add model

.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

README.md

@@ -0,0 +1,186 @@
+---
+language:
+- en
+tags:
+- moe
+- fp8
+- vllm
+license: other
+license_name: deepseek
+license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
+library_name: transformers
+---
+
+# DeepSeek-V2.5-1210-FP8
+
+## Model Overview
+- **Model Architecture:** DeepSeek-V2.5-1210
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP8
+  - **Activation quantization:** FP8
+- **Release Date:** 3/1/2025
+- **Version:** 1.0
+- **Model Developers:** Neural Magic
+
+Quantized version of [DeepSeek-V2.5-1210](https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210).
+It achieves an average score of 77.8 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 77.82.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights and activations to FP8 data type, ready for inference with vLLM >= 0.5.2.
+This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. The weights and activations of the linear operators within transformers blocks are quantized, except the MLP routers. 
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from transformers import AutoTokenizer
+from vllm import LLM, SamplingParams
+
+max_model_len, tp_size = 4096, 4
+model_name = "neuralmagic-ent/DeepSeek-V2.5-1210-FP8"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
+sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
+
+messages_list = [
+    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
+]
+
+prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
+
+outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
+
+generated_text = [output.outputs[0].text for output in outputs]
+print(generated_text)
+```
+
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below with the following command:
+
+```bash
+python quantize.py --model_path deepseek-ai/DeepSeek-V2.5-1210 --quant_path "output_dir" --calib_size 128
+```
+
+
+```python
+import argparse
+from datasets import load_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot
+from llmcompressor.transformers.compression.helpers import calculate_offload_device_map
+import torch
+import os
+
+
+def main():
+    # Set up command line argument parsing
+    parser = argparse.ArgumentParser(description='Quantize a transformer model to FP8')
+    parser.add_argument('--model_id', type=str, required=True,
+                        help='The model ID from HuggingFace (e.g., "meta-llama/Meta-Llama-3-8B-Instruct")')
+    parser.add_argument('--save_path', type=str, default='.',
+                        help='Custom path to save the quantized model. If not provided, will use model_name-FP8')
+    parser.add_argument('--calib_size', type=int, default=256)
+    args = parser.parse_args()
+
+    device_map = calculate_offload_device_map(
+        args.model_id,
+        reserve_for_hessians=False,
+        num_gpus=torch.cuda.device_count(),
+        trust_remote_code=True,
+        torch_dtype=torch.bfloat16,
+    )
+
+    model = AutoModelForCausalLM.from_pretrained(
+        args.model_id, device_map=device_map, torch_dtype=torch.bfloat16, trust_remote_code=True,
+    )
+    tokenizer = AutoTokenizer.from_pretrained(args.model_id)
+
+    NUM_CALIBRATION_SAMPLES = args.calib_size
+    DATASET_ID = "garage-bAInd/Open-Platypus"
+    DATASET_SPLIT = "train"
+    ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
+    ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+
+    def preprocess(example):
+        concat_txt = example["instruction"] + "\n" + example["output"]
+        return {"text": concat_txt}
+
+    ds = ds.map(preprocess)
+
+    def tokenize(sample):
+        return tokenizer(
+            sample["text"],
+            padding=False,
+            truncation=False,
+            add_special_tokens=True,
+        )
+
+    ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+    # Configure the quantization algorithm and scheme
+    recipe = QuantizationModifier(
+        targets="Linear", scheme="FP8", ignore=["lm_head", "re:.*\.mlp\.gate$"]
+    )
+
+    # Apply quantization
+    oneshot(
+        model=model,
+        dataset=ds,
+        recipe=recipe,
+        num_calibration_samples=args.calib_size
+    )
+
+    save_path = os.path.join(args.save_path, args.model_id.split("/")[1] + "-FP8")
+    os.makedirs(save_path, exist_ok=True)
+
+    # Save to disk in compressed-tensors format
+    model.save_pretrained(save_path, save_compressed=True, skip_compression_stats=True)
+    tokenizer.save_pretrained(save_path)
+    print(f"Model and tokenizer saved to: {save_path}")
+
+if __name__ == "__main__":
+    main()
+```
+
+## Evaluation
+
+The model was evaluated on OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard) using the following command:
+
+OpenLLM Leaderboard V1:
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic-ent/DeepSeek-V2.5-1210-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=4,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
+  --tasks openllm \
+  --write_out \
+  --batch_size auto \
+  --output_path output_dir \
+  --show_config
+```
+
+
+### Accuracy
+
+#### OpenLLM Leaderboard V1 evaluation scores
+
+| Metric                                   | deepseek-ai/DeepSeek-V2.5-1210             | neuralmagic-ent/DeepSeek-V2.5-1210-FP8 |
+|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
+| ARC-Challenge (Acc-Norm, 25-shot)       | 72.61                            | 72.44                                       |
+| GSM8K (Strict-Match, 5-shot)            | 88.25                            | 88.02                                       |
+| HellaSwag (Acc-Norm, 10-shot)           | 85.01                            | 84.75                                       |
+| MMLU (Acc, 5-shot)                      | 79.60                            | 79.44                                       |
+| TruthfulQA (MC2, 0-shot)                | 57.18                            | 57.53                                       |
+| Winogrande (Acc, 5-shot)                | 84.29                            | 84.61                                       |
+| **Average Score**                       | **77.82**                        | **77.80**                                   |
+| **Recovery**                            | **100.00**                       | **99.97**                                   |
+

