umyunsang/GovOn-EXAONE-AWQ-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: umyunsang/GovOn-EXAONE-AWQ-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-10 20:08:11 +08:00
commit ff9b045879
15 changed files with 620372 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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

60
README.md Normal file
View File

@@ -0,0 +1,60 @@
---
language:
- ko
- en
license: apache-2.0
base_model: umyunsang/GovOn-EXAONE-Merged-v2
tags:
- exaone
- civil-complaint
- govon
- korean
- awq
- 4bit
- quantization
- on-device
pipeline_tag: text-generation
---
# GovOn-EXAONE-AWQ-v2
## Introduction
**GovOn-EXAONE-AWQ-v2** is an optimized 4-bit quantized version of [GovOn-EXAONE-Merged-v2](https://huggingface.co/umyunsang/GovOn-EXAONE-Merged-v2), designed for **On-Device** and **low-latency** deployment in civil service environments.
By applying **AWQ (Activation-aware Weight Quantization)** (W4A16g128), we reduced the model size by **66.1% (from 14.56GB to 4.94GB)** while preserving domain-specific performance. This enables high-quality Korean civil complaint assistance on consumer-grade GPUs with as little as 8GB of VRAM.
## Quickstart
We recommend using `vLLM` or `AutoAWQ` for optimized inference.
### Using AutoAWQ
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_id = "umyunsang/GovOn-EXAONE-AWQ-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoAWQForCausalLM.from_quantized(model_id, fuse_layers=True, trust_remote_code=True)
# (Inference code same as Merged-v2)
```
## Specifications
### Model Details
- **Source Model**: [umyunsang/GovOn-EXAONE-Merged-v2](https://huggingface.co/umyunsang/GovOn-EXAONE-Merged-v2)
- **Quantization Method**: AWQ (Weight-only 4-bit)
- **Config**: W4A16, Group Size 128, Zero Point True
- **Model Size**: 4.94 GB (BF16 Original: 14.56 GB)
- **VRAM Required**: ~6.5 GB (Inference)
### Efficiency
- **Compression Ratio**: 2.95x
- **Size Reduction**: 66.1%
- **Calibration**: 512 domain-specific civil complaint samples
## Limitation and Usage
1. **Quantization Loss**: While AWQ minimizes performance drops, slight deviations in CoT (`<thought>`) or nuanced reasoning might occur compared to the BF16 version.
2. **Infrastructure**: Optimized for NVIDIA GPUs (Ampere architecture or newer recommended).
## License
This model is licensed under the **Apache License 2.0**. However, users must also comply with the [EXAONE AI Model License Agreement](https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct/blob/main/LICENSE) of the base model.

48
config.json Normal file
View File

@@ -0,0 +1,48 @@
{
"_name_or_path": "/content/models/merged_model",
"activation_function": "silu",
"architectures": [
"ExaoneForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_exaone.ExaoneConfig",
"AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
"AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
},
"bos_token_id": 1,
"embed_dropout": 0.0,
"eos_token_id": 361,
"head_dim": 128,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 32768,
"model_type": "exaone",
"num_attention_heads": 32,
"num_key_value_heads": 8,
"num_layers": 32,
"pad_token_id": 0,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 1000000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.49.0",
"use_cache": false,
"vocab_size": 102400
}

182
configuration_exaone.py Normal file
View File

@@ -0,0 +1,182 @@
# coding=utf-8
# Copyright 2021 The LG AI Research EXAONE Lab. 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.
"""EXAONE model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
EXAONE_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
class ExaoneConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`ExaoneModel`]. It is used to
instantiate a EXAONE 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 EXAONE-3.0-7.8B-Instruct [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)
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 EXAONE model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`ExaoneModel`]. Vocabulary size of the model.
Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of
[`ExaoneModel`].
max_position_embeddings (`int`, *optional*, defaults to 2048):
The maximum sequence length that this model might ever be used with. Typically set this to something large
just in case (e.g., 512 or 1024 or 2048).
hidden_size (`int`, *optional*, defaults to 2048):
Dimensionality of the encoder layers and the pooler layer.
num_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 decoder.
num_key_value_heads (`int`, *optional*):
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
by meanpooling all the original heads within that group. For more details checkout [this
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
`num_attention_heads`.
intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
activation_function (`str` or `function`, *optional*, defaults to `"silu"`):
The non-linear activation function (function or string) in the decoder.
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. NOTE: if you apply new rope type
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
accordingly.
Expected contents:
`rope_type` (`str`):
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
'llama3'], with 'default' being the original RoPE implementation.
`factor` (`float`, *optional*):
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
original maximum pre-trained length.
`original_max_position_embeddings` (`int`, *optional*):
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
pretraining.
`attention_factor` (`float`, *optional*):
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
computation. If unspecified, it defaults to value recommended by the implementation, using the
`factor` field to infer the suggested value.
`beta_fast` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
ramp function. If unspecified, it defaults to 32.
`beta_slow` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
ramp function. If unspecified, it defaults to 1.
`short_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`long_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`low_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
`high_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
embed_dropout (`float`, *optional*, defaults to 0.0):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
The epsilon used by the layer normalization layers.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
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``.
bos_token_id (`int`, *optional*, defaults to 0):
Beginning of stream token id.
eos_token_id (`int`, *optional*, defaults to 2):
End of stream token id.
Example:
```python
>>> from transformers import EXAONEModel, ExaoneConfig
>>> # Initializing a EXAONE configuration
>>> configuration = ExaoneConfig()
>>> # Initializing a model from configuration
>>> model = EXAONEModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "exaone"
keys_to_ignore_at_inference = ["past_key_values"]
attribute_map = {"num_hidden_layers": "num_layers"}
def __init__(
self,
vocab_size=102400,
max_position_embeddings=2048,
hidden_size=2048,
num_layers=32,
num_attention_heads=32,
num_key_value_heads=None,
intermediate_size=None,
activation_function="silu",
rope_theta=10000.0,
rope_scaling=None,
embed_dropout=0.0,
attention_dropout=0.0,
layer_norm_epsilon=1e-5,
initializer_range=0.02,
use_cache=True,
bos_token_id=0,
eos_token_id=2,
**kwargs,
):
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.num_layers = num_layers
self.num_attention_heads = num_attention_heads
if num_key_value_heads is None:
num_key_value_heads = num_attention_heads
self.num_key_value_heads = num_key_value_heads
if intermediate_size:
self.intermediate_size = intermediate_size
else:
self.intermediate_size = hidden_size * 4
self.activation_function = activation_function
self.embed_dropout = embed_dropout
self.attention_dropout = attention_dropout
self.layer_norm_epsilon = layer_norm_epsilon
self.initializer_range = initializer_range
self.use_cache = use_cache
self.rope_theta = rope_theta
self.rope_scaling = rope_scaling
self.bos_token_id = bos_token_id
self.eos_token_id = eos_token_id
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"do_sample": true,
"eos_token_id": 361,
"pad_token_id": 0,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.49.0"
}

