Hugging Face's logo

jashing
/
TinyLlama_FT_NW02

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
jashing commited on
Commit
fdf5967
•
1 Parent(s): 4bb593f

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. README.md +9 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +8 -0
  5. checkpoint-14769/README.md +86 -0
  6. checkpoint-14769/adapter_config.json +23 -0
  7. checkpoint-14769/adapter_model.bin +3 -0
  8. checkpoint-14769/added_tokens.json +8 -0
  9. checkpoint-14769/optimizer.pt +3 -0
  10. checkpoint-14769/rng_state.pth +3 -0
  11. checkpoint-14769/scheduler.pt +3 -0
  12. checkpoint-14769/special_tokens_map.json +6 -0
  13. checkpoint-14769/tokenizer.json +0 -0
  14. checkpoint-14769/tokenizer.model +3 -0
  15. checkpoint-14769/tokenizer_config.json +64 -0
  16. checkpoint-14769/trainer_state.json +109 -0
  17. checkpoint-14769/training_args.bin +3 -0
  18. runs/Oct04_09-38-07_AN780100064/events.out.tfevents.1696383489.AN780100064.21700.0 +3 -0
  19. runs/Oct04_09-56-50_AN780100064/events.out.tfevents.1696384611.AN780100064.22620.0 +3 -0
  20. runs/Oct04_11-59-14_AN780100064/events.out.tfevents.1696391955.AN780100064.25112.0 +3 -0
  21. runs/Oct05_14-29-12_AN780100064/events.out.tfevents.1696487353.AN780100064.3248.0 +3 -0
  22. runs/Oct06_08-18-58_AN780100064/events.out.tfevents.1696551539.AN780100064.21268.0 +3 -0
  23. special_tokens_map.json +6 -0
  24. tokenizer.json +0 -0
  25. tokenizer.model +3 -0
  26. tokenizer_config.json +64 -0
  27. training_args.bin +3 -0
  28. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "PY007/TinyLlama-1.1B-Chat-v0.2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950e2df641fd479e0f8592cee05a4d7c18548c1d9cfbe62461d1010f49188a7d
3
+ size 9042553
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32002,
6
+ "<|im_start|>": 32001,
7
+ "[PAD]": 32000
8
+ }
checkpoint-14769/README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: False
34
+ - load_in_4bit: True
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: nf4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float16
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: False
46
+ - load_in_4bit: True
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: nf4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float16
54
+
55
+ The following `bitsandbytes` quantization config was used during training:
56
+ - quant_method: bitsandbytes
57
+ - load_in_8bit: False
58
+ - load_in_4bit: True
59
+ - llm_int8_threshold: 6.0
60
+ - llm_int8_skip_modules: None
61
+ - llm_int8_enable_fp32_cpu_offload: False
62
+ - llm_int8_has_fp16_weight: False
63
+ - bnb_4bit_quant_type: nf4
64
+ - bnb_4bit_use_double_quant: False
65
+ - bnb_4bit_compute_dtype: float16
66
+
67
+ The following `bitsandbytes` quantization config was used during training:
68
+ - quant_method: bitsandbytes
69
+ - load_in_8bit: False
70
+ - load_in_4bit: True
71
+ - llm_int8_threshold: 6.0
72
+ - llm_int8_skip_modules: None
73
+ - llm_int8_enable_fp32_cpu_offload: False
74
+ - llm_int8_has_fp16_weight: False
75
+ - bnb_4bit_quant_type: nf4
76
+ - bnb_4bit_use_double_quant: False
77
+ - bnb_4bit_compute_dtype: float16
78
+ ### Framework versions
79
+
80
+ - PEFT 0.6.0.dev0
81
+ - PEFT 0.6.0.dev0
82
+ - PEFT 0.6.0.dev0
83
+ - PEFT 0.6.0.dev0
84
+ - PEFT 0.6.0.dev0
85
+
86
+ - PEFT 0.6.0.dev0
checkpoint-14769/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "PY007/TinyLlama-1.1B-Chat-v0.2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-14769/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950e2df641fd479e0f8592cee05a4d7c18548c1d9cfbe62461d1010f49188a7d
3
+ size 9042553
checkpoint-14769/added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32002,
6
+ "<|im_start|>": 32001,
7
+ "[PAD]": 32000
8
+ }
checkpoint-14769/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a11914766aa45cb8fc17b4bbbcbb44cff2d2888fc80f4ee13e03992446fcbc3
3
+ size 18096133
checkpoint-14769/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8f2499e2f5f34d865a466b9f16ddd9475170f5c7fc41fa0ea1a7de37dd3074
3
+ size 14575
checkpoint-14769/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5aaec06007d7bb3acbc51689f883d34ac3eb54f4542f5ab86eeabd5807222b
3
+ size 627
checkpoint-14769/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-14769/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14769/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-14769/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|im_start|>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "32002": {
44
+ "content": "<|im_end|>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "additional_special_tokens": [],
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": false,
55
+ "eos_token": "</s>",
56
+ "legacy": false,
57
+ "model_max_length": 64,
58
+ "pad_token": "[PAD]",
59
+ "padding_side": "right",
60
+ "sp_model_kwargs": {},
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": true
64
+ }
checkpoint-14769/trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14769,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 0.00013324306025727826,
14
+ "loss": 2.3278,
15
+ "step": 984
16
+ },
17
+ {
18
+ "epoch": 0.4,
19
+ "learning_rate": 0.00019261209750225702,
20
+ "loss": 2.1512,
21
+ "step": 1968
22
+ },
23
+ {
24
+ "epoch": 0.6,
25
+ "learning_rate": 0.00017780619921757448,
26
+ "loss": 2.0221,
27
+ "step": 2952
28
+ },
29
+ {
30
+ "epoch": 0.8,
31
+ "learning_rate": 0.00016300030093289197,
32
+ "loss": 1.979,
33
+ "step": 3936
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "learning_rate": 0.00014819440264820946,
38
+ "loss": 2.0714,
39
+ "step": 4920
40
+ },
41
+ {
42
+ "epoch": 1.2,
43
+ "learning_rate": 0.00013338850436352695,
44
+ "loss": 2.0495,
45
+ "step": 5904
46
+ },
47
+ {
48
+ "epoch": 1.4,
49
+ "learning_rate": 0.00011858260607884442,
50
+ "loss": 2.0241,
51
+ "step": 6888
52
+ },
53
+ {
54
+ "epoch": 1.6,
55
+ "learning_rate": 0.00010377670779416191,
56
+ "loss": 2.0703,
57
+ "step": 7872
58
+ },
59
+ {
60
+ "epoch": 1.8,
61
+ "learning_rate": 8.89708095094794e-05,
62
+ "loss": 2.0445,
63
+ "step": 8856
64
+ },
65
+ {
66
+ "epoch": 2.0,
67
+ "learning_rate": 7.416491122479687e-05,
68
+ "loss": 1.995,
69
+ "step": 9840
70
+ },
71
+ {
72
+ "epoch": 2.2,
73
+ "learning_rate": 5.935901294011436e-05,
74
+ "loss": 2.0327,
75
+ "step": 10824
76
+ },
77
+ {
78
+ "epoch": 2.4,
79
+ "learning_rate": 4.455311465543184e-05,
80
+ "loss": 2.1159,
81
+ "step": 11808
82
+ },
83
+ {
84
+ "epoch": 2.6,
85
+ "learning_rate": 2.9747216370749325e-05,
86
+ "loss": 2.1016,
87
+ "step": 12792
88
+ },
89
+ {
90
+ "epoch": 2.8,
91
+ "learning_rate": 1.4941318086066807e-05,
92
+ "loss": 2.0736,
93
+ "step": 13776
94
+ },
95
+ {
96
+ "epoch": 3.0,
97
+ "learning_rate": 1.354198013842913e-07,
98
+ "loss": 2.0239,
99
+ "step": 14760
100
+ }
101
+ ],
102
+ "logging_steps": 984,
103
+ "max_steps": 14769,
104
+ "num_train_epochs": 3,
105
+ "save_steps": 500,
106
+ "total_flos": 1.1759674170802176e+16,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
checkpoint-14769/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b9bdfbccda5b0a242ea2efd21457b4df35eb5a8f16d65ae853ae832f79af48
3
+ size 4091
runs/Oct04_09-38-07_AN780100064/events.out.tfevents.1696383489.AN780100064.21700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a45b66b4bc95b95fffbf1f4417c8ae97c70c024e4380cef1d305505f6c5f9eb
3
+ size 4529
runs/Oct04_09-56-50_AN780100064/events.out.tfevents.1696384611.AN780100064.22620.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815f6e3e2d7cbbfe0db66f0f13081ad9ad1283725c1f76e7f51f4af0fb4e1bf9
3
+ size 4686
runs/Oct04_11-59-14_AN780100064/events.out.tfevents.1696391955.AN780100064.25112.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f9de2ce753b112694cc55ba2f45d6d6e8a8e77bf9ee1d252131ff88e7f2835
3
+ size 7238
runs/Oct05_14-29-12_AN780100064/events.out.tfevents.1696487353.AN780100064.3248.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42632ce0021e98b248afeab53ce3f71f172f953931bdf43d682664cc5abd92e9
3
+ size 7238
runs/Oct06_08-18-58_AN780100064/events.out.tfevents.1696551539.AN780100064.21268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea6beb19285c6e1663782b161b55a97fcd9ad67d2322d0a2b133b7aac0c7ab9
3
+ size 7238
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|im_start|>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "32002": {
44
+ "content": "<|im_end|>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "additional_special_tokens": [],
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": false,
55
+ "eos_token": "</s>",
56
+ "legacy": false,
57
+ "model_max_length": 64,
58
+ "pad_token": "[PAD]",
59
+ "padding_side": "right",
60
+ "sp_model_kwargs": {},
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": true
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b9bdfbccda5b0a242ea2efd21457b4df35eb5a8f16d65ae853ae832f79af48
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "PY007/TinyLlama-1.1B-Chat-v0.2", "data_path": "timdettmers/openassistant-guanaco", "project_name": "'FT-TinyLlama'", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 64, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 64, "repo_id": "jashing/TinyLlama_FT_NW02", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false}