Commit
•
5f4129b
1
Parent(s):
01feec1
Upload folder using huggingface_hub
Browse files- README.md +46 -0
- config.json +39 -0
- generation_config.json +6 -0
- model.safetensors.index.json +262 -0
- output.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenization_neo.py +253 -0
- tokenizer.model +3 -0
- tokenizer_config.json +95 -0
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
# NEO
|
5 |
+
|
6 |
+
[🤗Neo-Models](https://huggingface.co/collections/m-a-p/neo-models-66395a5c9662bb58d5d70f04) | [🤗Neo-Datasets](https://huggingface.co/collections/m-a-p/neo-models-66395a5c9662bb58d5d70f04) | [Github](https://github.com/multimodal-art-projection/MAP-NEO)
|
7 |
+
|
8 |
+
Neo is a completely open source large language model, including code, all model weights, datasets used for training, and training details.
|
9 |
+
|
10 |
+
## Model
|
11 |
+
|
12 |
+
| Model | Describe | Download |
|
13 |
+
|---|---|---|
|
14 |
+
neo_7b| This repository contains the base model of neo_7b | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_7b)
|
15 |
+
neo_7b_intermediate| This repo contains normal pre-training intermediate ckpts. A total of 3.7T tokens were learned at this phase. | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_7b_intermediate)
|
16 |
+
neo_7b_decay| This repo contains intermediate ckpts during the decay phase. A total of 720B tokens were learned at this phase. | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_7b_decay)
|
17 |
+
neo_scalinglaw_980M | This repo contains ckpts related to scalinglaw experiments | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_scalinglaw_980M)
|
18 |
+
neo_scalinglaw_460M | This repo contains ckpts related to scalinglaw experiments | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_scalinglaw_460M)
|
19 |
+
neo_scalinglaw_250M | This repo contains ckpts related to scalinglaw experiments | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_scalinglaw_250M)
|
20 |
+
neo_2b_general | This repo contains ckpts of 2b model trained using common domain knowledge | • [🤗 Hugging Face](https://huggingface.co/m-a-p/neo_2b_general)
|
21 |
+
|
22 |
+
### Usage
|
23 |
+
|
24 |
+
```python
|
25 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
26 |
+
|
27 |
+
model_path = '<your-hf-model-path-with-tokenizer>'
|
28 |
+
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False, trust_remote_code=True)
|
30 |
+
|
31 |
+
model = AutoModelForCausalLM.from_pretrained(
|
32 |
+
model_path,
|
33 |
+
device_map="auto",
|
34 |
+
torch_dtype='auto'
|
35 |
+
).eval()
|
36 |
+
|
37 |
+
input_text = "A long, long time ago,"
|
38 |
+
|
39 |
+
input_ids = tokenizer(input_text, add_generation_prompt=True, return_tensors='pt').to(model.device)
|
40 |
+
output_ids = model.generate(**input_ids, max_new_tokens=20)
|
41 |
+
response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
|
42 |
+
|
43 |
+
print(response)
|
44 |
+
```
|
45 |
+
|
46 |
+
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "None",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 3072,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 24576,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.39.3",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 64256,
|
28 |
+
"quantization_config": {
|
29 |
+
"quant_method": "exl2",
|
30 |
+
"version": "0.0.19",
|
31 |
+
"bits": 5.5,
|
32 |
+
"head_bits": 6,
|
33 |
+
"calibration": {
|
34 |
+
"rows": 100,
|
35 |
+
"length": 2048,
|
36 |
+
"dataset": "(default)"
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15587432448
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
198 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
200 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
201 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
202 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
203 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
204 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
205 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
206 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
207 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
208 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
209 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
210 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
211 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
212 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
213 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
214 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
215 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
224 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
225 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
226 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
227 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
228 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
229 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
230 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
231 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
232 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
233 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
234 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
235 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
236 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
237 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
238 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
239 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
240 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
241 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
242 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
243 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
244 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
245 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
246 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
247 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
248 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
249 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
250 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
251 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
252 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
253 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
254 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
255 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
256 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
257 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
258 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
259 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
260 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
261 |
+
}
|
262 |
+
}
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b06af8520dd1005b095db46259873a489730f55f5b2b81dfae392c9c4abe7f8
|
3 |
+
size 5637419716
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenization_neo.py
ADDED
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright 2024 NEO Inc. All Rights Reserved.
