Upload folder using huggingface_hub
Browse files- README.md +77 -0
- config.json +65 -0
- mergekit_config.yml +41 -0
- merges.txt +0 -0
- model-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +24 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- mllm-dev/gpt2_f_experiment_0_drug_data
|
4 |
+
- mllm-dev/gpt2_f_experiment_3_drug_data
|
5 |
+
- mllm-dev/gpt2_f_experiment_4_drug_data
|
6 |
+
- mllm-dev/gpt2_f_experiment_2_drug_data
|
7 |
+
- mllm-dev/gpt2_f_experiment_1_drug_data
|
8 |
+
library_name: transformers
|
9 |
+
tags:
|
10 |
+
- mergekit
|
11 |
+
- merge
|
12 |
+
|
13 |
+
---
|
14 |
+
# tam_test_merge_out_drug_data_dare_ties
|
15 |
+
|
16 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
### Merge Method
|
20 |
+
|
21 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mllm-dev/gpt2_f_experiment_0_drug_data](https://huggingface.co/mllm-dev/gpt2_f_experiment_0_drug_data) as a base.
|
22 |
+
|
23 |
+
### Models Merged
|
24 |
+
|
25 |
+
The following models were included in the merge:
|
26 |
+
* [mllm-dev/gpt2_f_experiment_3_drug_data](https://huggingface.co/mllm-dev/gpt2_f_experiment_3_drug_data)
|
27 |
+
* [mllm-dev/gpt2_f_experiment_4_drug_data](https://huggingface.co/mllm-dev/gpt2_f_experiment_4_drug_data)
|
28 |
+
* [mllm-dev/gpt2_f_experiment_2_drug_data](https://huggingface.co/mllm-dev/gpt2_f_experiment_2_drug_data)
|
29 |
+
* [mllm-dev/gpt2_f_experiment_1_drug_data](https://huggingface.co/mllm-dev/gpt2_f_experiment_1_drug_data)
|
30 |
+
|
31 |
+
### Configuration
|
32 |
+
|
33 |
+
The following YAML configuration was used to produce this model:
|
34 |
+
|
35 |
+
```yaml
|
36 |
+
base_model:
|
37 |
+
model:
|
38 |
+
path: mllm-dev/gpt2_f_experiment_0_drug_data
|
39 |
+
dtype: float16
|
40 |
+
merge_method: dare_ties
|
41 |
+
parameters:
|
42 |
+
normalize: 1.0
|
43 |
+
slices:
|
44 |
+
- sources:
|
45 |
+
- layer_range: [0, 12]
|
46 |
+
model:
|
47 |
+
model:
|
48 |
+
path: mllm-dev/gpt2_f_experiment_0_drug_data
|
49 |
+
- layer_range: [0, 12]
|
50 |
+
model:
|
51 |
+
model:
|
52 |
+
path: mllm-dev/gpt2_f_experiment_1_drug_data
|
53 |
+
parameters:
|
54 |
+
density: 0.9
|
55 |
+
weight: 0.2
|
56 |
+
- layer_range: [0, 12]
|
57 |
+
model:
|
58 |
+
model:
|
59 |
+
path: mllm-dev/gpt2_f_experiment_2_drug_data
|
60 |
+
parameters:
|
61 |
+
density: 0.9
|
62 |
+
weight: 0.2
|
63 |
+
- layer_range: [0, 12]
|
64 |
+
model:
|
65 |
+
model:
|
66 |
+
path: mllm-dev/gpt2_f_experiment_3_drug_data
|
67 |
+
parameters:
|
68 |
+
density: 0.9
|
69 |
+
weight: 0.2
|
70 |
+
- layer_range: [0, 12]
|
71 |
+
model:
|
72 |
+
model:
|
73 |
+
path: mllm-dev/gpt2_f_experiment_4_drug_data
|
74 |
+
parameters:
|
75 |
+
density: 0.9
|
76 |
+
weight: 0.2
|
77 |
+
```
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mllm-dev/gpt2_f_experiment_0_drug_data",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7,
|
33 |
+
"LABEL_8": 8,
|
34 |
+
"LABEL_9": 9
|
35 |
+
},
|
36 |
+
