Danielbrdz commited on
Commit
cd1fc84
1 Parent(s): 5b750eb

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Users/danielbarcenas/Downloads/Modelo/DeciLM-6b-instruct",
3
+ "architectures": [
4
+ "DeciLMForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_decilm.DeciLMConfig",
8
+ "AutoModelForCausalLM": "modeling_decilm.DeciLMForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 11008,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "llama",
18
+ "naive_attention_decode_batched": false,
19
+ "naive_attention_decode_single": false,
20
+ "naive_attention_prefill": false,
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "num_key_value_heads_per_layer": [
25
+ 4,
26
+ 2,
27
+ 2,
28
+ 2,
29
+ 2,
30
+ 2,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 1,
36
+ 1,
37
+ 1,
38
+ 1,
39
+ 1,
40
+ 1,
41
+ 1,
42
+ 1,
43
+ 1,
44
+ 1,
45
+ 1,
46
+ 1,
47
+ 1,
48
+ 1,
49
+ 1,
50
+ 1,
51
+ 1,
52
+ 1,
53
+ 1,
54
+ 1,
55
+ 4,
56
+ 4
57
+ ],
58
+ "pad_token_id": 0,
59
+ "pretraining_tp": 1,
60
+ "rms_norm_eps": 1e-05,
61
+ "rope_scaling": {
62
+ "factor": 2.0,
63
+ "type": "dynamic"
64
+ },
65
+ "tie_word_embeddings": false,
66
+ "torch_dtype": "float16",
67
+ "transformers_version": "4.31.0",
68
+ "use_bfloat16": true,
69
+ "use_cache": true,
70
+ "vocab_size": 32000
71
+ }
configuration_decilm.py ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from packaging import version
2
+ import transformers
3
+ if version.parse(transformers.__version__) < version.parse("4.31.0"):
4
+ raise ImportError(
5
+ f"You are using transformers=={transformers.__version__}, but transformers>=4.31.0 is required to use DeciLM. Please upgrade transformers."
6
+ )
7
+ from transformers.models.llama.configuration_llama import LlamaConfig
8
+ from transformers.utils import logging
9
+
10
+
11
+ logger = logging.get_logger(__name__)
12
+
13
+ LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
14
+
15
+
16
+ class DeciLMConfig(LlamaConfig):
17
+ r"""
18
+
19
+ Args:
20
+ num_key_value_heads_per_layer (`List[int]`):
21
+ The number of key-value heads per layer.
22
+ naive_attention_prefill (`bool`, *optional*, defaults to False):
23
+ Whether to use naive matmul or scaled dot product attention during prefill.
24
+ naive_attention_decode_batched (`bool`, *optional*, defaults to True):
25
+ Whether to use naive matmul or scaled dot product attention during decode for batch_size > 1.
26
+ naive_attention_decode_single (`bool`, *optional*, defaults to False):
27
+ Whether to use naive matmul or scaled dot product attention during decode for batch_size == 1.
28
+
29
+
30
+ ```"""
31
+ keys_to_ignore_at_inference = ["past_key_values"]
32
+
33
+ def __init__(
34
+ self,
35
+ num_key_value_heads_per_layer: list = None,
36
+ naive_attention_prefill: bool = False,
37
+ naive_attention_decode_batched: bool = False,
38
+ naive_attention_decode_single: bool = False,
39
+ **kwargs,
40
+ ):
41
+ self.num_key_value_heads_per_layer = num_key_value_heads_per_layer
42
+ self.naive_attention_prefill = naive_attention_prefill
43
+ self.naive_attention_decode_batched = naive_attention_decode_batched
44
+ self.naive_attention_decode_single = naive_attention_decode_single
45
+ super().__init__(**kwargs, )
46
+
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
modeling_decilm.py ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright and license here
3
+ """ PyTorch DeciLM model."""
4
+ import math
5
+ from typing import Optional, Tuple
6
+
7
+ import torch
8
+ import torch.nn.functional as F
9
+ import torch.utils.checkpoint
10
+ from torch import nn
11
+ from packaging import version
12
+ import transformers
13
+ if version.parse(transformers.__version__) < version.parse("4.31.0"):
14
+ raise ImportError(
15
+ f"You are using transformers=={transformers.__version__}, but transformers>=4.31.0 is required to use DeciLM. Please upgrade transformers."
