3v324v23 commited on
Commit
f15fa81
1 Parent(s): 9ed2166

llama-v12a-6500-7500-merge

Browse files
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: gptq
9
+ - bits: 4
10
+ - tokenizer: None
11
+ - dataset: None
12
+ - group_size: 512
13
+ - damp_percent: 0.01
14
+ - desc_act: True
15
+ - sym: True
16
+ - true_sequential: True
17
+ - use_cuda_fp16: False
18
+ - model_seqlen: None
19
+ - block_name_to_quantize: None
20
+ - module_name_preceding_first_block: None
21
+ - batch_size: 1
22
+ - pad_token_id: None
23
+ - disable_exllama: True
24
+ - max_input_length: None
25
+
26
+ The following `bitsandbytes` quantization config was used during training:
27
+ - quant_method: gptq
28
+ - bits: 4
29
+ - tokenizer: None
30
+ - dataset: None
31
+ - group_size: 512
32
+ - damp_percent: 0.01
33
+ - desc_act: True
34
+ - sym: True
35
+ - true_sequential: True
36
+ - use_cuda_fp16: False
37
+ - model_seqlen: None
38
+ - block_name_to_quantize: None
39
+ - module_name_preceding_first_block: None
40
+ - batch_size: 1
41
+ - pad_token_id: None
42
+ - disable_exllama: True
43
+ - max_input_length: None
44
+ ### Framework versions
45
+
46
+ - PEFT 0.6.0.dev0
47
+
48
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "llama2-70B-gptq-4bit",
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": 64,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 2,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "gate_proj",
20
+ "down_proj",
21
+ "up_proj"
22
+ ],
23
+ "task_type": "CAUSAL_LM"
24
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eda6f4478eb3424dcd92ba631ae9e16e286d2695009ecc73bafa5cbc746b858
3
+ size 70950538
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884141cd1f6fc01a636ee3463eaa5917933d1695d79bb97f213966e3f0a1c7d7
3
+ size 141841722
rng_state.pth ADDED
Binary file (14.2 kB). View file
 
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3273a85744b3d22d441cfbbaa704a772e911973d90ac6677a606a46685646da0
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
tokenizer.model ADDED
Binary file (500 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "left",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfe22c2c8a8726ca20a59a57de3e68487c1eb15122d170b99005fc1b55ea7b8
3
+ size 4536