Commit
•
1a87f3c
1
Parent(s):
f667769
Upgrade to AquilaChat-7B v0.6 configurations
Browse files- BAAI_Aquila_Model_License.pdf +0 -0
- BAAI_Aquila_Model_License_Agreement.pdf +0 -0
- config.json +2 -3
- convert_aquila_weights_to_hf.py +38 -30
- generation_config.json +1 -1
- modeling_aquila.py +1 -1
- pytorch_model.bin.index.json +324 -324
- tokenizer.json +1 -1
BAAI_Aquila_Model_License.pdf
DELETED
|
Binary file (225 kB)
|
|
|
BAAI_Aquila_Model_License_Agreement.pdf
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "aquilachat-7b-hf",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -21,8 +20,8 @@
|
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
-
"torch_dtype": "
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"unk_token_id": 0,
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 100008
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LlamaForCausalLM"
|
| 4 |
],
|
|
|
|
| 20 |
"pad_token_id": 0,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.29.2",
|
| 25 |
"unk_token_id": 0,
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 100008
|
convert_aquila_weights_to_hf.py
CHANGED
|
@@ -13,16 +13,17 @@
|
|
| 13 |
# limitations under the License.
|
| 14 |
import argparse
|
| 15 |
import gc
|
|
|
|
| 16 |
import json
|
| 17 |
import math
|
| 18 |
import os
|
| 19 |
import shutil
|
| 20 |
import warnings
|
| 21 |
-
|
| 22 |
import torch
|
|
|
|
| 23 |
|
| 24 |
from transformers import LlamaConfig, LlamaForCausalLM, LlamaTokenizer
|
| 25 |
-
|
| 26 |
|
| 27 |
try:
|
| 28 |
from transformers import LlamaTokenizerFast
|
|
@@ -44,10 +45,10 @@ python src/transformers/models/llama/convert_llama_weights_to_hf.py \
|
|
| 44 |
Thereafter, models can be loaded via:
|
| 45 |
|
| 46 |
```py
|
| 47 |
-
from transformers import
|
| 48 |
|
| 49 |
-
model =
|
| 50 |
-
tokenizer =
|
| 51 |
```
|
| 52 |
|
| 53 |
Important note: you need to be able to host the whole model in RAM to execute this script (even if the biggest versions
|
|
@@ -93,6 +94,8 @@ def write_model(model_path, input_base_path, model_size):
|
|
| 93 |
print("params: ", params)
|
| 94 |
|
| 95 |
num_shards = NUM_SHARDS[model_size]
|
|
|
|
|
|
|
| 96 |
n_layers = params["n_layers"]
|
| 97 |
n_heads = params["n_heads"]
|
| 98 |
n_heads_per_shard = n_heads // num_shards
|
|
@@ -100,23 +103,9 @@ def write_model(model_path, input_base_path, model_size):
|
|
| 100 |
dims_per_head = dim // n_heads
|
| 101 |
base = 10000.0
|
| 102 |
inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
|
| 103 |
-
|
| 104 |
-
""
|
| 105 |
-
params = {}
|
| 106 |
-
num_shards = 1
|
| 107 |
-
n_layers = 32
|
| 108 |
-
n_heads = 32
|
| 109 |
-
n_heads_per_shard = n_heads // num_shards
|
| 110 |
-
dim = 4096
|
| 111 |
-
dims_per_head = dim // n_heads
|
| 112 |
-
base = 10000.0
|
| 113 |
-
inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
|
| 114 |
|
| 115 |
-
params["n_layers"] = n_layers
|
| 116 |
-
params["n_heads"] = n_heads
|
| 117 |
-
params["dim"] = dim
|
| 118 |
-
params["norm_eps"] = 1e-05
|
| 119 |
-
"""
|
| 120 |
|
| 121 |
# permute for sliced rotary
|
| 122 |
def permute(w):
|
|
@@ -246,6 +235,17 @@ def write_model(model_path, input_base_path, model_size):
|
|
| 246 |
num_hidden_layers=params["n_layers"],
|
| 247 |
rms_norm_eps=params["norm_eps"],
|
| 248 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 249 |
config.save_pretrained(tmp_model_path)
