Hugging Face's logo

SeanLee97
/
bellm-llama-7b-nli

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
SeanLee97 commited on
Commit
40fcc87
•
1 Parent(s): d057037

Training in progress, step 100

Browse files
Files changed (11) hide show
  1. adapter_config.json +32 -0
  2. adapter_model.safetensors +3 -0
  3. angle.config +23 -0
  4. runs/Mar19_14-17-45_instance-20240226-074643/events.out.tfevents.1710857869.instance-20240226-074643.1285845.0 +3 -0
  5. runs/Mar19_14-27-04_instance-20240226-074643/events.out.tfevents.1710858427.instance-20240226-074643.1298096.0 +3 -0
  6. runs/Mar19_14-28-10_instance-20240226-074643/events.out.tfevents.1710858494.instance-20240226-074643.1298492.0 +3 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +40 -0
  11. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
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
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "up_proj",
23
+ "q_proj",
24
+ "gate_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "k_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b83708c1af2da52bd6e13d3d0b1e415ea5691f6cbe4f1525a57b49fb6fe94dc
3
+ size 319876032
angle.config ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name_or_path": "NousResearch/Llama-2-7b-hf",
3
+ "max_length": 64,
4
+ "model_kwargs": {},
5
+ "pooling_strategy": "cls",
6
+ "lora_config_kwargs": {
7
+ "task_type": "CAUSAL_LM",
8
+ "r": 32,
9
+ "lora_alpha": 32,
10
+ "lora_dropout": 0.1,
11
+ "bias": "none",
12
+ "target_modules": [
13
+ "v_proj",
14
+ "q_proj",
15
+ "o_proj",
16
+ "gate_proj",
17
+ "up_proj",
18
+ "down_proj",
19
+ "k_proj"
20
+ ]
21
+ },
22
+ "apply_lora": 1
23
+ }
runs/Mar19_14-17-45_instance-20240226-074643/events.out.tfevents.1710857869.instance-20240226-074643.1285845.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409391610d5b717dad7176fa438ec463b316b8fd98b1616a50017f5c6db134f7
3
+ size 5200
runs/Mar19_14-27-04_instance-20240226-074643/events.out.tfevents.1710858427.instance-20240226-074643.1298096.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2cb2097c596271ec8532e1efd4fbaf5860634575ae179196c7ac1d577e7527d
3
+ size 5200
runs/Mar19_14-28-10_instance-20240226-074643/events.out.tfevents.1710858494.instance-20240226-074643.1298492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:227240e2e2c09f713c60b1ab066c7fb8332d6e6773319b8991dd6035fe5c970e
3
+ size 5407
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<unk>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3d8ea6c18bd35637bb2d4ce07766eba6b096ba3d6991f5da597891b23d4f8c
3
+ size 5048