|
2 |
+
|
3 |
+
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
|
4 |
+
#
|
5 |
+
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
6 |
+
# and OPT implementations in this library. It has been modified from its
|
7 |
+
# original forms to accommodate minor architectural differences compared
|
8 |
+
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
9 |
+
#
|
10 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
11 |
+
# you may not use this file except in compliance with the License.
|
12 |
+
# You may obtain a copy of the License at
|
13 |
+
#
|
14 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
15 |
+
#
|
16 |
+
# Unless required by applicable law or agreed to in writing, software
|
17 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
18 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
19 |
+
# See the License for the specific language governing permissions and
|
20 |
+
# limitations under the License.
|
21 |
+
|
22 |
+
import os
|
23 |
+
from shutil import copyfile
|
24 |
+
from typing import Any, Dict, List, Optional, Tuple
|
25 |
+
|
26 |
+
import sentencepiece as spm
|
27 |
+
|
28 |
+
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
|
29 |
+
from transformers.utils import logging
|
30 |
+
|
31 |
+
|
32 |
+
logger = logging.get_logger(__name__)
|
33 |
+
|
34 |
+
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
|
35 |
+
|
36 |
+
PRETRAINED_VOCAB_FILES_MAP = {
|
37 |
+
"vocab_file": {},
|
38 |
+
"tokenizer_file": {},
|
39 |
+
}
|
40 |
+
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
|
41 |
+
|
42 |
+
|
43 |
+
class NEOTokenizer(PreTrainedTokenizer):
|
44 |
+
"""
|
45 |
+
Construct a NEO tokenizer. Based on byte-level Byte-Pair-Encoding.
|
46 |
+
|
47 |
+
Args:
|
48 |
+
vocab_file (`str`):
|
49 |
+
Path to the vocabulary file.
|
50 |
+
"""
|
51 |
+
|
52 |
+
vocab_files_names = VOCAB_FILES_NAMES
|
53 |
+
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
54 |
+
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
|
55 |
+
model_input_names = ["input_ids", "attention_mask"]
|
56 |
+
|
57 |
+
def __init__(
|
58 |
+
self,
|
59 |
+
vocab_file,
|
60 |
+
unk_token="<unk>",
|
61 |
+
bos_token="<s>",
|
62 |
+
eos_token="</s>",
|
63 |
+
pad_token=None,
|
64 |
+
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
65 |
+
add_bos_token=True,
|
66 |
+
add_eos_token=False,
|
67 |
+
clean_up_tokenization_spaces=False,
|
68 |
+
**kwargs,
|
69 |
+
):
|
70 |
+
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
71 |
+
bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
|
72 |
+
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
|
73 |
+
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
|
74 |
+
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
75 |
+
|
76 |
+
self.vocab_file = vocab_file
|
77 |
+
self.add_bos_token = add_bos_token
|
78 |
+
self.add_eos_token = add_eos_token
|
79 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
80 |
+
self.sp_model.Load(vocab_file)
|
81 |
+
|
82 |
+
super().__init__(
|
83 |
+
bos_token=bos_token,
|
84 |
+
eos_token=eos_token,
|
85 |
+
unk_token=unk_token,
|
86 |
+
pad_token=pad_token,
|
87 |
+
add_bos_token=add_bos_token,
|
88 |
+
add_eos_token=add_eos_token,
|
89 |
+
sp_model_kwargs=self.sp_model_kwargs,
|
90 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
91 |
+
**kwargs,
|
92 |
+
)
|
93 |
+
|
94 |
+
def __getstate__(self):
|
95 |
+
state = self.__dict__.copy()
|
96 |
+
state["sp_model"] = None
|
97 |
+
return state
|
98 |
+
|
99 |
+
def __setstate__(self, d):
|
100 |
+
self.__dict__ = d
|
101 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
102 |
+
self.sp_model.Load(self.vocab_file)
|
103 |
+
|
104 |
+
@property
|
105 |
+
def vocab_size(self):
|
106 |
+
"""Returns vocab size"""
|
107 |
+
return self.sp_model.get_piece_size()
|
108 |
+
|
109 |
+
def get_vocab(self):
|
110 |
+
"""Returns vocab as a dict"""
|
111 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
112 |
+
vocab.update(self.added_tokens_encoder)
|
113 |
+
return vocab
|
114 |
+
|
115 |
+
def _tokenize(self, text):
|
116 |
+
"""Returns a tokenized string."""