config.json

@@ -0,0 +1,103 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-V2.5-1210",
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-V2.5-1210--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-V2.5-1210--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-V2.5-1210--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1536,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 160,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 128,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.5935207871800965,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 16.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 3,
+  "topk_method": "group_limited_greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}

configuration_deepseek.py

@@ -0,0 +1,206 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV2Model`]. It is used to instantiate an DeepSeek
+    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 DeepSeek-V2.
+
+    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 102400):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV2Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV2Model, DeepseekV2Config
+
+    >>> # Initializing a Deepseek-V2 style configuration
+    >>> configuration = DeepseekV2Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v2"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=102400,
+        hidden_size=4096,
+        intermediate_size=11008,
+        moe_intermediate_size = 1407,
+        num_hidden_layers=30,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        n_shared_experts = None,
+        n_routed_experts = None,
+        ep_size = 1,
+        routed_scaling_factor = 1.0,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'gready',
+        n_group = None,
+        topk_group = None,
+        num_experts_per_tok = None,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 0,
+        norm_topk_prob = False,
+        scoring_func = 'softmax',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=100000,
+        eos_token_id=100001,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "do_sample": true,
+  "eos_token_id": 100001,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471efd450dbaf240a96e7b629ed7fca399289842401d191fd8235aad4c56f9bc
+size 4996270948

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febb24c8eeedcfbdd81de8f21a5fcdbab6a3e33f5d55b5902f1e968b00afe71e
+size 4996995084

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceba9e82bcec6925a69301d0ebfc973e5223c024525dcb5ef3edbb1a535a32f4
+size 4995531320

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92a71fb4c5b2d96e754ab0c946c851c69eaed494c887a49198fde06123f2da1
+size 4995532432

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b3f4e4ee3ba09cbf8a6c4a5388a2fcc86558d5cf073187b535de2c722e1ca6
+size 4995533784

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060507abc07620bd5fd073310e8ebd7aba6a06ce74576993f5b9a0201b58cfea
+size 4996995156

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc932ae56b3105bd8a43a33b68e2f999540bf5628932d6dd18768f152e8c936
+size 4995531440

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d895ff67b4fdb1374f7c50ce9285719e9211ed8deb4876716bed625cee4d6b
+size 4995528376

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8b17a934b36e829a556634b468012e11039c36d4c265377deb37d2a1c70950
+size 4995535760

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb44a4397272bf232f452bb53e11a30e85c32f27825279fbe3bc64cfa4eb68b
+size 4996997044

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d9defe3ba8c87a6d26e97ad2f142ccd6dfd8d120dcfca027869eed98f1664a0
+size 4995533416

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d58c3d5759bd5b2470183cd806cd29f061d1a060830ffa11ed1b7dd2b3dcd2
+size 4995534624

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be59946250c98d251b013440a9ca308675dfd263f000bc95bc81d9b4a6bacd6e
+size 4989308980