|
| 250 |
|
| 251 |
# Make space so we can load the model properly now.
|
|
@@ -263,13 +263,20 @@ def write_model(model_path, input_base_path, model_size):
|
|
| 263 |
shutil.rmtree(tmp_model_path)
|
| 264 |
|
| 265 |
|
| 266 |
-
def write_tokenizer(
|
| 267 |
-
|
| 268 |
-
|
| 269 |
-
print(f"Saving a {tokenizer_class.__name__} to {
|
| 270 |
-
tokenizer
|
| 271 |
-
tokenizer.save_pretrained(tokenizer_path)
|
| 272 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 273 |
|
| 274 |
def main():
|
| 275 |
parser = argparse.ArgumentParser()
|
|
@@ -286,6 +293,7 @@ def main():
|
|
| 286 |
help="Location to write HF model and tokenizer",
|
| 287 |
)
|
| 288 |
args = parser.parse_args()
|
|
|
|
| 289 |
if args.model_size != "tokenizer_only":
|
| 290 |
write_model(
|
| 291 |
model_path=args.output_dir,
|
|
@@ -293,9 +301,9 @@ def main():
|
|
| 293 |
input_base_path=args.input_dir,
|
| 294 |
model_size=args.model_size,
|
| 295 |
)
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
|
| 300 |
if __name__ == "__main__":
|
| 301 |
main()
|
|
|
|
| 13 |
# limitations under the License.
|
| 14 |
import argparse
|
| 15 |
import gc
|
| 16 |
+
import glob
|
| 17 |
import json
|
| 18 |
import math
|
| 19 |
import os
|
| 20 |
import shutil
|
| 21 |
import warnings
|
|
|
|
| 22 |
import torch
|
| 23 |
+
import urllib
|
| 24 |
|
| 25 |
from transformers import LlamaConfig, LlamaForCausalLM, LlamaTokenizer
|
| 26 |
+
from transformers import GPTNeoXTokenizerFast
|
| 27 |
|
| 28 |
try:
|
| 29 |
from transformers import LlamaTokenizerFast
|
|
|
|
| 45 |
Thereafter, models can be loaded via:
|
| 46 |
|
| 47 |
```py
|
| 48 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 49 |
|
| 50 |
+
model = AutoModelForCausalLM.from_pretrained("/output/path")
|
| 51 |
+
tokenizer = AutoTokenizer.from_pretrained("/output/path")
|
| 52 |
```
|
| 53 |
|
| 54 |
Important note: you need to be able to host the whole model in RAM to execute this script (even if the biggest versions
|
|
|
|
| 94 |
print("params: ", params)
|
| 95 |
|
| 96 |
num_shards = NUM_SHARDS[model_size]
|
| 97 |
+
|
| 98 |
+
# Model parameters
|
| 99 |
n_layers = params["n_layers"]
|
| 100 |
n_heads = params["n_heads"]
|
| 101 |
n_heads_per_shard = n_heads // num_shards
|
|
|
|
| 103 |
dims_per_head = dim // n_heads
|
| 104 |
base = 10000.0
|
| 105 |
inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
|
| 106 |
+
# Tokenizer parameters
|
| 107 |
+
#vocab_size = params["vocab_size"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
|
| 110 |
# permute for sliced rotary
|
| 111 |
def permute(w):
|
|
|
|
| 235 |
num_hidden_layers=params["n_layers"],
|
| 236 |
rms_norm_eps=params["norm_eps"],
|
| 237 |
)
|
| 238 |
+
#config["_name_or_path"] = tmp_model_path
|
| 239 |
+
config.auto_map = {
|
| 240 |
+
"AutoConfig": "modeling_aquila.LlamaConfig",
|
| 241 |
+
"AutoModel": "modeling_aquila.LlamaModel",
|
| 242 |
+
"AutoModelForCausalLM": "modeling_aquila.LlamaForCausalLM"
|
| 243 |
+
}
|
| 244 |
+
config.bos_token_id = 100006
|
| 245 |
+
config.eos_token_id = 100007
|
| 246 |
+
config.pad_token_id = 0
|
| 247 |
+
config.unk_token_id = 0
|
| 248 |
+
config.vocab_size = params["vocab_size"]
|
| 249 |
config.save_pretrained(tmp_model_path)
|
| 250 |
|
| 251 |
# Make space so we can load the model properly now.
|
|
|
|
| 263 |
shutil.rmtree(tmp_model_path)
|
| 264 |
|
| 265 |
|
| 266 |
+
def write_tokenizer(input_tokenizer_path, output_dir):
|
| 267 |
+
tokenizer_class = GPTNeoXTokenizerFast
|
| 268 |
+
tokenizer = tokenizer_class.from_pretrained(input_tokenizer_path)
|
| 269 |
+
print(f"Saving a {tokenizer_class.__name__} to {output_dir}.")
