Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -7,11 +7,12 @@ tags:
 - multimodal
 - qwen
 - mlx
+- mlx
 ---
 
 # mlx-community/nanoLLaVA-1.5-8bit
-This model was converted to MLX format from [`qnguyen3/nanoLLaVA-1.5`]() using mlx-vlm version **0.0.11**.
-Refer to the [original model card](https://huggingface.co/qnguyen3/nanoLLaVA-1.5) for more details on the model.
+This model was converted to MLX format from [`mlx-community/nanoLLaVA-1.5-bf16`]() using mlx-vlm version **0.1.6**.
+Refer to the [original model card](https://huggingface.co/mlx-community/nanoLLaVA-1.5-bf16) for more details on the model.
 ## Use with mlx
 
 ```bash

config.json

@@ -21,48 +21,6 @@
     "mm_hidden_size": 1152,
     "mm_projector_lr": null,
     "mm_projector_type": "mlp2x_gelu",
-    "vision_config": {
-      "return_dict": true,
-      "tie_word_embeddings": true,
-      "max_length": 20,
-      "min_length": 0,
-      "do_sample": false,
-      "early_stopping": false,
-      "num_beams": 1,
-      "num_beam_groups": 1,
-      "diversity_penalty": 0.0,
-      "temperature": 1.0,
-      "model_type": "siglip_vision_model",
-      "hidden_size": 1152,
-      "intermediate_size": 4304,
-      "num_hidden_layers": 27,
-      "num_attention_heads": 16,
-      "num_channels": 3,
-      "patch_size": 14,
-      "image_size": 384,
-      "attention_dropout": 0.0,
-      "layer_norm_eps": 1e-06,
-      "hidden_act": "gelu_pytorch_tanh"
-    },
-    "text_config": {
-      "vocab_size": 151936,
-      "max_position_embeddings": 32768,
-      "hidden_size": 1024,
-      "intermediate_size": 2816,
-      "num_hidden_layers": 24,
-      "num_attention_heads": 16,
-      "use_sliding_window": false,
-      "sliding_window": "None",
-      "max_window_layers": 21,
-      "num_key_value_heads": 16,
-      "hidden_act": "silu",
-      "initializer_range": 0.02,
-      "rms_norm_eps": 1e-06,
-      "use_cache": false,
-      "rope_theta": 1000000.0,
-      "attention_dropout": 0.0,
-      "model_type": "qwen2"
-    },
     "model_type": "llava-qwen2",
     "num_attention_heads": 16,
     "num_hidden_layers": 24,
@@ -74,14 +32,56 @@
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
     "sliding_window": 4096,
+    "text_config": {
+        "vocab_size": 151936,
+        "max_position_embeddings": 32768,
+        "hidden_size": 1024,
+        "intermediate_size": 2816,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "use_sliding_window": false,
+        "sliding_window": "None",
+        "max_window_layers": 21,
+        "num_key_value_heads": 16,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-06,
+        "use_cache": false,
+        "rope_theta": 1000000.0,
+        "attention_dropout": 0.0,
+        "model_type": "qwen2"
+    },
     "tie_word_embeddings": false,
     "tokenizer_model_max_length": 4096,
     "tokenizer_padding_side": "right",
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.39.2",
+    "transformers_version": "4.41.1",
     "tune_mm_mlp_adapter": false,
-    "use_cache": false,
+    "use_cache": true,
     "use_mm_proj": true,
     "use_sliding_window": false,
+    "vision_config": {
+        "return_dict": true,
+        "tie_word_embeddings": true,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "model_type": "siglip_vision_model",
+        "hidden_size": 1152,
+        "intermediate_size": 4352,
+        "num_hidden_layers": 27,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "image_size": 384,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "gelu_pytorch_tanh"
+    },
     "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cae428eb06e3ef36ddc9ebddee0c01a2030b1d1dd7f00e84a117068a3f959f
-size 1138138539
+oid sha256:f0a1d1517ad9e6e810bc6ac99956643c66e4b87a2f82bd5d1b5cb0966e5c5476
+size 1120283029

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 1137941384
+        "total_size": 1120085896
     },
     "weight_map": {
         "language_model.model.embed_tokens.biases": "model.safetensors",

tokenizer_config.json

@@ -35,6 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",