Upload folder using huggingface_hub
Browse files- .gitattributes +5 -0
- llm-jp/llm-jp-1.3b-v1.0/Constant_161_attr__value +3 -0
- llm-jp/llm-jp-1.3b-v1.0/Constant_171_attr__value +3 -0
- llm-jp/llm-jp-1.3b-v1.0/config.json +33 -0
- llm-jp/llm-jp-1.3b-v1.0/generation_config.json +6 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model.onnx_data +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged.onnx_data +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged_quantized.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_quantized.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model.onnx_data +3 -0
- llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model_quantized.onnx +3 -0
- llm-jp/llm-jp-1.3b-v1.0/quantize_config.json +97 -0
- llm-jp/llm-jp-1.3b-v1.0/special_tokens_map.json +12 -0
- llm-jp/llm-jp-1.3b-v1.0/tokenizer.json +0 -0
- llm-jp/llm-jp-1.3b-v1.0/tokenizer_config.json +18 -0
.gitattributes
CHANGED
@@ -74,3 +74,8 @@ line-corporation/japanese-large-lm-1.7b-instruction-sft/Constant_171_attr__value
|
|
74 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
75 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
|
76 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
74 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
75 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
|
76 |
line-corporation/japanese-large-lm-1.7b-instruction-sft/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
77 |
+
llm-jp/llm-jp-1.3b-v1.0/Constant_161_attr__value filter=lfs diff=lfs merge=lfs -text
|
78 |
+
llm-jp/llm-jp-1.3b-v1.0/Constant_171_attr__value filter=lfs diff=lfs merge=lfs -text
|
79 |
+
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
80 |
+
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
|
81 |
+
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
llm-jp/llm-jp-1.3b-v1.0/Constant_161_attr__value
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83dd5f1a5a07912d2e7dbb73b75edeb2ce4c1f1d6ec48144a887bd4a4f72325b
|
3 |
+
size 4194304
|
llm-jp/llm-jp-1.3b-v1.0/Constant_171_attr__value
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83dd5f1a5a07912d2e7dbb73b75edeb2ce4c1f1d6ec48144a887bd4a4f72325b
|
3 |
+
size 4194304
|
llm-jp/llm-jp-1.3b-v1.0/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "llm-jp/llm-jp-1.3b-v1.0",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 7,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 7,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 2048,
|
17 |
+
"n_head": 16,
|
18 |
+
"n_inner": 8192,
|
19 |
+
"n_layer": 24,
|
20 |
+
"n_positions": 2048,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"transformers_version": "4.33.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50688
|
33 |
+
}
|
llm-jp/llm-jp-1.3b-v1.0/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 7,
|
4 |
+
"eos_token_id": 7,
|
5 |
+
"transformers_version": "4.33.2"
|
6 |
+
}
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7b9e08f537b10407966df070b787bcca5fcac186f733ac48d6d78f8adc38c8c
|
3 |
+
size 5241500
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768dfe9eba4c21d61602e92576e0b0141ededcc525ceb209c27581e0e6aa6345
|
3 |
+
size 5266423808
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e9cd4bdb5e6debe6610af85fbb39eca7e3fc1ab1ebc8b127ca2cf82a914758
|
3 |
+
size 10476041
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768dfe9eba4c21d61602e92576e0b0141ededcc525ceb209c27581e0e6aa6345
|
3 |
+
size 5266423808
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1112b5c802cb50c44e9b51b8b2dd3902b44ac23221c2f93f56ad63d9a0cf1f2b
|
3 |
+
size 1329918523
