Upload siglip checkpoint-4000

siglip-checkpoint-4000/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-4000/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-4000/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-4000/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b2b775bbce27be43ef8fe49aa018d02440edb215854afd6873ff284c3da49e
+size 1583329739

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc4004e841371cd00089ec6c682684cb7a2a8826a59b1d2db81501ff24e0470
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94da9b44419a2ebca1da5b73b0a6fe6fc4c57433807ae43b7d9852fbfd686031
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947373b23e23aa90d096fa2c72a65429dc38cfc05b57f28833bb3018aec53038
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59e7afe3ba574f47b784a3b592df73be60dcd20572889c9c1acf6e94f6ad5e3
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f256c3a050dea99615ed84f6e25dfb8030c101e72d044559227e0461405cf6c
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa78429b422e70487feaabb7dcf81049aa5f6fb35dced16e2ae5a15f134cc49
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b959ebf9f1a70b5e4fd33aa1c78ccebe49d20d8b756a5591f80ece85d6b547
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cf7fa16c848a9e2ab9824840014afffb49d14e2b2ebe917ee4f76563055968
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e381d1f1a4276dfd48c260ca3a75cf57caa208f18693ba020217c53da0937efa
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf8ca275fa4616cd8d2017728418f81dc20df3bca337b16bb838355c1391436
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73b35f7ba384db895959500e2c268b366411f127f7f05fea47714664f8cbee5
+size 1583329739

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb209313d1ba985364a666b35ee54f86e32380d1776f98efe80554aa72d0ba4
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e12bffbe1d3978a21d7c990a8149a356724492c8e4a6ef352c2f0208dd868e5
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba322e1aabe35d3e450ffe02815ba4744a0a2c6b757843e74fe24ffc3abe9d30
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2326285f6512bf006781044b89a7bd0f64fd134186e9b3b604b4453c511cad72
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f952f45b4754790e8e01b7ffca6b3653e52317efad7c18c435e0145f8097d363
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd1a3a41e7eecffe6f660f778c7f757f61d52a4dd74b937d8a81aeb9eef4816
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ec25b968700d68d84a5a9ee88e942bf50309038164a27d1fc0f80b11498b99
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951995c7d076df14c88442531ba93fa690f46d766c8bab7e6f7708a26d4da114
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901a3d9888c32a6ccda50b3bf555af4485aad8e50f6d0a4708363341c1ec9da0
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89416cdbc2200feda168aeee1aee180294e3d9a899b609695fdc3b98307fdc14
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fd73c769b7e73a6e5b8f4fd9c32a2f6759aee0ee39c965dbc6a14d11a1a641
+size 1583329739

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d2f7a858bf9b8368f2a262d608cbd7f9b9f29864ac75b4bb018ec038a946db
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9061e35099539e6064c8619337ef16d7e31c3e4c2450a5bb4d0970981dd0c495
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540c68ac43f6d0595895134837c6efc8b4ed9a96d755cf99afeb3fddd21aadcc
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56618c2128dbcccab7d47b3e06d508ad232e208d5a2bbe58f5a5a5c0287c6f9b
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a283b9d0c2027d99d2ec02149f79650818ecb5a0980520a44b468db11956c6
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6918a4ec9b3241663d8a3ee218ca4cb3fc53af4aadfee67d3a451f48ae0ebb24
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a328691b19001692b1de35ccceec1c2093de85296fa2f98b8ce06a0e31743603
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf090848782ff9dc583d3de6328f6303059cf8772fb730ff2f3cf735610d8b7
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e8850bd680496cf2e99441787aeb393da96678beac3edb2baf5a5339cd0766
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87f61c7ed7d90ada356ce03b2264b710f282b9fd7adf2ec0799c017a3dca34d
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ead56898d647092c5ebc84b225cb1cf324906ef2224e49898e29d927d35c1e
+size 1583329739

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d33d6b521fb05ceb38d21009b4db5d1c768d5d0b89142f77a6344e170733d9f
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9935496585f0394e24999d306fac3498eecc18932ed26e49e3a6ad00388964
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0843df1c98da51bcf1346c9ee8edf58742a940c3bbdf9198a4ebace947e984ae
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920133667bb7bdb019dc8e57e986a97d7ced5473780da300cce328593c9dcb4c
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f3549a6f77f80cf5d47c1f524c52d35d8dbfbada9081b38ec71f175b65ec2a
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ae243ec8d6f4cbc37432cfaa2a91cf37805d0c3004a5bd06a94095eab90e82
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa2d3fe1e0a5804d236d27dcbed357a5457f7a86d5499291a1483b554c5f208
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444e97bdaf6735a55d578519c6c06121a29e78e75ef5d05be5bc1090af51f194
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d801b34b4835e178f92067b8eb89bb3c43ac4e561f75efe3b936dbf6364dd9
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273fca81dd7c0e6c470f5ebc1f562f3befa194e6db1b572aa1249f759ccc19ec
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e38b931bfe2291ab49985b9e42b0cbda01b48d3db995b3856bcd9668627b891
+size 1583329739

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a3bdcc13e434407546e8fa5a605a829cee46b79b5ddc95627fa7e411102600
+size 1583329761

siglip-checkpoint-4000/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbff3fd1e95b754f61cb7e3aef2774f2de085e1fbc06420528d201267c08061
+size 1583329761