Upload folder using huggingface_hub

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 4,
+  "attn_layer_period": 8,
+  "auto_map": {
+    "AutoConfig": "configuration_jamba.JambaConfig",
+    "AutoModel": "modeling_jamba.JambaModel",
+    "AutoModelForCausalLM": "modeling_jamba.JambaForCausalLM",
+    "AutoModelForSequenceClassification": "model.JambaForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "calc_logits_for_entire_prompt": false,
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
+  "mamba_expand": 2,
+  "mamba_inner_layernorms": true,
+  "mamba_proj_bias": false,
+  "model_type": "jamba",
+  "n_ctx": 262144,
+  "num_attention_heads": 32,
+  "num_experts": 1,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 65536
+}

configuration_jamba.py

@@ -0,0 +1,213 @@
+# coding=utf-8
+# Copyright 2024 AI21 Labs Ltd. 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.
+""" Jamba model configuration"""
+import math
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class JambaConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`JambaModel`]. It is used to instantiate a
+    Jamba 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 jamba-small architecture.
+
+    [ai21labs/jamba-small](https://huggingface.co/ai21labs/Jamba-v0.1)
+
+    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 65536):
+            Vocabulary size of the Jamba model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`JambaModel`]
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied. Note that this is only relevant if the
+            model has a output word embedding layer.
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 14336):
+            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 8):
+            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 `8`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        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`.
+        calc_logits_for_entire_prompt (`bool`, *optional*, defaults to `False`):
+            Whether or not to calculate logits for entire prompt during generation. If `False`, only the logits of the
+            last prompt token will be calculated, which are the only logits needed for generation. For long sequences,
+            the logits for the entire sequence may use a lot of memory so setting `calc_logits_for_entire_prompt=False`
+            will reduce memory footprint significantly.
+            Note: some generation features may not be available if this is set to `False`.
+        output_router_logits (`bool`, *optional*, defaults to `False`):
+            Whether or not the router logits should be returned by the model. Enabling this will also
+            allow the model to output the auxiliary loss. See [here]() for more details
+        router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
+            The aux loss factor for the total loss.
+        pad_token_id (`int`, *optional*, defaults to 0):
+            The id of the padding token.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            The id of the "end-of-sequence" token.
+        sliding_window (`int`, *optional*):
+            Sliding window attention window size. If not specified, will default to `None`.
+        n_ctx (`int`, *optional*, defaults to 262144):
+            This value doesn't have any real effect. The maximum sequence length that this model is intended to be
+            used with. It can be used with longer sequences, but performance may degrade.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        num_experts_per_tok (`int`, *optional*, defaults to 2):
+            The number of experts to root per-token, can be also interpreted as the `top-p` routing
+            parameter
+        num_experts (`int`, *optional*, defaults to 16):
+            Number of experts per Sparse MLP layer.
+        expert_layer_period (`int`, *optional*, defaults to 2):
+            Once in this many layers, we will have an expert layer
+        expert_layer_offset (`int`, *optional*, defaults to 1):
+            The first layer index that contains an expert mlp layer
+        attn_layer_period (`int`, *optional*, defaults to 8):
+            Once in this many layers, we will have a vanilla attention layer
+        attn_layer_offset (`int`, *optional*, defaults to 4):
+            The first layer index that contains a vanilla attention mlp layer
+        use_mamba_kernels (`bool`, *optional*, defaults to `True`):
+            Flag indicating whether or not to use the fast mamba kernels. These are available only if `mamba-ssm` and
+            `causal-conv1d` are installed, and the mamba modules are running on a CUDA device. Raises ValueError if
+            `True` and kernels are not available
+        mamba_d_state (`int`, *optional*, defaults to 16):
+            The dimension the mamba state space latents
+        mamba_d_conv (`int`, *optional*, defaults to 4):
+            The size of the mamba convolution kernel
+        mamba_expand (`int`, *optional*, defaults to 2):
+            Expanding factor (relative to hidden_size) used to determine the mamba intermediate size
+        mamba_dt_rank (`Union[int,str]`, *optional*, defaults to `"auto"`):
+            Rank of the the mamba discretization projection matrix. `"auto"` means that it will default to `math.ceil(self.hidden_size / 16)`
+        mamba_conv_bias (`bool`, *optional*, defaults to `True`):
+            Flag indicating whether or not to use bias in the convolution layer of the mamba mixer block.
+        mamba_proj_bias (`bool`, *optional*, defaults to `False`):
+            Flag indicating whether or not to use bias in the input and output projections (["in_proj", "out_proj"]) of the mamba mixer block
+        mamba_inner_layernorms (`bool`, *optional*, defaults to `True`):
+            Flag indicating whether or not to apply layernorms to internal mamba activations
+
+    """
+
+    model_type = "jamba"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+            self,
+            vocab_size=65536,
+            tie_word_embeddings=False,
+            hidden_size=4096,
+            intermediate_size=14336,
+            num_hidden_layers=32,
+            num_attention_heads=32,
+            num_key_value_heads=8,
+            hidden_act="silu",
+            initializer_range=0.02,
+            rms_norm_eps=1e-6,
+            use_cache=True,
+            calc_logits_for_entire_prompt=False,
+            output_router_logits=False,
+            router_aux_loss_coef=0.001,
+            pad_token_id=0,
+            bos_token_id=1,
+            eos_token_id=2,
+            sliding_window=None,
+            n_ctx=262144,
+            attention_dropout=0.0,
+            num_experts_per_tok=2,
+            num_experts=16,
+            expert_layer_period=2,
+            expert_layer_offset=1,
+            attn_layer_period=8,
+            attn_layer_offset=4,
+            use_mamba_kernels=True,
+            mamba_d_state=16,
+            mamba_d_conv=4,
+            mamba_expand=2,
+            mamba_dt_rank="auto",
+            mamba_conv_bias=True,
+            mamba_proj_bias=False,
+            mamba_inner_layernorms=True,
+            **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.tie_word_embeddings = tie_word_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.sliding_window = sliding_window
+        self.n_ctx = n_ctx
+        self.attention_dropout = attention_dropout
+
+        # 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.calc_logits_for_entire_prompt = calc_logits_for_entire_prompt
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+
+        self.num_experts_per_tok = num_experts_per_tok
+        self.num_experts = num_experts
+        self.expert_layer_period = expert_layer_period
+        self.expert_layer_offset = expert_layer_offset
+        self.attn_layer_period = attn_layer_period
+        self.attn_layer_offset = attn_layer_offset
+
+        self.use_mamba_kernels = use_mamba_kernels
+        self.mamba_d_state = mamba_d_state
+        self.mamba_d_conv = mamba_d_conv
+        self.mamba_expand = mamba_expand
+        self.mamba_dt_rank = math.ceil(self.hidden_size / 16) if mamba_dt_rank == "auto" else mamba_dt_rank
+        self.mamba_conv_bias = mamba_conv_bias
+        self.mamba_proj_bias = mamba_proj_bias
+        self.mamba_inner_layernorms = mamba_inner_layernorms
+
+        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,
+        )

