laquythang
commited on
Commit
•
a0ccfaa
1
Parent(s):
4962b50
End of training
Browse files- README.md +146 -0
- adapter_config.json +31 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +16 -0
- config.json +186 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +156 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: mit
|
4 |
+
base_model: migtissera/Tess-v2.5-Phi-3-medium-128k-14B
|
5 |
+
tags:
|
6 |
+
- axolotl
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: 4c207c82-ea29-4763-878a-6f54b59bc718
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
17 |
+
<details><summary>See axolotl config</summary>
|
18 |
+
|
19 |
+
axolotl version: `0.4.1`
|
20 |
+
```yaml
|
21 |
+
adapter: lora
|
22 |
+
base_model: migtissera/Tess-v2.5-Phi-3-medium-128k-14B
|
23 |
+
bf16: auto
|
24 |
+
chat_template: llama3
|
25 |
+
dataset_prepared_path: null
|
26 |
+
datasets:
|
27 |
+
- data_files:
|
28 |
+
- 6a8f4ac733647cc6_train_data.json
|
29 |
+
ds_type: json
|
30 |
+
format: custom
|
31 |
+
path: /workspace/input_data/6a8f4ac733647cc6_train_data.json
|
32 |
+
type:
|
33 |
+
field_instruction: question
|
34 |
+
field_output: answerKey
|
35 |
+
format: '{instruction}'
|
36 |
+
no_input_format: '{instruction}'
|
37 |
+
system_format: '{system}'
|
38 |
+
system_prompt: ''
|
39 |
+
debug: null
|
40 |
+
deepspeed: null
|
41 |
+
early_stopping_patience: null
|
42 |
+
eval_max_new_tokens: 128
|
43 |
+
eval_table_size: null
|
44 |
+
evals_per_epoch: 1
|
45 |
+
flash_attention: false
|
46 |
+
fp16: null
|
47 |
+
fsdp: null
|
48 |
+
fsdp_config: null
|
49 |
+
gradient_accumulation_steps: 1
|
50 |
+
gradient_checkpointing: true
|
51 |
+
group_by_length: false
|
52 |
+
hub_model_id: laquythang/4c207c82-ea29-4763-878a-6f54b59bc718
|
53 |
+
hub_repo: null
|
54 |
+
hub_strategy: end
|
55 |
+
hub_token: null
|
56 |
+
learning_rate: 0.0002
|
57 |
+
load_in_4bit: true
|
58 |
+
load_in_8bit: true
|
59 |
+
local_rank: null
|
60 |
+
logging_steps: 1
|
61 |
+
lora_alpha: 32
|
62 |
+
lora_dropout: 0.05
|
63 |
+
lora_fan_in_fan_out: null
|
64 |
+
lora_model_dir: null
|
65 |
+
lora_r: 16
|
66 |
+
lora_target_linear: true
|
67 |
+
lr_scheduler: cosine
|
68 |
+
max_steps: 10
|
69 |
+
micro_batch_size: 1
|
70 |
+
mlflow_experiment_name: /tmp/6a8f4ac733647cc6_train_data.json
|
71 |
+
model_type: AutoModelForCausalLM
|
72 |
+
num_epochs: 1
|
73 |
+
optimizer: adamw_bnb_8bit
|
74 |
+
output_dir: miner_id_24
|
75 |
+
pad_to_sequence_len: true
|
76 |
+
resume_from_checkpoint: null
|
77 |
+
s2_attention: null
|
78 |
+
sample_packing: false
|
79 |
+
saves_per_epoch: 1
|
80 |
+
sequence_len: 2048
|
81 |
+
strict: false
|
82 |
+
tf32: false
|
83 |
+
tokenizer_type: AutoTokenizer
|
84 |
+
train_on_inputs: false
|
85 |
+
trust_remote_code: true
|
86 |
+
val_set_size: 0.05
|
87 |
+
wandb_entity: null
|
88 |
+
wandb_mode: online
|
89 |
+
wandb_name: 4c207c82-ea29-4763-878a-6f54b59bc718
|
90 |
+
wandb_project: Gradients-On-Demand
|
91 |
+
wandb_run: your_name
|
92 |
+
wandb_runid: 4c207c82-ea29-4763-878a-6f54b59bc718
|
93 |
+
warmup_steps: 10
|
94 |
+
weight_decay: 0.0
|
95 |
+
xformers_attention: true
|
96 |
+
|
97 |
+
```
|
98 |
+
|
99 |
+
</details><br>
|
100 |
+
|
101 |
+
# 4c207c82-ea29-4763-878a-6f54b59bc718
|
102 |
+
|
103 |
+
This model is a fine-tuned version of [migtissera/Tess-v2.5-Phi-3-medium-128k-14B](https://huggingface.co/migtissera/Tess-v2.5-Phi-3-medium-128k-14B) on the None dataset.