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c1f2aac40dbb05e1471bbdeb9c2854055804a267ce628ecf6995a9839ad3886
|
3 |
+
size 1324221751
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5ae26eac243fa75076de44c6c363f4547931aa1c2166e73ccd544502d22db33
|
3 |
+
size 5257490
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768dfe9eba4c21d61602e92576e0b0141ededcc525ceb209c27581e0e6aa6345
|
3 |
+
size 5266423808
|
llm-jp/llm-jp-1.3b-v1.0/onnx/decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b34637d5412b077eb8b2304ce0cc874710af7c353e8e34b599e95dba3984b16e
|
3 |
+
size 1324238876
|
llm-jp/llm-jp-1.3b-v1.0/quantize_config.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": false,
|
3 |
+
"reduce_range": false,
|
4 |
+
"per_model_config": {
|
5 |
+
"decoder_model_merged": {
|
6 |
+
"op_types": [
|
7 |
+
"Mul",
|
8 |
+
"Add",
|
9 |
+
"Sqrt",
|
10 |
+
"Gemm",
|
11 |
+
"Sub",
|
12 |
+
"Gather",
|
13 |
+
"Slice",
|
14 |
+
"Reshape",
|
15 |
+
"MatMul",
|
16 |
+
"ReduceMean",
|
17 |
+
"Split",
|
18 |
+
"Squeeze",
|
19 |
+
"Pow",
|
20 |
+
"Transpose",
|
21 |
+
"Constant",
|
22 |
+
"Shape",
|
23 |
+
"Range",
|
24 |
+
"Erf",
|
25 |
+
"Softmax",
|
26 |
+
"If",
|
27 |
+
"Concat",
|
28 |
+
"ConstantOfShape",
|
29 |
+
"Where",
|
30 |
+
"Div",
|
31 |
+
"Unsqueeze",
|
32 |
+
"Cast"
|
33 |
+
],
|
34 |
+
"weight_type": "QInt8"
|
35 |
+
},
|
36 |
+
"decoder_model": {
|
37 |
+
"op_types": [
|
38 |
+
"Mul",
|
39 |
+
"Add",
|
40 |
+
"Sqrt",
|
41 |
+
"Gemm",
|
42 |
+
"Sub",
|
43 |
+
"Gather",
|
44 |
+
"Slice",
|
45 |
+
"Reshape",
|
46 |
+
"MatMul",
|
47 |
+
"ReduceMean",
|
48 |
+
"Split",
|
49 |
+
"Squeeze",
|
50 |
+
"Pow",
|
51 |
+
"Transpose",
|
52 |
+
"Constant",
|
53 |
+
"Shape",
|
54 |
+
"Range",
|
55 |
+
"Erf",
|
56 |
+
"Softmax",
|
57 |
+
"Concat",
|
58 |
+
"ConstantOfShape",
|
59 |
+
"Where",
|
60 |
+
"Div",
|
61 |
+
"Unsqueeze",
|
62 |
+
"Cast"
|
63 |
+
],
|
64 |
+
"weight_type": "QInt8"
|
65 |
+
},
|
66 |
+
"decoder_with_past_model": {
|
67 |
+
"op_types": [
|
68 |
+
"Mul",
|
69 |
+
"Add",
|
70 |
+
"Sqrt",
|
71 |
+
"Gemm",
|
72 |
+
"Sub",
|
73 |
+
"Gather",
|
74 |
+
"Slice",
|
75 |
+
"Reshape",
|
76 |
+
"MatMul",
|
77 |
+
"ReduceMean",
|
78 |
+
"Split",
|
79 |
+
"Squeeze",
|
80 |
+
"Pow",
|
81 |
+
"Transpose",
|
82 |
+
"Constant",
|
83 |
+
"Shape",
|
84 |
+
"Range",
|
85 |
+
"Erf",
|
86 |
+
"Softmax",
|
87 |
+
"Concat",
|
88 |
+
"ConstantOfShape",
|
89 |
+
"Where",
|
90 |
+
"Div",
|
91 |
+
"Unsqueeze",
|
92 |
+
"Cast"
|
93 |
+
],
|
94 |
+
"weight_type": "QInt8"
|
95 |
+
}
|
96 |
+
}
|
97 |
+
}
|
llm-jp/llm-jp-1.3b-v1.0/special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"</s|LLM-jp>"
|
4 |
+
],
|
5 |
+
"bos_token": "<s|LLM-jp>",
|
6 |
+
"cls_token": "<CLS|LLM-jp>",
|
7 |
+
"eos_token": "<EOD|LLM-jp>",
|
8 |
+
"mask_token": "<mask|LLM-jp>",
|
9 |
+
"pad_token": "<pad|LLM-jp>",
|
10 |
+
"sep_token": "<SEP|LLM-jp>",
|
11 |
+
"unk_token": "<unk|LLM-jp>"
|
12 |
+
}
|
llm-jp/llm-jp-1.3b-v1.0/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llm-jp/llm-jp-1.3b-v1.0/tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"</s|LLM-jp>"
|
4 |
+
],
|
5 |
+
"bos_token": "<s|LLM-jp>",
|
6 |
+
"clean_up_tokenization_spaces": false,
|
7 |
+
"cls_token": "<CLS|LLM-jp>",
|
8 |
+
"eod_token": "<EOD|LLM-jp>",
|
9 |
+
"eos_token": "<EOD|LLM-jp>",
|
10 |
+
"extra_ids": 0,
|
11 |
+
"mask_token": "<mask|LLM-jp>",
|
12 |
+
"model_max_length": 1000000000000000019884624838656,
|
13 |
+
"pad_token": "<pad|LLM-jp>",
|
14 |
+
"sep_token": "<SEP|LLM-jp>",
|
15 |
+
"sp_model_kwargs": {},
|
16 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
17 |
+
"unk_token": "<unk|LLM-jp>"
|
18 |
+
}
|