Utshav/command-4-v01-Finetuned
Browse files- .gitattributes +1 -0
- README.md +113 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +322 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: CohereForAI/c4ai-command-r-v01-4bit
|
9 |
+
datasets:
|
10 |
+
- generator
|
11 |
+
model-index:
|
12 |
+
- name: c4ai-command-r-v01-SFT
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# c4ai-command-r-v01-SFT
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [CohereForAI/c4ai-command-r-v01-4bit](https://huggingface.co/CohereForAI/c4ai-command-r-v01-4bit) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6709
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2.5e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 0.03
|
49 |
+
- training_steps: 500
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
55 |
+
| 1.5906 | 0.2326 | 10 | 1.5675 |
|
56 |
+
| 1.5542 | 0.4651 | 20 | 1.4713 |
|
57 |
+
| 1.3934 | 0.6977 | 30 | 1.3839 |
|
58 |
+
| 1.346 | 0.9302 | 40 | 1.2949 |
|
59 |
+
| 1.2605 | 1.1628 | 50 | 1.2154 |
|
60 |
+
| 1.1887 | 1.3953 | 60 | 1.1361 |
|
61 |
+
| 1.0784 | 1.6279 | 70 | 1.0520 |
|
62 |
+
| 1.0086 | 1.8605 | 80 | 0.9770 |
|
63 |
+
| 0.9247 | 2.0930 | 90 | 0.9134 |
|
64 |
+
| 0.8671 | 2.3256 | 100 | 0.8640 |
|
65 |
+
| 0.8391 | 2.5581 | 110 | 0.8284 |
|
66 |
+
| 0.7849 | 2.7907 | 120 | 0.8026 |
|
67 |
+
| 0.7458 | 3.0233 | 130 | 0.7818 |
|
68 |
+
| 0.7377 | 3.2558 | 140 | 0.7684 |
|
69 |
+
| 0.7112 | 3.4884 | 150 | 0.7544 |
|
70 |
+
| 0.7054 | 3.7209 | 160 | 0.7430 |
|
71 |
+
| 0.7029 | 3.9535 | 170 | 0.7331 |
|
72 |
+
| 0.657 | 4.1860 | 180 | 0.7263 |
|
73 |
+
| 0.675 | 4.4186 | 190 | 0.7189 |
|
74 |
+
| 0.6695 | 4.6512 | 200 | 0.7117 |
|
75 |
+
| 0.6418 | 4.8837 | 210 | 0.7058 |
|
76 |
+
| 0.6348 | 5.1163 | 220 | 0.7028 |
|
77 |
+
| 0.6414 | 5.3488 | 230 | 0.6981 |
|
78 |
+
| 0.612 | 5.5814 | 240 | 0.6951 |
|
79 |
+
| 0.6114 | 5.8140 | 250 | 0.6909 |
|
80 |
+
| 0.6149 | 6.0465 | 260 | 0.6876 |
|
81 |
+
| 0.5978 | 6.2791 | 270 | 0.6884 |
|
82 |
+
| 0.5955 | 6.5116 | 280 | 0.6839 |
|
83 |
+
| 0.6112 | 6.7442 | 290 | 0.6802 |
|
84 |
+
| 0.5841 | 6.9767 | 300 | 0.6794 |
|
85 |
+
| 0.5746 | 7.2093 | 310 | 0.6801 |
|
86 |
+
| 0.5849 | 7.4419 | 320 | 0.6773 |
|
87 |
+
| 0.5863 | 7.6744 | 330 | 0.6760 |
|
88 |
+
| 0.5738 | 7.9070 | 340 | 0.6748 |
|
89 |
+
| 0.5696 | 8.1395 | 350 | 0.6739 |
|
90 |
+
| 0.5632 | 8.3721 | 360 | 0.6747 |
|
91 |
+
| 0.5732 | 8.6047 | 370 | 0.6737 |
|
92 |
+
| 0.5512 | 8.8372 | 380 | 0.6725 |
|
93 |
+
| 0.5761 | 9.0698 | 390 | 0.6716 |
|
94 |
+
| 0.5471 | 9.3023 | 400 | 0.6727 |
|
95 |
+
| 0.5579 | 9.5349 | 410 | 0.6724 |
|
96 |
+
| 0.573 | 9.7674 | 420 | 0.6714 |
|
97 |
+
| 0.5459 | 10.0 | 430 | 0.6708 |
|
98 |
+
| 0.5677 | 10.2326 | 440 | 0.6710 |
|
99 |
+
| 0.5453 | 10.4651 | 450 | 0.6708 |
|
100 |
+
| 0.5638 | 10.6977 | 460 | 0.6708 |
|
101 |
+
| 0.5473 | 10.9302 | 470 | 0.6709 |
|
102 |
+
| 0.5553 | 11.1628 | 480 | 0.6709 |
|
103 |
+
| 0.5535 | 11.3953 | 490 | 0.6708 |
|
104 |
+
| 0.5409 | 11.6279 | 500 | 0.6709 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- PEFT 0.10.1.dev0
|
110 |
+
- Transformers 4.40.0.dev0
|
111 |
+
- Pytorch 2.1.1+cu121
|
112 |
+
- Datasets 2.18.0
|
113 |
+
- Tokenizers 0.19.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "CohereForAI/c4ai-command-r-v01-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 16,
|
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 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c37f187d3d37fac2c421a09abffcea50537391d3a20d0b312d20046fb6f04cab
|
3 |
+
size 201926688
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<BOS_TOKEN>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|END_OF_TURN_TOKEN|>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c95c3fe9615f59c012b7bf5a8397d99c9ec0dff41e87440857fd49234f7df3cb
|
3 |
+
size 12777946
|
tokenizer_config.json
ADDED
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<PAD>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<UNK>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<CLS>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "<SEP>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "<MASK_TOKEN>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"5": {
