Trained with Unsloth - config
Browse files- config.json +54 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Mistral3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"torch_dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"image_token_index": 10,
|
| 9 |
+
"model_type": "mistral3",
|
| 10 |
+
"multimodal_projector_bias": false,
|
| 11 |
+
"pad_token_id": 11,
|
| 12 |
+
"projector_hidden_act": "gelu",
|
| 13 |
+
"spatial_merge_size": 2,
|
| 14 |
+
"text_config": {
|
| 15 |
+
"attention_dropout": 0.0,
|
| 16 |
+
"torch_dtype": "bfloat16",
|
| 17 |
+
"head_dim": 128,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 5120,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 32768,
|
| 22 |
+
"max_position_embeddings": 131072,
|
| 23 |
+
"model_type": "mistral",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 40,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"rms_norm_eps": 1e-05,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rope_theta": 1000000000.0,
|
| 30 |
+
"sliding_window": null,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 131072
|
| 33 |
+
},
|
| 34 |
+
"transformers_version": "4.56.2",
|
| 35 |
+
"unsloth_fixed": true,
|
| 36 |
+
"unsloth_version": "2026.1.3",
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"attention_dropout": 0.0,
|
| 39 |
+
"torch_dtype": "bfloat16",
|
| 40 |
+
"head_dim": 64,
|
| 41 |
+
"hidden_act": "silu",
|
| 42 |
+
"hidden_size": 1024,
|
| 43 |
+
"image_size": 1540,
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"intermediate_size": 4096,
|
| 46 |
+
"model_type": "pixtral",
|
| 47 |
+
"num_attention_heads": 16,
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"num_hidden_layers": 24,
|
| 50 |
+
"patch_size": 14,
|
| 51 |
+
"rope_theta": 10000.0
|
| 52 |
+
},
|
| 53 |
+
"vision_feature_layer": -1
|
| 54 |
+
}
|