Upload folder using huggingface_hub

siglip-checkpoint-1500/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-1500/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-1500/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-1500/latest

@@ -0,0 +1 @@
+global_step1500

siglip-checkpoint-1500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b3bae10c9d86b1bf4fc86eb4e40c662e237889545f00361b62e4f41aabe9b2
+size 4994631072

siglip-checkpoint-1500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8461dc345355ef979b28449f19dcd670bb8c7c2514fec3ca419dc4ac29963b71
+size 4999802600

siglip-checkpoint-1500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671faa8cf738cf8dbb158264aafc415e9f5b13169d07af28bed0d23aa93a08ae
+size 4999827272

siglip-checkpoint-1500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354ac5f9b9ad83646344f4750df54b981082cd3b11ca011c35cd6ae975c22379
+size 2564944658

siglip-checkpoint-1500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66a0526bf63b851368dbf75f1151b161470b5cdb0bbe67f2e8b38f090e8a469
+size 16389

siglip-checkpoint-1500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3a694ca86372a76ae7e686ca8c250ce1a9ea4bb9be2d2ea118d775312874f9
+size 16389

siglip-checkpoint-1500/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ae69bf50afe746dfad729c88dcf004a4c88ba9b1f804488b0d07393b9ea28c
+size 16404

siglip-checkpoint-1500/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3db87a22afc097f6f1d75020158eb467e98c2e672c4b26795f806e2e155596
+size 16404

siglip-checkpoint-1500/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff20355761598fa54858d8ebeeb2580eacb19eaa8f910481553481f612a0943e
+size 16404

siglip-checkpoint-1500/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacb99f73c555cb3878ccb22e940aab0de99c325cddcfaf26a16387215690251
+size 16404

siglip-checkpoint-1500/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fdc0f68b0a1562c063dbb3066a29c3d9b8c4f9e26c6b3006ce37b72337b8c5
+size 16404

siglip-checkpoint-1500/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec75eef465034f8c951bf67388f484de706334cd6122fe98c1887cf8b9de8e8
+size 16404

siglip-checkpoint-1500/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1ec6f701ec064c5c357003fddf37e727e4a4c0a84c7f91a6d57946a92c3f27
+size 16404

siglip-checkpoint-1500/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02040881b8101ab0e577ec4c81932133d4305e6340492aec253cb2c0e85b1132
+size 16404

siglip-checkpoint-1500/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed156b63c6ec8a4870f2226123a3a4b5331523c44ba330e3117465967b90713
+size 16404

siglip-checkpoint-1500/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1711f9e27b0906160d0e4a6732e7ac7e322c2d29a0f32bd33b9a826c0450b9
+size 16404

siglip-checkpoint-1500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728639bd94988caa33fbca020c82014ac8ff646245972350614545209d5bee61
+size 16389

siglip-checkpoint-1500/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207a0205d9f97637d155874d1e39662a727042d09d8055af35c26ef51c06fa59
+size 16404

siglip-checkpoint-1500/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3e3da30f56f7385d6462bf0cdbcf4485f0899e4b4267fd81b83e5721466741
+size 16404

siglip-checkpoint-1500/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785e82c2f948da945ca4574170ef402704f9bb9eda71e4839392b8e18bd647fc
+size 16404

siglip-checkpoint-1500/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3b66f95cc26f3fd895324349a084735339e143f3be38ca547b38d743e9c53d
+size 16404

siglip-checkpoint-1500/rng_state_24.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44bec86c24543a8d7963ef1b12be60d3870a820ad2da57dbb179cd589047b78
+size 16404

siglip-checkpoint-1500/rng_state_25.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af245d4ba62459174ae00dbce34131b2bc19390e76f6f140147068e5015d2ba
+size 16404

siglip-checkpoint-1500/rng_state_26.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f3cab2791e84ab8b7ec5a15c303c696495c4afac28deefe8a750ca322e8311
+size 16404

siglip-checkpoint-1500/rng_state_27.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a276f41aab399548a7b49766cdf413b4058d2b193c74ae2c6c9f6f55ff1d304
+size 16404

siglip-checkpoint-1500/rng_state_28.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd68ba239316c990cfbf47eab153787993042534ae2477e3be0d41146cccd4bc
+size 16404

siglip-checkpoint-1500/rng_state_29.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e996c059dff9e8ca7f20d4b75f29c7309a5d63145b26b8b8be3974a43be773
+size 16404

siglip-checkpoint-1500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc258a13f81ed7069b07f919edf70442d32a2ac71dce1c14a4859cf1c289652a
+size 16389

siglip-checkpoint-1500/rng_state_30.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02da171380796dd41272983a9b74878498b37fd3d8bccbabfa5232ab7789ad4e
+size 16404

siglip-checkpoint-1500/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b142498972ba5c23eecf9f471178d645be3805789be4fc017c2e5c5539b25ab4
+size 16404

siglip-checkpoint-1500/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737bba1b30c9ca7a944eeb122976d159fb84fb3cf73d39d5e86f6c0ece6bb20b
+size 16404

siglip-checkpoint-1500/rng_state_33.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddd43b0ea6eac0202eba78bad0a6625d2c1affda8b9f0901afad8223135e06d
+size 16404

siglip-checkpoint-1500/rng_state_34.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c0aad3bdc814a51c2b60f52f7bb956d46be47e237252b06a189cd31d805c58
+size 16404

siglip-checkpoint-1500/rng_state_35.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25500ea9d1114311fac5ce35c6a7d84eaa4478530b9a600527d31a567dcd4f9
+size 16404

siglip-checkpoint-1500/rng_state_36.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fdb5b9b64d84afa05900a72fc98bdc5bbc1cf6546a21dbaec0730dece542d00
+size 16404

siglip-checkpoint-1500/rng_state_37.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77720ad070560df3b65fbdb6aa76773766027cdc272ed23f0b5db2b6fd80127a
+size 16404

siglip-checkpoint-1500/rng_state_38.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e9d668013ca938b1f1406f0363f4cc4d5ba3161e349313ab088f3906809f01
+size 16404

siglip-checkpoint-1500/rng_state_39.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace34c20b0175cd79c0044439c72ad249f98b74dd1eaa99fef3e769492535132
+size 16404

siglip-checkpoint-1500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369bea4c4ca8ccb7b94fe17c491d6bec368627688d8c64a53b3abec4c76d8f25
+size 16389

siglip-checkpoint-1500/rng_state_40.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55eabd99527126bca309e51607825e12f66f8b0665477c059f77ff7d808d1f20
+size 16404

siglip-checkpoint-1500/rng_state_41.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242a81a8d6a8134dfc73ce32bf0c647e5ef149fdedff233b4ba84f300d5264a9
+size 16404

siglip-checkpoint-1500/rng_state_42.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0f5a8e412a5b0ff976f7c55d60bbf2290cfc033e2624b5e9a5bf0ce658d698
+size 16404

siglip-checkpoint-1500/rng_state_43.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42283846c811ca80e8a47842577b2068452fabb4734a0cbdcd1a6b8b634fc66
+size 16404

siglip-checkpoint-1500/rng_state_44.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f3089487dabe92673c57f74f9a298eae03632bd99c32a3b086778b96778965
+size 16404

siglip-checkpoint-1500/rng_state_45.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea788a6dae1a8016a3b9dba89daffdde89a0a05a619cbb969c9e3f47c5a055b
+size 16404