"layer_norm_epsilon": 1e-05,
|
37 |
+
"model_type": "gpt2",
|
38 |
+
"n_ctx": 1024,
|
39 |
+
"n_embd": 768,
|
40 |
+
"n_head": 12,
|
41 |
+
"n_inner": null,
|
42 |
+
"n_layer": 12,
|
43 |
+
"n_positions": 1024,
|
44 |
+
"pad_token_id": 50256,
|
45 |
+
"problem_type": "single_label_classification",
|
46 |
+
"reorder_and_upcast_attn": false,
|
47 |
+
"resid_pdrop": 0.1,
|
48 |
+
"scale_attn_by_inverse_layer_idx": false,
|
49 |
+
"scale_attn_weights": true,
|
50 |
+
"summary_activation": null,
|
51 |
+
"summary_first_dropout": 0.1,
|
52 |
+
"summary_proj_to_labels": true,
|
53 |
+
"summary_type": "cls_index",
|
54 |
+
"summary_use_proj": true,
|
55 |
+
"task_specific_params": {
|
56 |
+
"text-generation": {
|
57 |
+
"do_sample": true,
|
58 |
+
"max_length": 50
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"torch_dtype": "float16",
|
62 |
+
"transformers_version": "4.40.0.dev0",
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 50257
|
65 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model:
|
2 |
+
model:
|
3 |
+
path: mllm-dev/gpt2_f_experiment_0_drug_data
|
4 |
+
dtype: float16
|
5 |
+
merge_method: dare_ties
|
6 |
+
parameters:
|
7 |
+
normalize: 1.0
|
8 |
+
slices:
|
9 |
+
- sources:
|
10 |
+
- layer_range: [0, 12]
|
11 |
+
model:
|
12 |
+
model:
|
13 |
+
path: mllm-dev/gpt2_f_experiment_0_drug_data
|
14 |
+
- layer_range: [0, 12]
|
15 |
+
model:
|
16 |
+
model:
|
17 |
+
path: mllm-dev/gpt2_f_experiment_1_drug_data
|
18 |
+
parameters:
|
19 |
+
density: 0.9
|
20 |
+
weight: 0.2
|
21 |
+
- layer_range: [0, 12]
|
22 |
+
model:
|
23 |
+
model:
|
24 |
+
path: mllm-dev/gpt2_f_experiment_2_drug_data
|
25 |
+
parameters:
|
26 |
+
density: 0.9
|
27 |
+
weight: 0.2
|
28 |
+
- layer_range: [0, 12]
|
29 |
+
model:
|
30 |
+
model:
|
31 |
+
path: mllm-dev/gpt2_f_experiment_3_drug_data
|
32 |
+
parameters:
|
33 |
+
density: 0.9
|
34 |
+
weight: 0.2
|
35 |
+
- layer_range: [0, 12]
|
36 |
+
model:
|
37 |
+
model:
|
38 |
+
path: mllm-dev/gpt2_f_experiment_4_drug_data
|
39 |
+
parameters:
|
40 |
+
density: 0.9
|
41 |
+
weight: 0.2
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1810937373135e5a4647345f84ce0d57dda0e07bf448d2378c9040046b0b8d
|
3 |
+
size 248909944
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 248894976}, "weight_map": {"score.weight": "model-00001-of-00001.safetensors", "transformer.ln_f.bias": "model-00001-of-00001.safetensors", "transformer.ln_f.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.wpe.weight": "model-00001-of-00001.safetensors", "transformer.wte.weight": "model-00001-of-00001.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"max_length": 1024,
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"stride": 0,
|
20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"truncation_side": "right",
|
22 |
+
"truncation_strategy": "longest_first",
|
23 |
+
"unk_token": "<|endoftext|>"
|
24 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|