Upload 8 files
Browse files- README.md +162 -0
- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- config.json +43 -0
- configuration_stablelm_epoch.py +110 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +238 -0
README.md
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: stabilityai/stablelm-3b-4e1t
|
7 |
+
model-index:
|
8 |
+
- name: everything
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
16 |
+
<details><summary>See axolotl config</summary>
|
17 |
+
|
18 |
+
axolotl version: `0.3.0`
|
19 |
+
```yaml
|
20 |
+
base_model: stabilityai/stablelm-3b-4e1t
|
21 |
+
base_model_config: stabilityai/stablelm-3b-4e1t
|
22 |
+
trust_remote_code: true
|
23 |
+
model_type: AutoModelForCausalLM
|
24 |
+
tokenizer_type: GPTNeoXTokenizerFast
|
25 |
+
|
26 |
+
load_in_8bit: false
|
27 |
+
load_in_4bit: true
|
28 |
+
strict: false
|
29 |
+
|
30 |
+
datasets:
|
31 |
+
- path: totally-not-an-llm/EverythingLM-data-V3
|
32 |
+
type: alpaca
|
33 |
+
|
34 |
+
dataset_prepared_path:
|
35 |
+
val_set_size: 0.005
|
36 |
+
output_dir: ./everything
|
37 |
+
|
38 |
+
adapter: qlora
|
39 |
+
|
40 |
+
sequence_len: 1024
|
41 |
+
sample_packing: false
|
42 |
+
pad_to_sequence_len: true
|
43 |
+
save_safetensors: false
|
44 |
+
|
45 |
+
lora_r: 128
|
46 |
+
lora_alpha: 256
|
47 |
+
lora_dropout: 0.05
|
48 |
+
lora_target_linear: false
|
49 |
+
lora_fan_in_fan_out:
|
50 |
+
lora_modules_to_save:
|
51 |
+
- embed_tokens
|
52 |
+
- lm_head
|
53 |
+
lora_target_modules:
|
54 |
+
- q_proj
|
55 |
+
- v_proj
|
56 |
+
|
57 |
+
gradient_accumulation_steps: 1
|
58 |
+
micro_batch_size: 16
|
59 |
+
num_epochs: 5
|
60 |
+
optimizer: paged_adamw_32bit
|
61 |
+
lr_scheduler: cosine
|
62 |
+
learning_rate: 0.00005
|
63 |
+
|
64 |
+
train_on_inputs: false
|
65 |
+
group_by_length: false
|
66 |
+
bf16: true
|
67 |
+
fp16: false
|
68 |
+
tf32: false
|
69 |
+
|
70 |
+
gradient_checkpointing: true
|
71 |
+
early_stopping_patience:
|
72 |
+
resume_from_checkpoint:
|
73 |
+
local_rank:
|
74 |
+
logging_steps: 1
|
75 |
+
xformers_attention:
|
76 |
+
flash_attention: true
|
77 |
+
|
78 |
+
warmup_steps: 10
|
79 |
+
evals_per_epoch: 1
|
80 |
+
eval_table_size:
|
81 |
+
saves_per_epoch: 1
|
82 |
+
debug:
|
83 |
+
deepspeed:
|
84 |
+
weight_decay: 0.0
|
85 |
+
fsdp:
|
86 |
+
fsdp_config:
|
87 |
+
special_tokens:
|
88 |
+
bos_token: "<|endoftext|>"
|
89 |
+
eos_token: "<|im_end|>"
|
90 |
+
unk_token: "<|endoftext|>"
|
91 |
+
tokens:
|
92 |
+
- "<|im_start|>"
|
93 |
+
- "<|im_end|>"
|
94 |
+
|
95 |
+
```
|
96 |
+
|
97 |
+
</details><br>
|
98 |
+
|
99 |
+
# everything
|
100 |
+
|
101 |
+
This model is a fine-tuned version of [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) on the None dataset.
