Upload LlavaNextForConditionalGeneration

config.json

@@ -2,6 +2,7 @@
   "architectures": [
     "LlavaNextForConditionalGeneration"
   ],
+  "ignore_index": -100,
   "image_grid_pinpoints": [
     [
       336,
@@ -30,29 +31,32 @@
   "multimodal_projector_bias": true,
   "projector_hidden_act": "gelu",
   "text_config": {
-    "attention_bias": false,
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
     "attention_dropout": 0.0,
-    "head_dim": 4,
+    "head_dim": null,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
-    "max_position_embeddings": 2048,
-    "mlp_bias": false,
-    "model_type": "llama",
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
     "num_key_value_heads": 2,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
-    "rope_theta": 10000.0,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
     "use_cache": true,
-    "vocab_size": 32005
+    "vocab_size": 32064
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.56.0.dev0",
+  "use_image_newline_parameter": true,
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "quick_gelu",
@@ -60,15 +64,18 @@
     "image_size": 336,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
+    "intermediate_size": 4096,
     "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 4,
     "num_channels": 3,
     "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
     "patch_size": 14,
-    "projection_dim": 8
+    "projection_dim": 768,
+    "vocab_size": 32000
   },
   "vision_feature_layer": -2,
-  "vision_feature_select_strategy": "default"
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:808b7578d4e2e120e46b755311c7c811c3c31309bb06471cdeded5487fa8bc82
-size 4218192
+oid sha256:d4f465eb7fce9edb50690acacc93afe884226f04363f36d64e9d7dd101212d15
+size 5399728