|
| 270 |
+
tokenizer.save_pretrained(output_dir)
|
|
|
|
| 271 |
|
| 272 |
+
def copy_aquila_license(input_base_path, output_dir):
|
| 273 |
+
for path in glob.glob(os.path.join(input_base_path, "*.pdf")):
|
| 274 |
+
print(f"Copy Aquila License file from {path} to {output_dir}")
|
| 275 |
+
shutil.copy2(path, output_dir)
|
| 276 |
+
|
| 277 |
+
def download_modeling_aquila_file(output_dir):
|
| 278 |
+
url = "https://gist.githubusercontent.com/sammysun0711/4f2622dba7f7ec2dff6cdd31ea21d419/raw/0fa7e79f3fa27bf9fbb8d85e9b5bb16b5e93db88/modeling_aqulia.py"
|
| 279 |
+
urllib.request.urlretrieve(url, os.path.join(output_dir, "modeling_aquila.py"))
|
| 280 |
|
| 281 |
def main():
|
| 282 |
parser = argparse.ArgumentParser()
|
|
|
|
| 293 |
help="Location to write HF model and tokenizer",
|
| 294 |
)
|
| 295 |
args = parser.parse_args()
|
| 296 |
+
|
| 297 |
if args.model_size != "tokenizer_only":
|
| 298 |
write_model(
|
| 299 |
model_path=args.output_dir,
|
|
|
|
| 301 |
input_base_path=args.input_dir,
|
| 302 |
model_size=args.model_size,
|
| 303 |
)
|
| 304 |
+
copy_aquila_license(args.input_dir, args.output_dir)
|
| 305 |
+
write_tokenizer(args.input_dir, args.output_dir)
|
| 306 |
+
download_modeling_aquila_file(args.output_dir)
|
| 307 |
|
| 308 |
if __name__ == "__main__":
|
| 309 |
main()
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 100006,
|
| 4 |
"eos_token_id": 100007,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 100006,
|
| 4 |
"eos_token_id": 100007,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.29.2"
|
| 7 |
}
|
modeling_aquila.py
CHANGED
|
@@ -897,4 +897,4 @@ class LlamaForSequenceClassification(LlamaPreTrainedModel):
|
|
| 897 |
past_key_values=transformer_outputs.past_key_values,
|
| 898 |
hidden_states=transformer_outputs.hidden_states,
|
| 899 |
attentions=transformer_outputs.attentions,
|
| 900 |
-
)
|
|
|
|
| 897 |
past_key_values=transformer_outputs.past_key_values,
|
| 898 |
hidden_states=transformer_outputs.hidden_states,
|
| 899 |
attentions=transformer_outputs.attentions,
|
| 900 |
+
)
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,330 +1,330 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "pytorch_model-
|
| 7 |
-
"model.embed_tokens.weight": "pytorch_model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 16 |
-
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 17 |
-
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 18 |
-
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-
|
| 19 |
-
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 20 |
-
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 21 |
-
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 22 |
-
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 23 |
-
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 24 |
-
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 25 |
-
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 26 |
-
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 27 |
-
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 28 |
-
"model.layers.10.input_layernorm.weight": "pytorch_model-
|
| 29 |
-
"model.layers.10.mlp.down_proj.weight": "pytorch_model-
|
| 30 |
-
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-
|
| 31 |
-
"model.layers.10.mlp.up_proj.weight": "pytorch_model-
|
| 32 |
-
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-
|
| 33 |
-
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 34 |
-
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-
|
| 35 |
-
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 36 |
-
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 37 |
-
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 38 |
-
"model.layers.11.input_layernorm.weight": "pytorch_model-
|
| 39 |
-
"model.layers.11.mlp.down_proj.weight": "pytorch_model-
|
| 40 |
-
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-
|
| 41 |
-
"model.layers.11.mlp.up_proj.weight": "pytorch_model-
|
| 42 |
-
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-
|
| 43 |
-
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-
|
| 44 |
-
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-
|
| 45 |
-
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-
|
| 46 |
-
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 47 |
-
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-
|
| 48 |
-
"model.layers.12.input_layernorm.weight": "pytorch_model-
|
| 49 |
-
"model.layers.12.mlp.down_proj.weight": "pytorch_model-
|
| 50 |
-
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-
|
| 51 |
-
"model.layers.12.mlp.up_proj.weight": "pytorch_model-
|
| 52 |
-
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-
|
| 53 |
-
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-
|
| 54 |
-
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-
|
| 55 |
-
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-
|
| 56 |
-
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 57 |
-
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-
|
| 58 |
-
"model.layers.13.input_layernorm.weight": "pytorch_model-
|
| 59 |
-
"model.layers.13.mlp.down_proj.weight": "pytorch_model-
|
| 60 |
-
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-
|
| 61 |
-
"model.layers.13.mlp.up_proj.weight": "pytorch_model-
|
| 62 |
-
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-
|
| 63 |
-
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-
|
| 64 |
-
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-
|
| 65 |
-
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-
|
| 66 |
-
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 67 |
-
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-
|
| 68 |
-
"model.layers.14.input_layernorm.weight": "pytorch_model-
|
| 69 |
-
"model.layers.14.mlp.down_proj.weight": "pytorch_model-
|
| 70 |
-
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-
