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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_qwen2.Qwen2Config",
+    "AutoModelForCausalLM": "modeling_qwen2.Qwen2ForCausalLM"
+  },
+  "beacon_attend_prev": true,
+  "beacon_attn": "full-coverage",
+  "beacon_embed_init": "eos",
+  "beacon_parallel_window": 1,
+  "beacon_param": [
+    "q",
+    "k",
+    "v"
+  ],
+  "beacon_pos": "interleave",
+  "beacon_ratio": [
+    4
+  ],
+  "beacon_ratio_mix": "adapt-1024",
+  "beacon_sink_size": 0,
+  "beacon_stride": 2048,
+  "beacon_window": 2048,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064,
+  "lychee_memory_window": 2048,
+  "lychee_memory_stride": 2048,
+  "lychee_memory_attn": "full-coverage",
+  "lychee_memory_ratio": [
+    4
+  ],
+  "lychee_memory_ratio_mix": "adapt-1024",
+  "lychee_memory_param": [
+    "q",
+    "k",
+    "v"
+  ],
+  "lychee_memory_embed_init": "eos",
+  "lychee_memory_sink_size": 0,
+  "lychee_memory_attend_prev": true,
+  "lychee_memory_pos": "interleave",
+  "lychee_memory_parallel_window": 1
+}

configuration_qwen2.py

@@ -0,0 +1,169 @@
+# 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,
+        rope_scaling=None,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        beacon_window=1024,
+        beacon_stride=1024,
+        beacon_attn="full-coverage",
+        beacon_ratio=[2,4,8,16,32],
+        beacon_ratio_mix="step-random",
+        beacon_param=[],
+        beacon_embed_init="eos",
+        beacon_sink_size=0,
+        beacon_attend_prev=True,
+        beacon_pos="interleave",
+        beacon_parallel_window=1,
+        **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
+        self.rope_scaling = rope_scaling
+
+        # 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
+
+        self.beacon_window = beacon_window
+        self.beacon_stride = beacon_stride
+        self.beacon_attn = beacon_attn
+        self.beacon_ratio = beacon_ratio
+        self.beacon_ratio_mix = beacon_ratio_mix
+        self.beacon_param = beacon_param
+        self.beacon_embed_init = beacon_embed_init
+        self.beacon_sink_size = beacon_sink_size
+        self.beacon_attend_prev = beacon_attend_prev
+        self.beacon_pos = beacon_pos
+        self.beacon_parallel_window = beacon_parallel_window
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.53.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbd78516ba434f37be86cb2097d1731d43befeef8d4f87456c81c3912efa9a2
+size 4947453488

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ff95b904a5c889425352c348c2d05e43d1e7242cd2b06170fd901183fd4887
+size 4991570824

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de00c13b36b97b2247411a4d6a8e62c9f884ac1895726715bbbe10a505cb6a57
+size 4991570888

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94507822bf942f71595dd0d66b2b6ce333e9150baa078e4b5571cb743c7a7bea
+size 1225814778

model.safetensors.index.json

@@ -0,0 +1,518 @@
+{
+  "metadata": {
+    "total_parameters": 8078174721,
+    "total_size": 16156349442
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.lychee_memory_v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.lychee_memory_v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.lychee_memory_v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.lychee_memory_embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "similarity_head.bias": "model-00004-of-00004.safetensors",
+    "similarity_head.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}