|
104 |
+
It achieves the following results on the evaluation set:
|
105 |
+
- Loss: 4.4289
|
106 |
+
|
107 |
+
## Model description
|
108 |
+
|
109 |
+
More information needed
|
110 |
+
|
111 |
+
## Intended uses & limitations
|
112 |
+
|
113 |
+
More information needed
|
114 |
+
|
115 |
+
## Training and evaluation data
|
116 |
+
|
117 |
+
More information needed
|
118 |
+
|
119 |
+
## Training procedure
|
120 |
+
|
121 |
+
### Training hyperparameters
|
122 |
+
|
123 |
+
The following hyperparameters were used during training:
|
124 |
+
- learning_rate: 0.0002
|
125 |
+
- train_batch_size: 1
|
126 |
+
- eval_batch_size: 1
|
127 |
+
- seed: 42
|
128 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
129 |
+
- lr_scheduler_type: cosine
|
130 |
+
- lr_scheduler_warmup_steps: 10
|
131 |
+
- training_steps: 10
|
132 |
+
|
133 |
+
### Training results
|
134 |
+
|
135 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
136 |
+
|:-------------:|:------:|:----:|:---------------:|
|
137 |
+
| 5.2407 | 0.0052 | 10 | 4.4289 |
|
138 |
+
|
139 |
+
|
140 |
+
### Framework versions
|
141 |
+
|
142 |
+
- PEFT 0.13.2
|
143 |
+
- Transformers 4.46.0
|
144 |
+
- Pytorch 2.5.0+cu124
|
145 |
+
- Datasets 3.0.1
|
146 |
+
- Tokenizers 0.20.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "migtissera/Tess-v2.5-Phi-3-medium-128k-14B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"gate_up_proj",
|
25 |
+
"qkv_proj",
|
26 |
+
"o_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:185b030911b55156c6089e5829f2da526d6977be3c338c572ae00a57b2e14723
|
3 |
+
size 222938570
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5551758c24bb1d5b774fe4bbe2f266ca4a8a60596c8aba2da79fdf04c25e5c3
|
3 |
+
size 222865880
|
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|end_of_text|>": 32012,
|
4 |
+
"<|endoftext|>": 32000,
|
5 |
+
"<|end|>": 32007,
|
6 |
+
"<|im_end|>": 32011,
|
7 |
+
"<|im_start|>": 32013,
|
8 |
+
"<|placeholder1|>": 32002,
|
9 |
+
"<|placeholder2|>": 32003,
|
10 |
+
"<|placeholder3|>": 32004,
|
11 |
+
"<|placeholder4|>": 32005,
|
12 |
+
"<|placeholder5|>": 32008,
|
13 |
+
"<|placeholder6|>": 32009,
|
14 |
+
"<|system|>": 32006,
|
15 |
+
"<|user|>": 32010
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "migtissera/Tess-v2.5-Phi-3-medium-128k-14B",
|
4 |
+
"architectures": [
|
5 |
+
"Phi3ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
|
11 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--modeling_phi3.Phi3ForCausalLM"
|
12 |
+
},
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"embd_pdrop": 0.0,
|
15 |