|
| 71 |
-
"model.layers.14.mlp.up_proj.weight": "pytorch_model-
|
| 72 |
-
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-
|
| 73 |
-
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-
|
| 74 |
-
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-
|
| 75 |
-
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-
|
| 76 |
-
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 77 |
-
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-
|
| 78 |
-
"model.layers.15.input_layernorm.weight": "pytorch_model-
|
| 79 |
-
"model.layers.15.mlp.down_proj.weight": "pytorch_model-
|
| 80 |
-
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-
|
| 81 |
-
"model.layers.15.mlp.up_proj.weight": "pytorch_model-
|
| 82 |
-
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-
|
| 83 |
-
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-
|
| 84 |
-
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-
|
| 85 |
-
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-
|
| 86 |
-
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 87 |
-
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-
|
| 88 |
-
"model.layers.16.input_layernorm.weight": "pytorch_model-
|
| 89 |
-
"model.layers.16.mlp.down_proj.weight": "pytorch_model-
|
| 90 |
-
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-
|
| 91 |
-
"model.layers.16.mlp.up_proj.weight": "pytorch_model-
|
| 92 |
-
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-
|
| 93 |
-
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-
|
| 94 |
-
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-
|
| 95 |
-
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-
|
| 96 |
-
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 97 |
-
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-
|
| 98 |
-
"model.layers.17.input_layernorm.weight": "pytorch_model-
|
| 99 |
-
"model.layers.17.mlp.down_proj.weight": "pytorch_model-
|
| 100 |
-
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-
|
| 101 |
-
"model.layers.17.mlp.up_proj.weight": "pytorch_model-
|
| 102 |
-
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-
|
| 103 |
-
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-
|
| 104 |
-
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-
|
| 105 |
-
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-
|
| 106 |
-
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 107 |
-
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-
|
| 108 |
-
"model.layers.18.input_layernorm.weight": "pytorch_model-
|
| 109 |
-
"model.layers.18.mlp.down_proj.weight": "pytorch_model-
|
| 110 |
-
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-
|
| 111 |
-
"model.layers.18.mlp.up_proj.weight": "pytorch_model-
|
| 112 |
-
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-
|
| 113 |
-
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-
|
| 114 |
-
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-
|
| 115 |
-
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-
|
| 116 |
-
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 117 |
-
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-
|
| 118 |
-
"model.layers.19.input_layernorm.weight": "pytorch_model-
|
| 119 |
-
"model.layers.19.mlp.down_proj.weight": "pytorch_model-
|
| 120 |
-
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-
|
| 121 |
-
"model.layers.19.mlp.up_proj.weight": "pytorch_model-
|
| 122 |
-
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-
|
| 123 |
-
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-
|
| 124 |
-
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-
|
| 125 |
-
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-
|
| 126 |
-
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 127 |
-
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-
|
| 128 |
-
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-
|
| 129 |
-
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 130 |
-
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 131 |
-
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 132 |
-
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 133 |
-
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 134 |
-
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 135 |
-
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 136 |
-
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 137 |
-
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 138 |
-
"model.layers.20.input_layernorm.weight": "pytorch_model-
|
| 139 |
-
"model.layers.20.mlp.down_proj.weight": "pytorch_model-
|
| 140 |
-
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-
|
| 141 |
-
"model.layers.20.mlp.up_proj.weight": "pytorch_model-
|
| 142 |
-
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-
|
| 143 |
-
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-
|
| 144 |
-
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-
|
| 145 |
-
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-
|
| 146 |
-
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 147 |
-
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-
|
| 148 |
-
"model.layers.21.input_layernorm.weight": "pytorch_model-
|
| 149 |
-
"model.layers.21.mlp.down_proj.weight": "pytorch_model-
|
| 150 |
-
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-
|
| 151 |
-
"model.layers.21.mlp.up_proj.weight": "pytorch_model-
|
| 152 |
-
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-
|
| 153 |
-
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-
|
| 154 |
-
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-
|
| 155 |
-
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-
|
| 156 |
-
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 157 |
-
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-
|
| 158 |
-
"model.layers.22.input_layernorm.weight": "pytorch_model-
|
| 159 |
-
"model.layers.22.mlp.down_proj.weight": "pytorch_model-
|
| 160 |
-
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-
|
| 161 |
-
"model.layers.22.mlp.up_proj.weight": "pytorch_model-
|
| 162 |
-
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-
|
| 163 |
-
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-
|
| 164 |
-
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-
|
| 165 |
-
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-
|
| 166 |
-
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 167 |
-
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-
|
| 168 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-
|
| 169 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-
|
| 170 |
-
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-
|
| 171 |
-
"model.layers.23.mlp.up_proj.weight": "pytorch_model-
|
| 172 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-
|
| 173 |
-
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-
|
| 174 |
-
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-
|
| 175 |
-
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-
|
| 176 |
-
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 177 |
-
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-
|
| 178 |
-
"model.layers.24.input_layernorm.weight": "pytorch_model-
|
| 179 |
-
"model.layers.24.mlp.down_proj.weight": "pytorch_model-
|
| 180 |
-
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-
|
| 181 |
-
"model.layers.24.mlp.up_proj.weight": "pytorch_model-
|
| 182 |
-
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-
|
| 183 |
-
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-
|
| 184 |
-
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-
|
| 185 |
-
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-
|
| 186 |
-
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 187 |
-
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-
|
| 188 |
-
"model.layers.25.input_layernorm.weight": "pytorch_model-
|
| 189 |
-
"model.layers.25.mlp.down_proj.weight": "pytorch_model-
|
| 190 |
-
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-
|
| 191 |
-
"model.layers.25.mlp.up_proj.weight": "pytorch_model-
|
| 192 |
-
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-
|
| 193 |
-
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-
|
| 194 |
-
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-
|
| 195 |
-
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-
|
| 196 |
-
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 197 |
-
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-
|
| 198 |
-
"model.layers.26.input_layernorm.weight": "pytorch_model-
|
| 199 |
-
"model.layers.26.mlp.down_proj.weight": "pytorch_model-
|
| 200 |
-
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-
|
| 201 |
-
"model.layers.26.mlp.up_proj.weight": "pytorch_model-
|
| 202 |
-
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-
|
| 203 |
-
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-
|
| 204 |
-
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-
|
| 205 |
-
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-
|
| 206 |
-
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 207 |
-
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-
|
| 208 |
-
"model.layers.27.input_layernorm.weight": "pytorch_model-
|
| 209 |
-
"model.layers.27.mlp.down_proj.weight": "pytorch_model-
|
| 210 |
-
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-
|
| 211 |
-
"model.layers.27.mlp.up_proj.weight": "pytorch_model-
|
| 212 |
-
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-
|
| 213 |
-
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-
|
| 214 |
-
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-
|
| 215 |
-
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-
|
| 216 |
-
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 217 |
-
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-
|
| 218 |
-
"model.layers.28.input_layernorm.weight": "pytorch_model-
|
| 219 |
-
"model.layers.28.mlp.down_proj.weight": "pytorch_model-
|
| 220 |
-
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-
|
| 221 |
-
"model.layers.28.mlp.up_proj.weight": "pytorch_model-
|
| 222 |
-
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-
|
| 223 |
-
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-
|
| 224 |
-
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-
|
| 225 |
-
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-
|
| 226 |
-
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 227 |
-
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-
|
| 228 |
-
"model.layers.29.input_layernorm.weight": "pytorch_model-
|
| 229 |
-
"model.layers.29.mlp.down_proj.weight": "pytorch_model-
|
| 230 |
-
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-
|
| 231 |
-
"model.layers.29.mlp.up_proj.weight": "pytorch_model-
|
| 232 |
-
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-
|
| 233 |
-
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-
|
| 234 |
-
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-
|
| 235 |
-
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-
|
| 236 |
-
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 237 |
-
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-
|
| 238 |
-
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-
|
| 239 |
-
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 240 |
-
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 241 |
-
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 242 |
-
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 243 |
-
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 244 |
-
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 245 |
-
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 246 |
-
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 247 |
-
