初始化项目，由ModelHub XC社区提供模型
Model: OpenAssistant/galactica-6.7b-finetuned Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
42
README.md
Normal file
42
README.md
Normal file
@@ -0,0 +1,42 @@
|
|||||||
|
Galactica-6.7b finetuned on webgpt and prompt_dialogue (version v2)
|
||||||
|
|
||||||
|
Demo use:
|
||||||
|
|
||||||
|
```
|
||||||
|
import torch
|
||||||
|
from torch import nn
|
||||||
|
from torch.nn import functional as F
|
||||||
|
import transformers
|
||||||
|
|
||||||
|
base_path = 'OpenAssistant/galactica-6.7b-finetuned'
|
||||||
|
|
||||||
|
model = transformers.OPTForCausalLM.from_pretrained(
|
||||||
|
base_path, load_in_8bit=True, device_map='auto', low_cpu_mem_usage=True,
|
||||||
|
torch_dtype=torch.float16, offload_state_dict=True
|
||||||
|
)
|
||||||
|
|
||||||
|
model.gradient_checkpointing_enable() # reduce number of stored activations
|
||||||
|
model.model.decoder.project_in = lambda x: x.requires_grad_(True)
|
||||||
|
|
||||||
|
class CastOutputToFloat(nn.Sequential):
|
||||||
|
def forward(self, x): return super().forward(x).to(torch.float32)
|
||||||
|
|
||||||
|
model.lm_head = CastOutputToFloat(model.lm_head)
|
||||||
|
|
||||||
|
tokenizer = transformers.AutoTokenizer.from_pretrained(base_path)
|
||||||
|
|
||||||
|
batch = tokenizer.encode("<question>What are the symptoms of Alzheimer's disease?<answer>", return_tensors="pt")
|
||||||
|
|
||||||
|
with torch.cuda.amp.autocast():
|
||||||
|
out = model.generate(
|
||||||
|
input_ids=batch.to(model.device),
|
||||||
|
max_length=300,
|
||||||
|
do_sample=True,
|
||||||
|
top_k=40,
|
||||||
|
num_beams=1,
|
||||||
|
num_return_sequences=1,
|
||||||
|
eos_token_id=tokenizer.additional_special_tokens_ids[tokenizer.additional_special_tokens.index('<question>')]
|
||||||
|
)
|
||||||
|
|
||||||
|
print(tokenizer.decode(out[0, :-1]).replace('<question>', "User:\n").replace('<answer>', '\nAssistant:\n'))
|
||||||
|
```
|
||||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/local/home/sanagnos/tmp/checkpoint-2500",
|
||||||
|
"_remove_final_layer_norm": false,
|
||||||
|
"activation_dropout": 0.0,
|
||||||
|
"activation_function": "gelu",
|
||||||
|
"architectures": [
|
||||||
|
"OPTForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.1,
|
||||||
|
"bos_token_id": 0,
|
||||||
|
"do_layer_norm_before": true,
|
||||||
|
"dropout": 0.1,
|
||||||
|
"enable_bias": true,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"ffn_dim": 16384,
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"init_std": 0.02,
|
||||||
|
"layer_norm_elementwise_affine": true,
|
||||||
|
"layerdrop": 0.0,
|
||||||
|
"learned_embeddings": true,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "opt",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"pad_token_id": 1,
|
||||||
|
"scale_embeddings": false,
|
||||||
|
"torch_dtype": "float32",
|
||||||
|
"transformers_version": "4.25.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 50002,
|
||||||
|
"word_embed_proj_dim": 4096
|
||||||
|
}
|
||||||
3
pytorch_model-00001-of-00003.bin
Normal file
3
pytorch_model-00001-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e042a5d3de9c5cd9b10157741956870fd36924389022f183d982cdb8ff3c0193
|
||||||
|
size 9982165317
|
||||||
3
pytorch_model-00002-of-00003.bin
Normal file
3
pytorch_model-00002-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1bea3d69b655bcb637be97b443a079551b0980a00df710e016504cd135d366a5
|
||||||
|
size 9934800489
|
||||||
3
pytorch_model-00003-of-00003.bin
Normal file
3
pytorch_model-00003-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f09e9c93777c71188a26d0b8aca6bbba9a06e95de02a3660407c5c6614c8a2f2
|
||||||
|
size 7531918122
|
||||||
524
pytorch_model.bin.index.json
Normal file
524
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,524 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 27448705024
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.embed_positions.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
8
special_tokens_map.json
Normal file
8
special_tokens_map.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<question>",
|
||||||
|
"<answer>"
|
||||||
|
],
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"pad_token": "<pad>"
|
||||||
|
}
|
||||||
100019
tokenizer.json
Normal file
100019
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
6
tokenizer_config.json
Normal file
6
tokenizer_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"name_or_path": "/local/home/sanagnos/tmp/checkpoint-2500",
|
||||||
|
"special_tokens_map_file": "/content/tokenizer/special_tokens_map.json",
|
||||||
|
"tokenizer_class": "PreTrainedTokenizerFast"
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user