16
+ )
17
+ from transformers.models.llama.modeling_llama import LlamaMLP, LlamaRMSNorm, LlamaAttention, apply_rotary_pos_emb, \
18
+ repeat_kv, LlamaPreTrainedModel, LLAMA_START_DOCSTRING, LlamaDecoderLayer, LlamaForCausalLM, LlamaModel
19
+ from transformers.utils import add_start_docstrings
20
+
21
+ from .configuration_decilm import DeciLMConfig
22
+
23
+ _CONFIG_FOR_DOC = "DeciLMConfig"
24
+
25
+
26
+ class DeciLMAttention(LlamaAttention):
27
+ """Multi-headed attention from 'Attention Is All You Need' paper"""
28
+
29
+ def __init__(self, config: DeciLMConfig, layer_idx: int):
30
+ nn.Module.__init__(self)
31
+ self.config = config
32
+ self.hidden_size = config.hidden_size
33
+ self.num_heads = config.num_attention_heads
34
+ self.head_dim = self.hidden_size // self.num_heads
35
+ self.layer_idx = layer_idx
36
+ self.num_key_value_heads = config.num_key_value_heads_per_layer[layer_idx]
37
+ self.num_key_value_groups = self.num_heads // self.num_key_value_heads
38
+ self.pretraining_tp = config.pretraining_tp
39
+ self.max_position_embeddings = config.max_position_embeddings
40
+ self.rope_theta = getattr(config, 'rope_theta', None)
41
+
42
+ if (self.head_dim * self.num_heads) != self.hidden_size:
43
+ raise ValueError(
44
+ f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}"
45
+ f" and `num_heads`: {self.num_heads})."
46
+ )
47
+ self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
48
+ self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
49
+ self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
50
+ self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
51
+
52
+ self.naive_attention_prefill = config.naive_attention_prefill
53
+ self.naive_attention_decode_batched = config.naive_attention_decode_batched
54
+ self.naive_attention_decode_single = config.naive_attention_decode_single
55
+ self._init_rope()
56
+
57
+ def forward(
58
+ self,
59
+ hidden_states: torch.Tensor,
60
+ attention_mask: Optional[torch.Tensor] = None,
61
+ position_ids: Optional[torch.LongTensor] = None,
62
+ past_key_value: Optional[Tuple[torch.Tensor]] = None,
63
+ output_attentions: bool = False,
64
+ use_cache: bool = False,
65
+ ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
66
+ bsz, q_len, _ = hidden_states.size()
67
+ if past_key_value is None:
68
+ is_decode = False
69
+ else:
70
+ is_decode = True
71
+ if self.pretraining_tp > 1:
72
+ key_value_slicing = (self.num_key_value_heads * self.head_dim) // self.pretraining_tp
73
+ query_slices = self.q_proj.weight.split((self.num_heads * self.head_dim) // self.pretraining_tp, dim=0)
74
+ key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
75
+ value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
76
+
77
+ query_states = [F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)]
78
+ query_states = torch.cat(query_states, dim=-1)
79
+
80
+ key_states = [F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)]
81
+ key_states = torch.cat(key_states, dim=-1)
82
+
83
+ value_states = [F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)]
84
+ value_states = torch.cat(value_states, dim=-1)
85
+
86
+ else:
87
+ query_states = self.q_proj(hidden_states)
88
+ key_states = self.k_proj(hidden_states)
89
+ value_states = self.v_proj(hidden_states)
90
+
91
+ query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
92
+ key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
93
+ value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
94
+
95
+ kv_seq_len = key_states.shape[-2]
96
+ if past_key_value is not None:
97
+ kv_seq_len += past_key_value[0].shape[-2]
98
+ cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
99
+
100
+ query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
101
+
102
+ if past_key_value is not None:
103
+ # reuse k, v, self_attention
104
+ key_states = torch.cat([past_key_value[0], key_states], dim=2)
105
+ value_states = torch.cat([past_key_value[1], value_states], dim=2)
106
+
107
+ past_key_value = (key_states, value_states) if use_cache else None
108
+
109
+ # repeat k/v heads if n_kv_heads < n_heads
110
+ key_states = repeat_kv(key_states, self.num_key_value_groups)
111
+ value_states = repeat_kv(value_states, self.num_key_value_groups)
112
+ if is_decode:
113
+ if self.naive_attention_decode_batched and bsz > 1 or self.naive_attention_decode_single and bsz == 1:
114
+ attn_weights = (query_states @ key_states.transpose(-2, -1)) / math.sqrt(key_states.size(-1))
115
+ attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
116
+ if attention_mask is not None:
117
+ if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
118
+ raise ValueError(
119
+ f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
120
+ )
121
+ attn_weights = attn_weights + attention_mask
122
+
123
+ attn_output = torch.matmul(attn_weights, value_states)
124
+ else:
125
+ attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, is_causal=False,
126
+ dropout_p=0.0)
127
+ attn_output = attn_output.contiguous().view(bsz, q_len, self.hidden_size)
128
+
129
+ else:
130
+ if not self.naive_attention_prefill:
131
+ with torch.backends.cuda.sdp_kernel(enable_math=True, enable_flash=False, enable_mem_efficient=False):
132
+ attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, is_causal=True,
133
+ dropout_p=0.0)
134
+ else:
135
+ attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim)
136
+ if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
137
+ raise ValueError(
138
+ f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
139
+ f" {attn_weights.size()}"
140
+ )
141
+
142
+ if attention_mask is not None:
143
+ if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
144
+ raise ValueError(
145
+ f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
146
+ )
147
+ attn_weights = attn_weights + attention_mask
148
+
149
+ # upcast attention to fp32
150
+ attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
151
+ attn_output = torch.matmul(attn_weights, value_states)
152
+
153
+ if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
154
+ raise ValueError(
155
+ f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
156
+ f" {attn_output.size()}"
157
+ )
158
+
159
+ attn_output = attn_output.transpose(1, 2).contiguous().view(bsz, q_len, self.hidden_size)
160
+
161
+ if self.pretraining_tp > 1:
162
+ attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
163
+ o_proj_slices = self.o_proj.weight.split(self.hidden_size // self.pretraining_tp, dim=1)
164
+ attn_output = sum([F.linear(attn_output[i], o_proj_slices[i]) for i in range(self.pretraining_tp)])
165
+ else:
166
+ attn_output = self.o_proj(attn_output)
167
+
168
+ if not output_attentions:
169
+ attn_weights = None
170
+
171
+ return attn_output, attn_weights, past_key_value
172
+
173
+
174
+ class DeciLMDecoderLayer(LlamaDecoderLayer):
175
+ def __init__(self, config: DeciLMConfig, layer_idx: int):
176
+ nn.Module.__init__(self)
177
+ self.hidden_size = config.hidden_size
178
+ self.layer_idx = layer_idx
179
+ self.self_attn = DeciLMAttention(config=config, layer_idx=layer_idx)
180
+ self.mlp = LlamaMLP(config)
181
+ self.input_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
182
+ self.post_attention_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
183
+
184
+
185
+ @add_start_docstrings(
186
+ "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
187
+ LLAMA_START_DOCSTRING,
188
+ )
189
+ class DeciLMPreTrainedModel(LlamaPreTrainedModel):
190
+ config_class = DeciLMConfig
191
+ _no_split_modules = ["DeciLMDecoderLayer"]
192
+ _keys_to_ignore_on_load_missing = ["self_attn.rotary_emb.inv_freq"]
193
+
194
+
195
+ @add_start_docstrings(
196
+ "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
197
+ LLAMA_START_DOCSTRING,
198
+ )
199
+ class DeciLMModel(LlamaModel, DeciLMPreTrainedModel):
200
+ """
201
+ Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DeciLMDecoderLayer`]
202
+
203
+ Args:
204
+ config: DeciLMConfig
205
+ """
206
+
207
+ def __init__(self, config: DeciLMConfig):
208
+ DeciLMPreTrainedModel.__init__(self, config)
209
+ self.padding_idx = config.pad_token_id
210
+ self.vocab_size = config.vocab_size
211
+
212
+ self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
213
+ self.layers = nn.ModuleList([DeciLMDecoderLayer(config, layer_idx) for layer_idx
214
+ in range(config.num_hidden_layers)])
215
+ self.norm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
216
+
217
+ self.gradient_checkpointing = False
218
+ # Initialize weights and apply final processing
219
+ self.post_init()
220
+
221
+ def _prepare_decoder_attention_mask(self, attention_mask, input_shape, inputs_embeds, past_key_values_length):
222
+ self._validate_config_supports_attention_mask(attention_mask, input_shape, past_key_values_length)
223
+ return LlamaModel._prepare_decoder_attention_mask(
224
+ self, attention_mask, input_shape, inputs_embeds, past_key_values_length)
225
+
226
+ def _validate_config_supports_attention_mask(self, attention_mask, input_shape, past_key_values_length):
227
+ is_decode = past_key_values_length > 0
228
+ if not torch.all(torch.eq(attention_mask, 1)).item():
229
+ if is_decode:
230
+ if input_shape[0] == 1 and not self.config.naive_attention_decode_single:
231
+ raise ValueError(
232
+ "For support of custom attention masks please set naive_attention_decode_single to True in the "
233
+ "config")
234
+ elif input_shape[0] > 1 and not self.config.naive_attention_decode_batched:
235
+ raise ValueError(
236
+ "For support of custom attention masks please set naive_attention_decode_batched to True in the"
237
+ "config")
238
+ else:
239
+ if not self.config.naive_attention_prefill:
240
+ raise ValueError("For support of custom attention masks please set naive_attention_prefill to "
241
+ "True in the config")
242
+
243
+
244
+ class DeciLMForCausalLM(LlamaForCausalLM, DeciLMPreTrainedModel):
245
+ def __init__(self, config):
246
+ DeciLMPreTrainedModel.__init__(self, config)
247
+ self.model = DeciLMModel(config)
248
+ self.pretraining_tp = config.pretraining_tp
249
+ self.vocab_size = config.vocab_size
250
+ self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
251
+
252
+ # Initialize weights and apply final processing
253
+ self.post_init()
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64533b61dc590a29d272551929aa6acc239f1881aa79a46c477b05f341a7bbc
3
+ size 9959940028
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba4cce11fe1e7584af8f087a76a7d7207ba6280598f3718903921a2b403cfe3
3
+ size 1474384343
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11434213376
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }