Upload siglip checkpoint-3000

siglip-checkpoint-3000/chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}

siglip-checkpoint-3000/config.json

@@ -0,0 +1,68 @@
+{
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaLLaDAModelLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bos_token_id": 126080,
+  "dtype": "bfloat16",
+  "embedding_loss_lambda": 0.5,
+  "embedding_loss_type": "infonce_learnable",
+  "embedding_pool_strategy": "response_tokens",
+  "eos_token_id": 126081,
+  "faster_token_stride": 10,
+  "force_sample": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 16384,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model,embedding_projection",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip2-so400m-patch14-384",
+  "mm_vision_tower_lr": 1e-06,
+  "model_type": "llada",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 126081,
+  "pos_skipping_range": 4096,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.57.1",
+  "use_auxiliary_embedding_loss": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 126349,
+  "y_encoder_dim": 1024,
+  "y_encoder_name": "abhinand/MedEmbed-large-v0.1"
+}

siglip-checkpoint-3000/configuration_llada.py

@@ -0,0 +1,175 @@
+# coding=utf-8
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# 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.
+""" LLaDA model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+LLaDA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class LLaDAConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`LLaDAModel`]. It is used to instantiate an LLaDA
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the LLaDA-8B.
+
+    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 32000):
+            Vocabulary size of the LLaDA model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`LLaDAModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            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
+            `num_attention_heads`.
+        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 2048):
+            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`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum. 
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+    """
+
+    model_type = "llada"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32000,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        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
+
+        # 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.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self._rope_scaling_validation()
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
+            )
+        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
+            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")

siglip-checkpoint-3000/latest

@@ -0,0 +1 @@
+global_step3000

siglip-checkpoint-3000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af770f4edc62abdc4419b4f3fa839f004c99a0012dbc9f42b469ec02229eb859
+size 4994631072

siglip-checkpoint-3000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9653a0a14bff8ebd8c8f72f1b4ba0ea7cfb7d5850a855fbd923e67cfcb6c97f1
+size 4999802600

siglip-checkpoint-3000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518053600e6083e39d36a57f1ba63eaf8757111e07cbc58169f70886c54e30ac
+size 4999827272

siglip-checkpoint-3000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1a285b0b557a369bd621f4517ada37d61fa0ac9ed2e5915ed4bd49e34d0e48
+size 2564944658

siglip-checkpoint-3000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b509c0b70892d7832c63382f21da5a9a8484335ebf733111ccb95420a3ae377e
+size 16389

siglip-checkpoint-3000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1422676a5189b429fc76726b69beebd1cafcb57c60b51175bcf8e2dd7a4b42c
+size 16389

siglip-checkpoint-3000/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788334f80ef249d7d8ab27bd470f3e38d1b63f4d248ae8022de6f3860f372cad
+size 16404

siglip-checkpoint-3000/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745633849e3c0837e93ea5e1905e208db6c1d263a26f8993e085202df1c8e3e5
+size 16404

siglip-checkpoint-3000/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a95e7e38c79401af8bd022300cfeb077edd9b04e2e517f71b8356519c8debc
+size 16404

siglip-checkpoint-3000/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5af197f9bb13c639420c8de850c5a5effeae6c9c80e0ceb2ef62c5fd0f8ada
+size 16404

siglip-checkpoint-3000/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abeb83690f0fc393168070f9c2979924b2d630bceb344080b84796bf7cc8d79
+size 16404

siglip-checkpoint-3000/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d661a98ca734e96bc657741176a70fbf4d947147cfb193013b360f4831459023
+size 16404

siglip-checkpoint-3000/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fb8f5e927e718cb497301319b5cf99e17ff479257fec0b0998523519639083
+size 16404

siglip-checkpoint-3000/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4c29ac137fe32393605b05101fdc1a948cc4c5a6a41b59eb2838e00e87f1e7
+size 16404

siglip-checkpoint-3000/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b9e549f46d048046f0f4ff1b8725f317db637845479652f26cab4a48f3e053
+size 16404

siglip-checkpoint-3000/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acf773dcff4a6020367796963848e90aa0ce5cb964def62bb1ec0d7179986b2
+size 16404

siglip-checkpoint-3000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603cc37d78131046b8968d0c980a4fdf8f325337f9e572be908ac92f99617d70
+size 16389

siglip-checkpoint-3000/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80019fc2b0d59a52e97df26e2d64b8d77a440d3361e4f973413daca5500adee1
+size 16404