|
102 |
+
It achieves the following results on the evaluation set:
|
103 |
+
- Loss: 0.8096
|
104 |
+
|
105 |
+
## Model description
|
106 |
+
|
107 |
+
More information needed
|
108 |
+
|
109 |
+
## Intended uses & limitations
|
110 |
+
|
111 |
+
More information needed
|
112 |
+
|
113 |
+
## Training and evaluation data
|
114 |
+
|
115 |
+
More information needed
|
116 |
+
|
117 |
+
## Training procedure
|
118 |
+
|
119 |
+
|
120 |
+
The following `bitsandbytes` quantization config was used during training:
|
121 |
+
- quant_method: bitsandbytes
|
122 |
+
- load_in_8bit: False
|
123 |
+
- load_in_4bit: True
|
124 |
+
- llm_int8_threshold: 6.0
|
125 |
+
- llm_int8_skip_modules: None
|
126 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
127 |
+
- llm_int8_has_fp16_weight: False
|
128 |
+
- bnb_4bit_quant_type: nf4
|
129 |
+
- bnb_4bit_use_double_quant: True
|
130 |
+
- bnb_4bit_compute_dtype: bfloat16
|
131 |
+
|
132 |
+
### Training hyperparameters
|
133 |
+
|
134 |
+
The following hyperparameters were used during training:
|
135 |
+
- learning_rate: 5e-05
|
136 |
+
- train_batch_size: 16
|
137 |
+
- eval_batch_size: 16
|
138 |
+
- seed: 42
|
139 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
140 |
+
- lr_scheduler_type: cosine
|
141 |
+
- lr_scheduler_warmup_steps: 10
|
142 |
+
- num_epochs: 5
|
143 |
+
|
144 |
+
### Training results
|
145 |
+
|
146 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
147 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
148 |
+
| 1.3873 | 0.02 | 1 | 1.6256 |
|
149 |
+
| 1.1399 | 1.0 | 60 | 0.8263 |
|
150 |
+
| 1.5717 | 2.0 | 120 | 0.8054 |
|
151 |
+
| 0.6861 | 3.0 | 180 | 0.8149 |
|
152 |
+
| 0.9527 | 4.0 | 240 | 0.8036 |
|
153 |
+
| 0.5738 | 5.0 | 300 | 0.8096 |
|
154 |
+
|
155 |
+
|
156 |
+
### Framework versions
|
157 |
+
|
158 |
+
- PEFT 0.7.0
|
159 |
+
- Transformers 4.37.0.dev0
|
160 |
+
- Pytorch 2.0.1+cu117
|
161 |
+
- Datasets 2.16.1
|
162 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 256,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": [
|
17 |
+
"embed_tokens",
|
18 |
+
"lm_head"
|
19 |
+
],
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 128,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"v_proj",
|
26 |
+
"q_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM"
|
29 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5331411cd58725567d33a7d5d8667628af7b65fbf16333d456da18d115120cf7
|
3 |
+
size 682931861
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stablelm-3b-4e1t",
|
3 |
+
"architectures": [
|
4 |
+
"StableLMEpochForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
|
8 |
+
"AutoModelForCausalLM": "stabilityai/stablelm-3b-4e1t--modeling_stablelm_epoch.StableLMEpochForCausalLM"
|
9 |
+
},
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 2560,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 6912,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"model_type": "stablelm_epoch",
|
18 |
+
"norm_eps": 1e-05,
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"quantization_config": {
|
24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_type": "nf4",
|
26 |
+
"bnb_4bit_use_double_quant": true,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": true,
|
32 |
+
"load_in_8bit": false,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
+
"rope_pct": 0.25,
|
36 |
+
"rope_theta": 10000,
|
37 |
+
"rotary_scaling_factor": 1.0,
|
38 |
+
"tie_word_embeddings": false,
|
39 |
+
"torch_dtype": "bfloat16",
|
40 |
+
"transformers_version": "4.37.0.dev0",
|
41 |
+
"use_cache": false,
|
42 |
+
"vocab_size": 50304
|
43 |
+
}
|
configuration_stablelm_epoch.py
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2023 Stability and The HuggingFace Inc. team. All rights reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
""" StableLM Epoch model configuration"""
|
16 |
+
from transformers import PretrainedConfig
|
17 |
+
from transformers.utils import logging
|
18 |
+
|
19 |
+
|
20 |
+
logger = logging.get_logger(__name__)
|
21 |
+
|
22 |
+
|
23 |
+
class StableLMEpochConfig(PretrainedConfig):
|
24 |
+
r"""
|
25 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
26 |
+
documentation from [`PretrainedConfig`] for more information.
|
27 |
+
|
28 |
+
Args:
|
29 |
+
vocab_size (`int`, *optional*, defaults to 50_304):
|
30 |
+
Vocabulary size of the StableLM model. Defines the number of different tokens that
|
31 |
+
can be represented by the `inputs_ids` passed when calling [`StableLMEpochModel`].
|
32 |
+
intermediate_size (`int`, *optional*, defaults to 6912):
|
33 |
+
Dimension of the MLP representations.
|
34 |
+
hidden_size (`int`, *optional*, defaults to 2560):
|
35 |
+
Dimension of the decoder layers and the pooler layer.