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3033b15f660d78a88bc4654bb014870f40994a9c34280a93ca065adcdda24c
+size 4995355444

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925610d291086e7c8d84902b471168c0818b64cf331cac1eaac0cb196e75cae8
+size 4995533520

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff10dfd512f9ecd74b59d6d91594217458a33add32186f206b5cb4880d94a66
+size 4995534776

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e81829b480b83b1cdb1261483707a6938ffd6241579fe825be45a35a1cd897
+size 4960298320

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1afdd44953d34e57ccda71378f046e74eb8f17dd941fad994997cb5e6012ff1
+size 4992907440

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5079a7e235c7869da6923f473bd700629420593cd09f44d169d8f4e8cde73a79
+size 4995533608

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5748a36dbbbe35b962ac0c996c5227a2f379318230663a6c88eebdea38cf16b
+size 4995534888

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e8127385d3f4d6fd9b315724bdf1d8be9c5e1a071f7a8b7fe74e16b1631af4
+size 4996996668

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb818c042d28bef33048a8b9d7a1eb5ab396da5023fc2f09691d7cc07096bc37
+size 4995532608

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6202affe540725174ab2a56a0e58f775dc1241b8878a0555881a4afd88c1af
+size 4995533728

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f61dc9d140b85898fd2a97ce5295e13694cc347b226a0bcdf496b6d5295293
+size 4995535048

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c3d8be0bae69f051cf18242fa99e2d75c3a9029a4b0cf4316debc8d38597f2
+size 4996996700

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b69f67d0ed8be010d917cdd1eb182d183d9a92b41dc8cda914de2a7c15312f8
+size 4995532768

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da5107606089e3dcbc99131d4538a57e7346887614ff00b2993f4cba0481269
+size 4995533848

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6311c9f449de8b3d8a51a589d9a618c990ddd8b478684cc2c9a959e87d7cfe81
+size 4995535216

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdd18f1cb5a2c6ca21d5673b4e1670fd75403125f99267afa33615f4260e1d4
+size 4996996740

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d15cdb6444dfdcc91dd4c03f4ffb4b4338231f053655694ce097c1dcc722e0e
+size 4995532920

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b1642e38d1b1d92b32d6e9e74485293006afa3bc693e48dbdaaf355fa6653c
+size 4995533968

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6ff131bfcdb3a94b6ae9b6f6152062ba7bd827e66165fc96a662f5723fe67a
+size 4995535384

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687be01abac467ecd8885fd89948b6db1db696ae49161242bc4056a0518d658a
+size 4996996812

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdea5fe86b274b57dd8454ab336fd19ee472b3188d427266383bf7d40dab9a2
+size 4995533040

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa214be2566f4312368665b2905ac3dc7c9e36d2a7c012c214dd08a2bd5e61c9
+size 4995534112

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b512d4d93ee8dc486f7fb6bbb915dd161996e61d74910a236ac95ef4f3b2d4ae
+size 4995535520

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9acfb4d5f521b8622c3409f398df6058ba2a1366e476d2de3899be8ece3cc5
+size 4996996892

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7870dcdf7213a0452758e2cc6d19c0b044f5b21f85e03fa6ccd74b889e1d2994
+size 4995533160

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aef01efe0ece26a9f580f23558fec148e074d13947474504ff4ddfdfad182d1
+size 4995534280

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3adaf1f40f88e16e4fb32addd394a5baabdc79c9504931cdd008c86a6ad814
+size 4995535640

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52eb4b203192e492f818df1c0f8799738dd9f111c807422c21507e7585d00ba1
+size 4996996964

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c2b0593bfde92f235cd055fc0dd4feeda1461daab4bbbdf124e8ccfe6b5688
+size 4995533280

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b079797af051a2c71df213edf1e0007d35566351b4218a72c11a2d74728c800
+size 4995534448

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5ffa4df53bc17884ce8ac6382395f114db2023ed2346b07b35b5487a97f708
+size 4995535760

model-00045-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8577db7dc2a002c3ac0c90c64d3d68b091a0ab395dd01d976e8ad93325a5d315
+size 4996997044