Model save
Browse files- README.md +4 -4
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- special_tokens_map.json +11 -7
- tokenizer.json +0 -0
- tokenizer_config.json +20 -20
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
library_name: peft
|
4 |
license: apache-2.0
|
5 |
tags:
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# output
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 1.
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
3 |
library_name: peft
|
4 |
license: apache-2.0
|
5 |
tags:
|
|
|
16 |
|
17 |
# output
|
18 |
|
19 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.5166
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 1.1365 | 1.0 | 1250 | 1.5166 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -21,9 +21,9 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"q_proj",
|
|
|
24 |
"v_proj",
|
25 |
-
"o_proj"
|
26 |
-
"k_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"q_proj",
|
24 |
+
"k_proj",
|
25 |
"v_proj",
|
26 |
+
"o_proj"
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1a128da6201da83f49042b448529bebabe4d2608c5d9243eb0da3fb3cd6cf34
|
3 |
+
size 72113224
|
special_tokens_map.json
CHANGED
@@ -1,17 +1,21 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
|
|
|
|
|
|
|
6 |
"eos_token": {
|
7 |
-
"content": "
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
11 |
"single_word": false
|
12 |
},
|
13 |
-
"pad_token":
|
14 |
-
|
|
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
"normalized": false,
|
21 |
"rstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,24 +1,26 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
-
"content": "
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
-
"content": "
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
@@ -26,18 +28,16 @@
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"
|
30 |
-
|
31 |
-
"<|im_end|>"
|
32 |
-
],
|
33 |
-
"bos_token": null,
|
34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "
|
37 |
-
"
|
38 |
-
"model_max_length":
|
39 |
-
"pad_token": "
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
11 |
"single_word": false,
|
12 |
"special": true
|
13 |
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
"special": true
|
21 |
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
"lstrip": false,
|
25 |
"normalized": false,
|
26 |
"rstrip": false,
|
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
|
|
|
|
|
|
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": false,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ed5a64c1454bf7d23ba756512181bb9d775e6fa004b2c80280404c2f8fe0e92
|
3 |
size 5368
|