|
117 |
+
return self.sp_model.encode(text, out_type=str)
|
118 |
+
|
119 |
+
def _convert_token_to_id(self, token):
|
120 |
+
"""Converts a token (str) in an id using the vocab."""
|
121 |
+
return self.sp_model.piece_to_id(token)
|
122 |
+
|
123 |
+
def _convert_id_to_token(self, index):
|
124 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
125 |
+
token = self.sp_model.IdToPiece(index)
|
126 |
+
return token
|
127 |
+
|
128 |
+
def convert_tokens_to_string(self, tokens):
|
129 |
+
"""Converts a sequence of tokens (string) in a single string."""
|
130 |
+
current_sub_tokens = []
|
131 |
+
out_string = ""
|
132 |
+
prev_is_special = False
|
133 |
+
for i, token in enumerate(tokens):
|
134 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
135 |
+
if token in self.all_special_tokens:
|
136 |
+
if not prev_is_special and i != 0:
|
137 |
+
out_string += " "
|
138 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
139 |
+
prev_is_special = True
|
140 |
+
current_sub_tokens = []
|
141 |
+
else:
|
142 |
+
current_sub_tokens.append(token)
|
143 |
+
prev_is_special = False
|
144 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
145 |
+
return out_string
|
146 |
+
|
147 |
+
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
148 |
+
"""
|
149 |
+
Save the vocabulary and special tokens file to a directory.
|
150 |
+
|
151 |
+
Args:
|
152 |
+
save_directory (`str`):
|
153 |
+
The directory in which to save the vocabulary.
|
154 |
+
|
155 |
+
Returns:
|
156 |
+
`Tuple(str)`: Paths to the files saved.
|
157 |
+
"""
|
158 |
+
if not os.path.isdir(save_directory):
|
159 |
+
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
160 |
+
return
|
161 |
+
out_vocab_file = os.path.join(
|
162 |
+
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
|
163 |
+
)
|
164 |
+
|
165 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
166 |
+
copyfile(self.vocab_file, out_vocab_file)
|
167 |
+
elif not os.path.isfile(self.vocab_file):
|
168 |
+
with open(out_vocab_file, "wb") as fi:
|
169 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
170 |
+
fi.write(content_spiece_model)
|
171 |
+
|
172 |
+
return (out_vocab_file,)
|
173 |
+
|
174 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
175 |
+
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
176 |
+
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
177 |
+
|
178 |
+
output = bos_token_id + token_ids_0 + eos_token_id
|
179 |
+
|
180 |
+
if token_ids_1 is not None:
|
181 |
+
output = output + bos_token_id + token_ids_1 + eos_token_id
|
182 |
+
|
183 |
+
return output
|
184 |
+
|
185 |
+
def get_special_tokens_mask(
|
186 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
187 |
+
) -> List[int]:
|
188 |
+
"""
|
189 |
+
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
190 |
+
special tokens using the tokenizer `prepare_for_model` method.
|
191 |
+
|
192 |
+
Args:
|
193 |
+
token_ids_0 (`List[int]`):
|
194 |
+
List of IDs.