101783
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91ef6333576c40629bd7b3c9b2e6461c8b956fa69db08d838eb12025d325b7a5
size 4465454112

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5a595e8e4eeb32fb568aebcfd80b02dd2e098d060947aed79bb46e09a31172f
size 838860928

746
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,746 @@
{
"metadata": {
"total_size": 5304229888
},
"weight_map": {
"transformer.wte.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.0.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.1.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.2.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.3.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.4.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.5.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.6.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.7.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.8.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.9.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.10.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.11.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.12.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.13.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.14.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.15.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.16.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.17.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.18.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.19.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.20.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.21.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.22.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.23.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.24.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.25.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.26.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.27.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.28.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.29.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.30.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
"transformer.h.31.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
"transformer.ln_f.weight": "model-00001-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors"
}
}

1394
modeling_exaone.py Normal file
View File

File diff suppressed because it is too large Load Diff

18
quantization_log.json Normal file
View File

@@ -0,0 +1,18 @@
{
"stage": "2_awq_quantization_v2",
"timestamp": "2026-03-19T10:52:52.952927",
"merged_model_dir": "/content/models/merged_model",
"output_dir": "/content/models/awq_quantized_model",
"quant_config": {
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
},
"calibration_samples": 512,
"awq_model_size_gb": 4.940028339624405,
"merged_model_size_gb": 14.563027188181877,
"compression_ratio": 2.947964300400981,
"size_reduction_pct": 66.07828663786802,
"quantization_time_seconds": 1117.1531629562378
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "[|endofturn|]",
"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
}
}

512837
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3222
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long