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 248 |
-
"model.layers.30.input_layernorm.weight": "pytorch_model-
|
| 249 |
-
"model.layers.30.mlp.down_proj.weight": "pytorch_model-
|
| 250 |
-
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-
|
| 251 |
-
"model.layers.30.mlp.up_proj.weight": "pytorch_model-
|
| 252 |
-
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-
|
| 253 |
-
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-
|
| 254 |
-
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-
|
| 255 |
-
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-
|
| 256 |
-
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 257 |
-
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-
|
| 258 |
-
"model.layers.31.input_layernorm.weight": "pytorch_model-
|
| 259 |
-
"model.layers.31.mlp.down_proj.weight": "pytorch_model-
|
| 260 |
-
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-
|
| 261 |
-
"model.layers.31.mlp.up_proj.weight": "pytorch_model-
|
| 262 |
-
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-
|
| 263 |
-
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-
|
| 264 |
-
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-
|
| 265 |
-
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-
|
| 266 |
-
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-
|
| 267 |
-
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-
|
| 268 |
-
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-
|
| 269 |
-
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 270 |
-
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 271 |
-
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 272 |
-
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 273 |
-
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 274 |
-
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 275 |
-
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 276 |
-
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 277 |
-
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 278 |
-
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-
|
| 279 |
-
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 280 |
-
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 281 |
-
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 282 |
-
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 283 |
-
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 284 |
-
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 285 |
-
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 286 |
-
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 287 |
-
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 288 |
-
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-
|
| 289 |
-
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 290 |
-
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 291 |
-
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 292 |
-
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 293 |
-
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 294 |
-
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 295 |
-
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 296 |
-
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 297 |
-
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 298 |
-
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-
|
| 299 |
-
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 300 |
-
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 301 |
-
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 302 |
-
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 303 |
-
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 304 |
-
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 305 |
-
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 306 |
-
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 307 |
-
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 308 |
-
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-
|
| 309 |
-
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 310 |
-
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 311 |
-
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 312 |
-
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 313 |
-
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 314 |
-
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 315 |
-
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 316 |
-
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 317 |
-
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 318 |
-
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-
|
| 319 |
-
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 320 |
-
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 321 |
-
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 322 |
-
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 323 |
-
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 324 |
-
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 325 |
-
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 326 |
-
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-
|
| 327 |
-
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 328 |
-
"model.norm.weight": "pytorch_model-
|
| 329 |
}
|
| 330 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 14591082496
|
| 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-00002-of-00002.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00002.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-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-00002-of-00002.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-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 |
}
|
tokenizer.json
CHANGED
|
@@ -199806,4 +199806,4 @@
|
|
| 199806 |
"çŃī 课ç¨ĭ"
|
| 199807 |
]
|
| 199808 |
}
|
| 199809 |
-
}
|
|
|
|
| 199806 |
"çŃī 课ç¨ĭ"
|
| 199807 |
]
|
| 199808 |
}
|
| 199809 |
+
}
|