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c60b5778b6856888ca24447b3880c39a777e523e5fb94dd18ed33d9532d01f0
+size 4916251136

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aa641dcb763378138fd1b4151c0726c8e06969417f1ddaccbcb04a6de69c79
+size 4941976032

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ab7424c95e53b2a769629468ecfb953cdc2f65790d5fa2acea4f27d567b538
+size 4941976080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9698548b8ec18b2258676c33df63f0c96986aa9a5c0846decc31c58e9d8a1e5c
+size 3788575776

model.safetensors.index.json

@@ -0,0 +1,522 @@
+{
+  "metadata": {
+    "total_size": 18588720896
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.final_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_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.weight": "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.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.17.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.17.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_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.weight": "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.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.B_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.C_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.moe.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.moe.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.moe.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_moe_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.A_log": "model-00003-of-00004.safetensors",
+    "model.layers.26.mamba.B_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.C_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.D": "model-00003-of-00004.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mamba.dt_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.dt_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.dt_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mamba.x_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.B_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.C_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.D": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.conv1d.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.dt_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.dt_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.dt_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mamba.x_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.B_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.C_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.D": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.conv1d.bias": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.dt_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.dt_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.dt_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mamba.x_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.B_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.C_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.D": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.conv1d.bias": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.dt_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.dt_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.dt_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mamba.x_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.A_log": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.B_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.C_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.D": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.conv1d.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.dt_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.dt_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.dt_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mamba.x_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.moe.experts.0.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.moe.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.moe.experts.0.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.pre_moe_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_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.weight": "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.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.B_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.C_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.moe.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.moe.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.moe.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.pre_moe_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.A_log": "model-00001-of-00004.safetensors",
+    "model.layers.8.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.D": "model-00001-of-00004.safetensors",
+    "model.layers.8.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.A_log": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.B_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.C_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.D": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.moe.experts.0.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.moe.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.moe.experts.0.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_moe_layernorm.weight": "model-00002-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
+size 1124742

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}