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

@@ -7,12 +7,12 @@ tags:
 - multimodal
 - qwen
 - mlx
-pipeline_tag: image-text-to-text
+- mlx
 ---
 
 # mlx-community/nanoLLaVA-1.5-4bit
-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
 }

configuration_llava_qwen2.py

@@ -0,0 +1,202 @@
+# coding=utf-8
+# Copyright 2024 The Qwen team, Alibaba Group and the HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" Qwen2 model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "Qwen/Qwen2-7B-beta": "https://huggingface.co/Qwen/Qwen2-7B-beta/resolve/main/config.json",
+}
+
+
+class Qwen2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a
+    Qwen2 model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of
+    Qwen2-7B-beta [Qwen/Qwen2-7B-beta](https://huggingface.co/Qwen/Qwen2-7B-beta).
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 151936):
+            Vocabulary size of the Qwen2 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Qwen2Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 22016):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 32):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 32768):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import Qwen2Model, Qwen2Config
+
+    >>> # Initializing a Qwen2 style configuration
+    >>> configuration = Qwen2Config()
+
+    >>> # Initializing a model from the Qwen2-7B style configuration
+    >>> model = Qwen2Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "qwen2"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=4096,
+        intermediate_size=22016,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+from typing import Union
+from transformers import PretrainedConfig
+import os
+
+
+class SigLipVisionConfig(PretrainedConfig):
+    model_type = "siglip_vision_model"
+
+    def __init__(
+            self,
+            hidden_size=1152,
+            image_mean=(0.5, 0.5, 0.5),
+            intermediate_size=4304,
+            num_hidden_layers=27,
+            num_attention_heads=16,
+            num_channels=3,
+            image_size=384,
+            patch_size=14,
+            hidden_act="gelu_pytorch_tanh",
+            layer_norm_eps=1e-6,
+            attention_dropout=0.0,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.attention_dropout = attention_dropout
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        self.image_mean = image_mean
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
+        cls._set_token_in_kwargs(kwargs)
+
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        # get the vision config dict if we are loading from SigLipConfig
+        if config_dict.get("model_type") == "siglip":
+            config_dict = config_dict["vision_config"]
+
+        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
+            )
+
+        return cls.from_dict(config_dict, **kwargs)
+
+class LlavaQwen2Config(Qwen2Config):
+    model_type = "llava-qwen2"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9263d1c5a6e121ac2041d3d885bbe431a51f95e69babb713c84f6a28f819a987
-size 612184804
+oid sha256:df5ca5cd0c995a0cd05c3366f76e3b2b9655b20616a5ae349d53b5db134abc53
+size 594329316

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 611988296
+        "total_size": 594132808
     },
     "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",