qnguyen3 commited on
Commit
a7a270a
1 Parent(s): d825d6f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: KnutJaegersberg/Qwen-1_8B-Llamafied
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: qwen-1.8b-vi
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
15
+ # qwen-1.8b-vi
16
+
17
+ This model is a fine-tuned version of [KnutJaegersberg/Qwen-1_8B-Llamafied](https://huggingface.co/KnutJaegersberg/Qwen-1_8B-Llamafied) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8096
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - total_eval_batch_size: 8
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 100
50
+ - num_epochs: 4
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 0.8123 | 1.02 | 2356 | 0.8183 |
57
+ | 0.7358 | 2.02 | 4713 | 0.7790 |
58
+ | 0.6379 | 3.02 | 7071 | 0.7822 |
59
+ | 0.5762 | 3.94 | 9252 | 0.8096 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.34.1
65
+ - Pytorch 2.0.1+cu118
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "KnutJaegersberg/Qwen-1_8B-Llamafied",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5504,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 16,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.34.1",
25
+ "use_cache": false,
26
+ "vocab_size": 151936
27
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chat_format": "chatml",
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 512,
6
+ "max_window_size": 6144,
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "top_k": 0,
10
+ "top_p": 0.8,
11
+ "transformers_version": "4.34.1"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5a8887a347b9e8576dfdd648df9c6a871a50274c2d3999f4b15d25c7c7a2e2
3
+ size 3673856569
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<|im_start|>",
32
+ "<|im_end|>"
33
+ ],
34
+ "bos_token": "<|endoftext|>",
35
+ "clean_up_tokenization_spaces": true,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "<|im_end|>",
40
+ "tokenizer_class": "GPT2Tokenizer",
41
+ "unk_token": "<|endoftext|>"
42
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff