rkumar1999 commited on
Commit
8ceeef3
·
verified ·
1 Parent(s): fa87314

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-tiny-MoE-instruct
3
+ library_name: transformers
4
+ model_name: phi-tiny-moe-math-lean-sft
5
+ tags:
6
+ - generated_from_trainer
7
+ - sft
8
+ - trl
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for phi-tiny-moe-math-lean-sft
13
+
14
+ This model is a fine-tuned version of [microsoft/Phi-tiny-MoE-instruct](https://huggingface.co/microsoft/Phi-tiny-MoE-instruct).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="rkumar1999/phi-tiny-moe-math-lean-sft", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.22.2
38
+ - Transformers: 4.56.1
39
+ - Pytorch: 2.6.0+cu126
40
+ - Datasets: 4.0.0
41
+ - Tokenizers: 0.22.0
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|' + message['role'] + '|>' + '
2
+ ' + message['content'] + '<|end|>
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
4
+ ' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PhiMoEForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_slimmoe.PhiMoEConfig",
9
+ "AutoModelForCausalLM": "modeling_slimmoe.PhiMoEForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 32000,
14
+ "expert_dropout": 0.0,
15
+ "head_dim": 128,
16
+ "hidden_act": "silu",
17
+ "hidden_dropout": 0.0,
18
+ "hidden_size": 4096,
19
+ "initializer_range": 0.02,
20
+ "input_jitter_noise": 0.01,
21
+ "intermediate_size": 448,
22
+ "lm_head_bias": true,
23
+ "max_position_embeddings": 4096,
24
+ "model_type": "phimoe",
25
+ "num_attention_heads": 16,
26
+ "num_experts_per_tok": 2,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 4,
29
+ "num_local_experts": 16,
30
+ "output_router_logits": false,
31
+ "pad_token_id": 32000,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "router_aux_loss_coef": 0.0,
36
+ "router_jitter_noise": 0.01,
37
+ "sliding_window": 2047,
38
+ "tie_word_embeddings": false,
39
+ "transformers_version": "4.56.1",
40
+ "use_cache": false,
41
+ "vocab_size": 32064
42
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1e28aa3ce5cf99ef6d6f7bf5885e93231cd8ca4c2f6476b6b36a8e6221704b
3
+ size 4998945744
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60c89c78c99291cb414fc976fb0174064ff2b4ecbefea5cb2577dec4ffd25e3
3
+ size 2511742008
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Oct16_23-31-00_computeinstance-u00a7v71bkxqf92h7d/events.out.tfevents.1760657596.computeinstance-u00a7v71bkxqf92h7d.191711.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35cb0d803f985d6ad10e746168f427665d223b441a9f6268ad14dfcf3e681e32
3
+ size 6017
runs/Oct17_01-41-18_computeinstance-u00fw5dwktkm9wrzxs/events.out.tfevents.1760665286.computeinstance-u00fw5dwktkm9wrzxs.16131.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a92f588a59ad4c1b09cb586a2311f0c51d3dcf298dbaeabbec7b8f0c3cf6c4
3
+ size 6017
runs/Oct17_01-46-55_computeinstance-u00fw5dwktkm9wrzxs/events.out.tfevents.1760665623.computeinstance-u00fw5dwktkm9wrzxs.30470.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6250672ba8a4a9a74337c58daeb3beaedf947d89661f0b2375bc44b99e16a7e1
3
+ size 6016
runs/Oct17_01-47-38_computeinstance-u00fw5dwktkm9wrzxs/events.out.tfevents.1760665666.computeinstance-u00fw5dwktkm9wrzxs.33678.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0eee783dd4a6a8ad60b4a788211eb704791d5b26c8f99517362426d6a6bfe6d
3
+ size 6016
runs/Oct17_01-49-14_computeinstance-u00fw5dwktkm9wrzxs/events.out.tfevents.1760665762.computeinstance-u00fw5dwktkm9wrzxs.40115.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76696c03a13b1835e4cf1dbb00ac926b02438edf4675fdd7f937e592820a93bd
3
+ size 6015
runs/Oct17_01-53-36_computeinstance-u00fw5dwktkm9wrzxs/events.out.tfevents.1760666025.computeinstance-u00fw5dwktkm9wrzxs.52926.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2977edc43541dfddfabe5f6c70695daddff779098250c938889d0e4cca9e60
3
+ size 6015
runs/Oct17_02-13-58_computeinstance-u00jxd66grq1djq6t5/events.out.tfevents.1760667249.computeinstance-u00jxd66grq1djq6t5.15737.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4ca00fff34d78a6b88fb74319f79c770cbb90d02b1ae10154652d3a2d9a712
3
+ size 8647
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizerFast",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42025881bf02af2812bcf5b03732deda48002bf3a20913f6ae43d7d8695dece
3
+ size 5880