+
"eos_token_id": 32011,
|
16 |
+
"hidden_act": "silu",
|
17 |
+
"hidden_size": 5120,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 17920,
|
20 |
+
"max_position_embeddings": 131072,
|
21 |
+
"model_type": "phi3",
|
22 |
+
"num_attention_heads": 40,
|
23 |
+
"num_hidden_layers": 40,
|
24 |
+
"num_key_value_heads": 10,
|
25 |
+
"original_max_position_embeddings": 4096,
|
26 |
+
"pad_token_id": null,
|
27 |
+
"quantization_config": {
|
28 |
+
"_load_in_4bit": false,
|
29 |
+
"_load_in_8bit": true,
|
30 |
+
"bnb_4bit_compute_dtype": "float32",
|
31 |
+
"bnb_4bit_quant_storage": "uint8",
|
32 |
+
"bnb_4bit_quant_type": "fp4",
|
33 |
+
"bnb_4bit_use_double_quant": false,
|
34 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
35 |
+
"llm_int8_has_fp16_weight": false,
|
36 |
+
"llm_int8_skip_modules": null,
|
37 |
+
"llm_int8_threshold": 6.0,
|
38 |
+
"load_in_4bit": false,
|
39 |
+
"load_in_8bit": true,
|
40 |
+
"quant_method": "bitsandbytes"
|
41 |
+
},
|
42 |
+
"resid_pdrop": 0.0,
|
43 |
+
"rms_norm_eps": 1e-05,
|
44 |
+
"rope_scaling": {
|
45 |
+
"long_factor": [
|
46 |
+
1.0,
|
47 |
+
1.0,
|
48 |
+
1.0,
|
49 |
+
1.0,
|
50 |
+
1.0,
|
51 |
+
1.0,
|
52 |
+
1.0,
|
53 |
+
1.0,
|
54 |
+
1.0,
|
55 |
+
1.0,
|
56 |
+
1.0,
|
57 |
+
1.0,
|
58 |
+
1.0,
|
59 |
+
1.25,
|
60 |
+
1.25,
|
61 |
+
1.5,
|
62 |
+
2.0,
|
63 |
+
2.75,
|
64 |
+
5.75,
|
65 |
+
5.75,
|
66 |
+
6.5,
|
67 |
+
9.25,
|
68 |
+
11.0,
|
69 |
+
13.25,
|
70 |
+
19.25,
|
71 |
+
19.75,
|
72 |
+
19.75,
|
73 |
+
21.25,
|
74 |
+
21.5,
|
75 |
+
26.5,
|
76 |
+
30.0,
|
77 |
+
33.75,
|
78 |
+
35.25,
|
79 |
+
38.5,
|
80 |
+
42.0,
|
81 |
+
42.25,
|
82 |
+
46.0,
|
83 |
+
47.0,
|
84 |
+
50.0,
|
85 |
+
50.5,
|
86 |
+
51.0,
|
87 |
+
52.0,
|
88 |
+
52.75,
|
89 |
+
53.75,
|
90 |
+
54.75,
|
91 |
+
57.0,
|
92 |
+
57.25,
|
93 |
+
58.5,
|
94 |
+
59.25,
|
95 |
+
59.5,
|
96 |
+
62.0,
|
97 |
+
62.5,
|
98 |
+
62.75,
|
99 |
+
63.25,
|
100 |
+
63.25,
|
101 |
+
63.25,
|
102 |
+
63.75,
|
103 |
+
64.0,
|
104 |
+
64.0,
|
105 |
+
64.25,
|
106 |
+
64.5,
|
107 |
+
64.5,
|
108 |
+
65.0,
|
109 |
+
65.0
|
110 |
+
],
|
111 |
+
"short_factor": [
|
112 |
+
1.0,
|
113 |
+
1.0,
|
114 |
+
1.0,
|
115 |
+
1.0,
|
116 |
+
1.0,
|
117 |
+
1.0,
|
118 |
+
1.01,
|
119 |
+
1.02,
|
120 |
+
1.02,
|
121 |
+
1.04,
|
122 |
+
1.04,
|
123 |
+
1.07,
|
124 |
+
1.07,
|
125 |
+
1.1,
|
126 |
+
1.3000000000000003,
|
127 |
+
1.3000000000000003,
|
128 |
+
1.5000000000000004,
|
129 |
+
1.5700000000000005,
|
130 |
+
1.9000000000000008,
|
131 |
+
2.3100000000000014,
|
132 |
+
2.759999999999992,
|
133 |
+
3.3899999999999784,
|
134 |