siglip-checkpoint-3000/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2cc635fb456dc0d62c3486844b13cf4646dca6883b0e4b36de84c26e211dff
+size 16404

siglip-checkpoint-3000/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d443d814a6c61ff1276fe28cb6132923ae88c6162ff05573b80013a63162e5f
+size 16404

siglip-checkpoint-3000/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7fa85bf8a98b9cc37710fd50db2cf2f11769d06e33df739291357de86761bf
+size 16404

siglip-checkpoint-3000/rng_state_24.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce3c9d9b3e8b852e35df207e35b1afb68b69384861e1e4055ae29d07ff2567e
+size 16404

siglip-checkpoint-3000/rng_state_25.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131f3d2996d8257d6252b9b9f6f4b7e93158798c5bfa81ccf5b3e65a28c3d028
+size 16404

siglip-checkpoint-3000/rng_state_26.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70177627701b8605beb364b5361d3acaae1e98da5971316717cdd74c3e99605
+size 16404

siglip-checkpoint-3000/rng_state_27.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e093af7dd9344f21ee2b1951e4144e1470fc7e61b6ad91927d3a4df2e37c1fbd
+size 16404

siglip-checkpoint-3000/rng_state_28.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23599f9f766a8bc2df1ac93833ef8f6355c20bf92e30fcb157f7522e476ae63
+size 16404

siglip-checkpoint-3000/rng_state_29.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f664ca9869260f8ce769a7a0124821d1991a75d00c38d70dc782c90b5eb9349
+size 16404

siglip-checkpoint-3000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bbbd639bfe8bcd2d9f2daf6b39f9e5d08889e8daf293bc85d8282a77b53513
+size 16389

siglip-checkpoint-3000/rng_state_30.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc04bbd3d661147dec7565f6293e8b3d05a5f2d31305f0a5018d195dd8f38d4
+size 16404

siglip-checkpoint-3000/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b663b2715b97c4af78e22c098ade9c17e81ca74ed0ca2cc8ba016da71cb50ebf
+size 16404

siglip-checkpoint-3000/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:decd782f4fd28d4cec1a581e912ee6473b48534eb8f59f2b9220d202241d8828
+size 16404

siglip-checkpoint-3000/rng_state_33.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930dde77965261035994a59c493f88d5f67369a88c18767463d8afd862fee453
+size 16404

siglip-checkpoint-3000/rng_state_34.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e169b76c7dcdfbc15455b91564a1be69a91bc820ff6844070acde542a9d8553b
+size 16404

siglip-checkpoint-3000/rng_state_35.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1036608f6cad9612658860d7f5f6014c12fcbb591755aa7606ddcdb0e19f5dc6
+size 16404

siglip-checkpoint-3000/rng_state_36.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8a8c896ececf256aa9561e5547cce3f419038699275a84f3a2896734dc140c
+size 16404

siglip-checkpoint-3000/rng_state_37.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d51dd4472fd59fd4ac52cecaba5b9acd72ee66d823e6467f555db7e68b630b
+size 16404

siglip-checkpoint-3000/rng_state_38.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb6ecd9fe2ddcc9d6073f5d5c773a85211cdc9d53b638810486c9a33f38bfe3
+size 16404

siglip-checkpoint-3000/rng_state_39.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317cef80a93743c329a58622c0f448cd453cad8b41b1ac1f0cf09d93cd7ba7e8
+size 16404

siglip-checkpoint-3000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66362706606703a8b908ba5752ae96638144e80a683b7af634db624eb317e507
+size 16389

siglip-checkpoint-3000/rng_state_40.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b933627b7aa5cd9aed0c4922db633be4298b9fd599a382f1c99a3b3d43acbcc
+size 16404

siglip-checkpoint-3000/rng_state_41.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855cc310b5a4ca7c6bc3fe2424c65b5296b41d5941091656a9082a9f40b32c7f
+size 16404

siglip-checkpoint-3000/rng_state_42.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9e2750a7b67723d16569d4e39a26cab6a870d91fa9871c18b5ca25fa219780
+size 16404

siglip-checkpoint-3000/rng_state_43.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b5c4bbffc392d0ea0ce1cb45376db24e9a918c62f9c21b5d4f1dc648d2fa84
+size 16404

siglip-checkpoint-3000/rng_state_44.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23283d2d75c8893f21addd4395a94aa4c22b16d3964f768250fa30baef56b83d
+size 16404

siglip-checkpoint-3000/rng_state_45.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77a1cf603f3f55e73d4b0a77acc2886a70e86f6da8b425851e5797c71a3d142
+size 16404