nihalnayak commited on
Commit
61c4561
1 Parent(s): 8b5fc97

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.5.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "up_proj",
19
+ "v_proj",
20
+ "o_proj",
21
+ "down_proj",
22
+ "gate_proj",
23
+ "k_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b86144bc6d5fdd90816ca78d655650ff76bf03952a6fa04c65eefeda94228c1
3
+ size 671250189
adapter_model/README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Training procedure
2
+
3
+
4
+ The following `bitsandbytes` quantization config was used during training:
5
+ - quant_method: bitsandbytes
6
+ - load_in_8bit: False
7
+ - load_in_4bit: True
8
+ - llm_int8_threshold: 6.0
9
+ - llm_int8_skip_modules: None
10
+ - llm_int8_enable_fp32_cpu_offload: False
11
+ - llm_int8_has_fp16_weight: False
12
+ - bnb_4bit_quant_type: nf4
13
+ - bnb_4bit_use_double_quant: True
14
+ - bnb_4bit_compute_dtype: float32
15
+ ### Framework versions
16
+
17
+
18
+ - PEFT 0.5.0
19
+ - PEFT 0.5.0
20
+ ing `bitsandbytes` quantization config was used during training:
21
+ - quant_method: bitsandbytes
22
+ - load_in_8bit: False
23
+ - load_in_4bit: True
24
+ - llm_int8_threshold: 6.0
25
+ - llm_int8_skip_modules: None
26
+ - llm_int8_enable_fp32_cpu_offload: False
27
+ - llm_int8_has_fp16_weight: False
28
+ - bnb_4bit_quant_type: nf4
29
+ - bnb_4bit_use_double_quant: True
30
+ - bnb_4bit_compute_dtype: float32
31
+ ### Framework versions
32
+
33
+ - PEFT 0.5.0
34
+
35
+ - PEFT 0.5.0
36
+ ## Training procedure
37
+
38
+
39
+ The following `bitsandbytes` quantization config was used during training:
40
+ - quant_method: bitsandbytes
41
+ - load_in_8bit: False
42
+ - load_in_4bit: True
43
+ - llm_int8_threshold: 6.0
44
+ - llm_int8_skip_modules: None
45
+ - llm_int8_enable_fp32_cpu_offload: False
46
+ - llm_int8_has_fp16_weight: False
47
+ - bnb_4bit_quant_type: nf4
48
+ - bnb_4bit_use_double_quant: True
49
+ - bnb_4bit_compute_dtype: float32
adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "o_proj",
18
+ "up_proj",
19
+ "k_proj",
20
+ "v_proj",
21
+ "down_proj",
22
+ "gate_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b86144bc6d5fdd90816ca78d655650ff76bf03952a6fa04c65eefeda94228c1
3
+ size 671250189
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "[PAD]": 32000
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4aa56d9063b368f1758c7ca65cc18cf5540d247787e1ed61757f9b2fb34ad7f
3
+ size 1342452997
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eafe3d5e0585dde8c5033613de99a5d4f23df4284a488f4007b3944580c0b97
3
+ size 17655
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e34eb456d2d003a2839f2daa9425e99bdd79ed7e24a1de9fc7d5738476bfb4b
3
+ size 17655
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b374af4a2765d8771cee7a72921d3c2e438b9bee34f0b2d098ce6071afeb65e4
3
+ size 17655
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df75d8477fcc69c7abb03025313915ebfe3ac18c54a7c57aaa455c0099e13e5
3
+ size 17655
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5e24b8bf255cbefe9d307944a9741807d095b40cc5429a7befe9515b366b0f
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "[PAD]",
10
+ "unk_token": "<unk>"
11
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [
37
+ "<unk>",
38
+ "<s>",
39
+ "</s>"
40
+ ],
41
+ "bos_token": "<s>",
42
+ "clean_up_tokenization_spaces": false,
43
+ "eos_token": "</s>",
44
+ "legacy": true,
45
+ "model_max_length": 1000000000000000019884624838656,
46
+ "pad_token": "[PAD]",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "tokenizer_class": "LlamaTokenizer",
50
+ "unk_token": "<unk>",
51
+ "use_default_system_prompt": false
52
+ }
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:f082ba1ffbf9fe8ba0cd957dd4bd4509b7ea8f8e0a056cb5c68ea279e6089229
3
+ size 4731