+
3.9399999999999666,
|
135 |
+
4.009999999999965,
|
136 |
+
4.289999999999959,
|
137 |
+
4.349999999999958,
|
138 |
+
5.349999999999937,
|
139 |
+
6.659999999999909,
|
140 |
+
7.029999999999901,
|
141 |
+
7.51999999999989,
|
142 |
+
8.00999999999988,
|
143 |
+
8.249999999999876,
|
144 |
+
8.279999999999875,
|
145 |
+
9.629999999999846,
|
146 |
+
9.89999999999984,
|
147 |
+
10.589999999999826,
|
148 |
+
11.049999999999816,
|
149 |
+
11.7899999999998,
|
150 |
+
12.189999999999792,
|
151 |
+
12.889999999999777,
|
152 |
+
13.129999999999772,
|
153 |
+
13.16999999999977,
|
154 |
+
13.20999999999977,
|
155 |
+
13.479999999999764,
|
156 |
+
13.539999999999763,
|
157 |
+
13.779999999999758,
|
158 |
+
13.929999999999755,
|
159 |
+
14.429999999999744,
|
160 |
+
14.759999999999737,
|
161 |
+
15.149999999999729,
|
162 |
+
15.419999999999723,
|
163 |
+
15.53999999999972,
|
164 |
+
15.659999999999718,
|
165 |
+
15.749999999999716,
|
166 |
+
15.759999999999716,
|
167 |
+
15.799999999999715,
|
168 |
+
16.05999999999971,
|
169 |
+
16.079999999999714,
|
170 |
+
16.11999999999972,
|
171 |
+
16.11999999999972,
|
172 |
+
16.18999999999973,
|
173 |
+
16.31999999999975,
|
174 |
+
16.539999999999786,
|
175 |
+
16.799999999999827
|
176 |
+
],
|
177 |
+
"type": "su"
|
178 |
+
},
|
179 |
+
"rope_theta": 10000.0,
|
180 |
+
"sliding_window": 131072,
|
181 |
+
"tie_word_embeddings": false,
|
182 |
+
"torch_dtype": "bfloat16",
|
183 |
+
"transformers_version": "4.46.0",
|
184 |
+
"use_cache": false,
|
185 |
+
"vocab_size": 32064
|
186 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
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": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|im_end|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|end_of_text|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|im_start|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
}
|
142 |
+
},
|
143 |
+
"bos_token": "<s>",
|
144 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
145 |
+
"clean_up_tokenization_spaces": false,
|
146 |
+
"eos_token": "<|im_end|>",
|
147 |
+
"legacy": false,
|
148 |
+
"model_max_length": 131072,
|
149 |
+
"pad_token": "<|end_of_text|>",
|
150 |
+
"padding_side": "left",
|
151 |
+
"sp_model_kwargs": {},
|
152 |
+
"spaces_between_special_tokens": false,
|
153 |
+
"tokenizer_class": "LlamaTokenizer",
|
154 |
+
"unk_token": "<unk>",
|
155 |
+
"use_default_system_prompt": false
|
156 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd19b928c2d6fd37ec8e02ef7d6e697b82e043452d92ef3be5429b0cc9be6cb0
|
3 |
+
size 6776
|