nihalnayak
commited on
Commit
•
61c4561
1
Parent(s):
8b5fc97
Upload folder using huggingface_hub
Browse files- README.md +21 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- adapter_model/README.md +49 -0
- adapter_model/adapter_config.json +26 -0
- adapter_model/adapter_model.bin +3 -0
- added_tokens.json +6 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +52 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
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
|