|
36 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
37 |
+
Number of hidden layers in the Transformer decoder.
|
38 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
39 |
+
Number of attention heads for each attention layer in the Transformer encoder.
|
40 |
+
num_key_value_heads (`int`, *optional*):
|
41 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
42 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
43 |
+
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
44 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
45 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
46 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
47 |
+
`num_attention_heads`.
|
48 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
49 |
+
The non-linear activation function (function or string).
|
50 |
+
rope_pct (`float`, *optional*, defaults to 1.0):
|
51 |
+
Percentage of hidden dimensions to allocate to rotary embeddings.
|
52 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
53 |
+
The base period of the RoPE embeddings.
|
54 |
+
max_position_embeddings (`int`, *optional*, defaults to 2048):
|
55 |
+
The maximum sequence length that this model might ever be used with.
|
56 |
+
Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
|
57 |
+
initializer_range (`float`, *optional*, defaults to 1e-5):
|
58 |
+
The standard deviation of the truncated_normal_initializer for initializing
|
59 |
+
all weight matrices.
|
60 |
+
norm_eps (`float`, *optional*, defaults to 1e-8):
|
61 |
+
The epsilon used by the normalization layers.
|
62 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
63 |
+
Whether or not the model should return the last key/values attentions
|
64 |
+
(not used by all models). Only relevant if `config.is_decoder=True`.
|
65 |
+
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
|
66 |
+
Whether to tie weight embeddings
|
67 |
+
"""
|
68 |
+
model_type = "stablelm_epoch"
|
69 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
70 |
+
|
71 |
+
def __init__(
|
72 |
+
self,
|
73 |
+
vocab_size=50_304,
|
74 |
+
intermediate_size=6912,
|
75 |
+
hidden_size=2560,
|
76 |
+
num_hidden_layers=32,
|
77 |
+
num_attention_heads=32,
|
78 |
+
num_key_value_heads=32,
|
79 |
+
hidden_act="silu",
|
80 |
+
rope_pct=0.25,
|
81 |
+
rope_theta=10_000,
|
82 |
+
max_position_embeddings=4096,
|
83 |
+
initializer_range=0.02,
|
84 |
+
norm_eps=1.0e-5,
|
85 |
+
use_cache=True,
|
86 |
+
bos_token_id=0,
|
87 |
+
eos_token_id=2,
|
88 |
+
tie_word_embeddings=False,
|
89 |
+
**kwargs,
|
90 |
+
):
|
91 |
+
self.vocab_size = vocab_size
|
92 |
+
self.max_position_embeddings = max_position_embeddings
|
93 |
+
self.intermediate_size = intermediate_size
|
94 |
+
self.hidden_size = hidden_size
|
95 |
+
self.num_hidden_layers = num_hidden_layers
|
96 |
+
self.num_attention_heads = num_attention_heads
|
97 |
+
self.num_key_value_heads = num_key_value_heads
|
98 |
+
self.hidden_act = hidden_act
|
99 |
+
self.rope_pct = rope_pct
|
100 |
+
self.rope_theta = rope_theta
|
101 |
+
self.initializer_range = initializer_range
|
102 |
+
self.norm_eps = norm_eps
|
103 |
+
self.use_cache = use_cache
|
104 |
+
self.tie_word_embeddings = tie_word_embeddings
|
105 |
+
super().__init__(
|
106 |
+
bos_token_id=bos_token_id,
|
107 |
+
eos_token_id=eos_token_id,
|
108 |
+
tie_word_embeddings=tie_word_embeddings,
|
109 |
+
**kwargs,
|
110 |
+
)
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
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 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|padding|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50254": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50255": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50256": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50257": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50258": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50259": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50260": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50261": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50262": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50263": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50264": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50265": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50266": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50267": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50268": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50269": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50270": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50271": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50272": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50273": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50274": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50275": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50276": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50277": {
|
205 |
+
"content": "[PAD]",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"50278": {
|
213 |
+
"content": "<|im_end|>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"50279": {
|
221 |
+
"content": "<|im_start|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
}
|
228 |
+
},
|
229 |
+
"bos_token": "<|endoftext|>",
|
230 |
+
"clean_up_tokenization_spaces": true,
|
231 |
+
"eos_token": "<|im_end|>",
|
232 |
+
"model_max_length": 1000000000000000019884624838656,
|
233 |
+
"pad_token": "[PAD]",
|
234 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
235 |
+
"trust_remote_code": true,
|
236 |
+
"unk_token": "<|endoftext|>",
|
237 |
+
"use_fast": true
|
238 |
+
}
|