StaAhmed commited on
Commit
8afd888
·
verified ·
1 Parent(s): 342cb2e

Delete model_llama

Browse files
model_llama/README.md DELETED
@@ -1,32 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - load_in_8bit: False
9
- - load_in_4bit: True
10
- - llm_int8_threshold: 6.0
11
- - llm_int8_skip_modules: None
12
- - llm_int8_enable_fp32_cpu_offload: False
13
- - llm_int8_has_fp16_weight: False
14
- - bnb_4bit_quant_type: nf4
15
- - bnb_4bit_use_double_quant: False
16
- - bnb_4bit_compute_dtype: float16
17
-
18
- The following `bitsandbytes` quantization config was used during training:
19
- - load_in_8bit: False
20
- - load_in_4bit: True
21
- - llm_int8_threshold: 6.0
22
- - llm_int8_skip_modules: None
23
- - llm_int8_enable_fp32_cpu_offload: False
24
- - llm_int8_has_fp16_weight: False
25
- - bnb_4bit_quant_type: nf4
26
- - bnb_4bit_use_double_quant: False
27
- - bnb_4bit_compute_dtype: float16
28
- ### Framework versions
29
-
30
- - PEFT 0.4.0
31
-
32
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_llama/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
4
- "bias": "none",
5
- "fan_in_fan_out": false,
6
- "inference_mode": true,
7
- "init_lora_weights": true,
8
- "layers_pattern": null,
9
- "layers_to_transform": null,
10
- "lora_alpha": 16,
11
- "lora_dropout": 0.1,
12
- "modules_to_save": null,
13
- "peft_type": "LORA",
14
- "r": 8,
15
- "revision": null,
16
- "target_modules": [
17
- "q_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_llama/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "<pad>": 32000
3
- }
 
 
 
 
model_llama/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab56012ddf69ad9a2fe04e8742ff505350d8d5b01be6619adf6ca5886add5a2
3
- size 33630138
 
 
 
 
model_llama/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:103859d7f26805fabdde7f1e59616999e10fd5a8851054ec55d46f9e14483626
3
- size 14244
 
 
 
 
model_llama/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
3
- size 1064
 
 
 
 
model_llama/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_llama/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
model_llama/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
model_llama/tokenizer_config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "legacy": false,
20
- "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
- "sp_model_kwargs": {},
23
- "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- }
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_llama/trainer_state.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.9259259259259259,
5
- "global_step": 200,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.12,
12
- "learning_rate": 0.0002,
13
- "loss": 1.9564,
14
- "step": 25
15
- },
16
- {
17
- "epoch": 0.23,
18
- "learning_rate": 0.0002,
19
- "loss": 0.4866,
20
- "step": 50
21
- },
22
- {
23
- "epoch": 0.35,
24
- "learning_rate": 0.0002,
25
- "loss": 0.4995,
26
- "step": 75
27
- },
28
- {
29
- "epoch": 0.46,
30
- "learning_rate": 0.0002,
31
- "loss": 0.3118,
32
- "step": 100
33
- },
34
- {
35
- "epoch": 0.58,
36
- "learning_rate": 0.0002,
37
- "loss": 0.4503,
38
- "step": 125
39
- },
40
- {
41
- "epoch": 0.69,
42
- "learning_rate": 0.0002,
43
- "loss": 0.2724,
44
- "step": 150
45
- },
46
- {
47
- "epoch": 0.81,
48
- "learning_rate": 0.0002,
49
- "loss": 0.4099,
50
- "step": 175
51
- },
52
- {
53
- "epoch": 0.93,
54
- "learning_rate": 0.0002,
55
- "loss": 0.2531,
56
- "step": 200
57
- }
58
- ],
59
- "max_steps": 216,
60
- "num_train_epochs": 1,
61
- "total_flos": 7233885092118528.0,
62
- "trial_name": null,
63
- "trial_params": null
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_llama/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:73a5da6b2de1b71ea130c7b10e4ae4a030f7560e22d8dc0a6f54eb10d102bde0
3
- size 4408