初始化项目，由ModelHub XC社区提供模型
Model: bigscience/sgpt-bloom-7b1-msmarco Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.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
|
||||
*.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
|
||||
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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
9
1_Pooling/config.json
Normal file
9
1_Pooling/config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"word_embedding_dimension": 4096,
|
||||
"pooling_mode_cls_token": false,
|
||||
"pooling_mode_mean_tokens": false,
|
||||
"pooling_mode_max_tokens": false,
|
||||
"pooling_mode_mean_sqrt_len_tokens": false,
|
||||
"pooling_mode_weightedmean_tokens": true,
|
||||
"pooling_mode_lasttoken": false
|
||||
}
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"BloomForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"attention_softmax_in_fp32": true,
|
||||
"bias_dropout_fusion": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_dropout": 0.0,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"masked_softmax_fusion": true,
|
||||
"model_type": "bloom",
|
||||
"n_embed": 4096,
|
||||
"n_inner": null,
|
||||
"n_layer": 30,
|
||||
"num_attention_heads": 32,
|
||||
"offset_alibi": 100,
|
||||
"pad_token_id": 3,
|
||||
"pretraining_tp": 4,
|
||||
"seq_length": 2048,
|
||||
"skip_bias_add": true,
|
||||
"skip_bias_add_qkv": false,
|
||||
"slow_but_exact": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.20.1",
|
||||
"unk_token_id": 0,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250682
|
||||
}
|
||||
7
config_sentence_transformers.json
Normal file
7
config_sentence_transformers.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "2.1.0",
|
||||
"transformers": "4.20.1",
|
||||
"pytorch": "1.12.0"
|
||||
}
|
||||
}
|
||||
1
evaluation/beir.json
Normal file
1
evaluation/beir.json
Normal file
File diff suppressed because one or more lines are too long
14
modules.json
Normal file
14
modules.json
Normal file
@@ -0,0 +1,14 @@
|
||||
[
|
||||
{
|
||||
"idx": 0,
|
||||
"name": "0",
|
||||
"path": "",
|
||||
"type": "sentence_transformers.models.Transformer"
|
||||
},
|
||||
{
|
||||
"idx": 1,
|
||||
"name": "1",
|
||||
"path": "1_Pooling",
|
||||
"type": "sentence_transformers.models.Pooling"
|
||||
}
|
||||
]
|
||||
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 sha256:7aa0368f5635d9558fff1652236f8e16dccc2f65aaa7320d3decc7d559eda631
|
||||
size 9947280444
|
||||
3
pytorch_model-00001-of-00003.safetensors
Normal file
3
pytorch_model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99883bbcfc2d2f195c097e6db259dd8c50237bee722cc018a7f516c6783b1c12
|
||||
size 9947260280
|
||||
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 sha256:2350a568a6491d756f271357ba5147c86d4e0ebe5d83b97156218d9d5366c835
|
||||
size 9733438429
|
||||
3
pytorch_model-00002-of-00003.safetensors
Normal file
3
pytorch_model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7af30a9c4b9c95941e25d39bf3afcc19fb28f8da23a34c5aa85e44d6233c4068
|
||||
size 9733406064
|
||||
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 sha256:75f5c706e045b84e7b54c554eae2da0f02fea5870a19e943997cc567849a1e9d
|
||||
size 8592219901
|
||||
3
pytorch_model-00003-of-00003.safetensors
Normal file
3
pytorch_model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d0f3db376f16ae3bba41d31d1b1bc05944070a5ff778397a99daa963313064f4
|
||||
size 8592192584
|
||||
372
pytorch_model.bin.index.json
Normal file
372
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,372 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28272820224
|
||||
},
|
||||
"weight_map": {
|
||||
"h.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.10.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.20.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.21.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.22.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.23.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.self_attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"h.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.self_attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"h.8.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.self_attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"ln_f.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"ln_f.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"word_embeddings_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"word_embeddings_layernorm.weight": "pytorch_model-00001-of-00003.bin"
|
||||
}
|
||||
}
|
||||
4
sentence_bert_config.json
Normal file
4
sentence_bert_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"max_seq_length": 300,
|
||||
"do_lower_case": false
|
||||
}
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "<pad>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:53b546fa3c6b32936b8e411c6b0c98c66fa272b0e69d1bb025b0026b1908e930
|
||||
size 14500905
|
||||
11
tokenizer_config.json
Normal file
11
tokenizer_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"name_or_path": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"special_tokens_map_file": null,
|
||||
"tokenizer_class": "BloomTokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user