|
195 |
+
token_ids_1 (`List[int]`, *optional*):
|
196 |
+
Optional second list of IDs for sequence pairs.
|
197 |
+
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
198 |
+
Whether or not the token list is already formatted with special tokens for the model.
|
199 |
+
|
200 |
+
Returns:
|
201 |
+
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
202 |
+
"""
|
203 |
+
if already_has_special_tokens:
|
204 |
+
return super().get_special_tokens_mask(
|
205 |
+
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
206 |
+
)
|
207 |
+
|
208 |
+
bos_token_id = [1] if self.add_bos_token else []
|
209 |
+
eos_token_id = [1] if self.add_eos_token else []
|
210 |
+
|
211 |
+
if token_ids_1 is None:
|
212 |
+
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
|
213 |
+
return (
|
214 |
+
bos_token_id
|
215 |
+
+ ([0] * len(token_ids_0))
|
216 |
+
+ eos_token_id
|
217 |
+
+ bos_token_id
|
218 |
+
+ ([0] * len(token_ids_1))
|
219 |
+
+ eos_token_id
|
220 |
+
)
|
221 |
+
|
222 |
+
def create_token_type_ids_from_sequences(
|
223 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
224 |
+
) -> List[int]:
|
225 |
+
"""
|
226 |
+
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
|
227 |
+
sequence pair mask has the following format:
|
228 |
+
|
229 |
+
```
|
230 |
+
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
|
231 |
+
| first sequence | second sequence |
|
232 |
+
```
|
233 |
+
|
234 |
+
if token_ids_1 is None, only returns the first portion of the mask (0s).
|
235 |
+
|
236 |
+
Args:
|
237 |
+
token_ids_0 (`List[int]`):
|
238 |
+
List of ids.
|
239 |
+
token_ids_1 (`List[int]`, *optional*):
|
240 |
+
Optional second list of IDs for sequence pairs.
|
241 |
+
|
242 |
+
Returns:
|
243 |
+
`List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
|
244 |
+
"""
|
245 |
+
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
246 |
+
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
247 |
+
|
248 |
+
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
|
249 |
+
|
250 |
+
if token_ids_1 is not None:
|
251 |
+
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
|
252 |
+
|
253 |
+
return output
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6a2447b0e5664cabb2481587597102d82f42f0ccb7ef22e1c2d95494a8b03c5
|
3 |
+
size 1002561
|
tokenizer_config.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": true,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": true,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"64000": {
|
30 |
+
"content": "<|CLS|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"64001": {
|
38 |
+
"content": "<|SEP|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"64002": {
|
46 |
+
"content": "<|EOD|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"64003": {
|
54 |
+
"content": "<|MASK|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"64004": {
|
62 |
+
"content": "<|PAD|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"additional_special_tokens": [
|
71 |
+
"<|CLS|>",
|
72 |
+
"<|SEP|>",
|
73 |
+
"<|EOD|>",
|
74 |
+
"<|MASK|>",
|
75 |
+
"<|PAD|>"
|
76 |
+
],
|
77 |
+
"auto_map": {
|
78 |
+
"AutoTokenizer": [
|
79 |
+
"tokenization_neo.NEOTokenizer",
|
80 |
+
null
|
81 |
+
]
|
82 |
+
},
|
83 |
+
"bos_token": "<s>",
|
84 |
+
"chat_template": "{% set system_message = 'You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don\\'t know the answer to a question, please don\\'t share false information.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
85 |
+
"clean_up_tokenization_spaces": false,
|
86 |
+
"eos_token": "</s>",
|
87 |
+
"model_max_length": 4096,
|
88 |
+
"pad_token": "<unk>",
|
89 |
+
"padding_side": "right",
|
90 |
+
"sp_model_kwargs": {},
|
91 |
+
"split_special_tokens": false,
|
92 |
+
"tokenizer_class": "NEOTokenizer",
|
93 |
+
"unk_token": "<unk>",
|
94 |
+
"use_fast": false
|
95 |
+
}
|