
|
|
|
| 38 |
"num_attention_heads": 4,
|
| 39 |
"num_hidden_layers": 2,
|
| 40 |
"num_key_value_heads": 2,
|
| 41 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"vocab_size": 32005
|
| 43 |
},
|
| 44 |
"tie_word_embeddings": false,
|
| 45 |
"torch_dtype": "float32",
|
| 46 |
-
"transformers_version": "4.
|
| 47 |
"vision_config": {
|
| 48 |
-
"
|
|
|
|
|
|
|
| 49 |
"image_size": 336,
|
|
|
|
|
|
|
| 50 |
"intermediate_size": 32,
|
|
|
|
| 51 |
"model_type": "clip_vision_model",
|
| 52 |
"num_attention_heads": 4,
|
|
|
|
| 53 |
"num_hidden_layers": 2,
|
| 54 |
"patch_size": 14,
|
| 55 |
"projection_dim": 8
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LlavaNextForConditionalGeneration"
|
| 4 |
],
|
|
|
|
| 5 |
"image_grid_pinpoints": [
|
| 6 |
[
|
| 7 |
336,
|
|
|
|
| 27 |
"image_seq_length": 576,
|
| 28 |
"image_token_index": 32000,
|
| 29 |
"model_type": "llava_next",
|
| 30 |
+
"multimodal_projector_bias": true,
|
| 31 |
"projector_hidden_act": "gelu",
|
| 32 |
"text_config": {
|
| 33 |
+
"attention_bias": false,
|
| 34 |
+
"attention_dropout": 0.0,
|
| 35 |
"head_dim": 2,
|
| 36 |
+
"hidden_act": "silu",
|
| 37 |
"hidden_size": 8,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
"intermediate_size": 32,
|
| 40 |
+
"max_position_embeddings": 2048,
|
| 41 |
+
"mlp_bias": false,
|
| 42 |
+
"model_type": "llama",
|
| 43 |
"num_attention_heads": 4,
|
| 44 |
"num_hidden_layers": 2,
|
| 45 |
"num_key_value_heads": 2,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"rms_norm_eps": 1e-06,
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 10000.0,
|
| 50 |
+
"use_cache": true,
|
| 51 |
"vocab_size": 32005
|
| 52 |
},
|
| 53 |
"tie_word_embeddings": false,
|
| 54 |
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.54.0.dev0",
|
| 56 |
"vision_config": {
|
| 57 |
+
"attention_dropout": 0.0,
|
| 58 |
+
"hidden_act": "quick_gelu",
|
| 59 |
+
"hidden_size": 16,
|
| 60 |
"image_size": 336,
|
| 61 |
+
"initializer_factor": 1.0,
|
| 62 |
+
"initializer_range": 0.02,
|
| 63 |
"intermediate_size": 32,
|
| 64 |
+
"layer_norm_eps": 1e-05,
|
| 65 |
"model_type": "clip_vision_model",
|
| 66 |
"num_attention_heads": 4,
|
| 67 |
+
"num_channels": 3,
|
| 68 |
"num_hidden_layers": 2,
|
| 69 |
"patch_size": 14,
|
| 70 |
"projection_dim": 8
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.54.0.dev0"
|
| 6 |
}
|
model.safetensors
CHANGED
|
@@ -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 sha256:5e9399a2c39e070ca7cbd3ecd45caa2e880c26672a15b666a8eac2a37850bab7
|
| 3 |
+
size 2157552
|