|
47 |
+
"content": "<BOS_TOKEN>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"6": {
|
55 |
+
"content": "<EOS_TOKEN>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"7": {
|
63 |
+
"content": "<EOP_TOKEN>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"255000": {
|
71 |
+
"content": "<|START_OF_TURN_TOKEN|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"255001": {
|
79 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"255002": {
|
87 |
+
"content": "<|YES_TOKEN|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"255003": {
|
95 |
+
"content": "<|NO_TOKEN|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"255004": {
|
103 |
+
"content": "<|GOOD_TOKEN|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"255005": {
|
111 |
+
"content": "<|BAD_TOKEN|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"255006": {
|
119 |
+
"content": "<|USER_TOKEN|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"255007": {
|
127 |
+
"content": "<|CHATBOT_TOKEN|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"255008": {
|
135 |
+
"content": "<|SYSTEM_TOKEN|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"255009": {
|
143 |
+
"content": "<|USER_0_TOKEN|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"255010": {
|
151 |
+
"content": "<|USER_1_TOKEN|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"255011": {
|
159 |
+
"content": "<|USER_2_TOKEN|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"255012": {
|
167 |
+
"content": "<|USER_3_TOKEN|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"255013": {
|
175 |
+
"content": "<|USER_4_TOKEN|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"255014": {
|
183 |
+
"content": "<|USER_5_TOKEN|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"255015": {
|
191 |
+
"content": "<|USER_6_TOKEN|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"255016": {
|
199 |
+
"content": "<|USER_7_TOKEN|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"255017": {
|
207 |
+
"content": "<|USER_8_TOKEN|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"255018": {
|
215 |
+
"content": "<|USER_9_TOKEN|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"255019": {
|
223 |
+
"content": "<|EXTRA_0_TOKEN|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"255020": {
|
231 |
+
"content": "<|EXTRA_1_TOKEN|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"255021": {
|
239 |
+
"content": "<|EXTRA_2_TOKEN|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"255022": {
|
247 |
+
"content": "<|EXTRA_3_TOKEN|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"255023": {
|
255 |
+
"content": "<|EXTRA_4_TOKEN|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"255024": {
|
263 |
+
"content": "<|EXTRA_5_TOKEN|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"255025": {
|
271 |
+
"content": "<|EXTRA_6_TOKEN|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"255026": {
|
279 |
+
"content": "<|EXTRA_7_TOKEN|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"255027": {
|
287 |
+
"content": "<|EXTRA_8_TOKEN|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"255028": {
|
295 |
+
"content": "<|EXTRA_9_TOKEN|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": false
|
301 |
+
}
|
302 |
+
},
|
303 |
+
"auto_map": {
|
304 |
+
"AutoTokenizer": [
|
305 |
+
null,
|
306 |
+
"CohereForAI/c4ai-command-r-v01-4bit--tokenization_cohere_fast.CohereTokenizerFast"
|
307 |
+
]
|
308 |
+
},
|
309 |
+
"bos_token": "<BOS_TOKEN>",
|
310 |
+
"clean_up_tokenization_spaces": false,
|
311 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
312 |
+
"legacy": true,
|
313 |
+
"merges_file": null,
|
314 |
+
"model_max_length": 1000000000000000019884624838656,
|
315 |
+
"pad_token": "<|END_OF_TURN_TOKEN|>",
|
316 |
+
"sp_model_kwargs": {},
|
317 |
+
"spaces_between_special_tokens": false,
|
318 |
+
"tokenizer_class": "CohereTokenizer",
|
319 |
+
"unk_token": null,
|
320 |
+
"use_default_system_prompt": false,
|
321 |
+
"vocab_file": null
|
322 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:181116c814268df82c64d98cc3e9b93bafd18809620f65168fe6c8ff463e406c
|
3 |
+
size 4984
|