Hugging Face's logo

medmekk
/
qat_smollm3

Text Generation
Transformers
PyTorch
TensorBoard
smollm3
Generated from Trainer
sft
trl
Model card Files
xet
 Metrics Community
medmekk commited on
Commit
d70df87
·
verified ·
1 Parent(s): 1fe76be

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. README.md +58 -0
  2. config.json +115 -0
  3. generation_config.json +9 -0
  4. pytorch_model-00001-of-00002.bin +3 -0
  5. pytorch_model-00002-of-00002.bin +3 -0
  6. pytorch_model.bin.index.json +335 -0
  7. runs/Aug27_10-51-54_ip-26-0-166-214/events.out.tfevents.1756291925.ip-26-0-166-214.1639603.0 +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM3-3B-Base
3
+ library_name: transformers
4
+ model_name: qat_finetuned_model_checkpoint
5
+ tags:
6
+ - generated_from_trainer
7
+ - sft
8
+ - trl
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for qat_finetuned_model_checkpoint
13
+
14
+ This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base).
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="None", 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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mekk/huggingface/runs/r1ds8s0w)
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.22.0.dev0
38
+ - Transformers: 4.56.0.dev0
39
+ - Pytorch: 2.8.0+cu129
40
+ - Datasets: 3.6.0
41
+ - Tokenizers: 0.21.4
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
+ ```
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SmolLM3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128012,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 65536,
53
+ "mlp_bias": false,
54
+ "model_type": "smollm3",
55
+ "no_rope_layer_interval": 4,
56
+ "no_rope_layers": [
57
+ 1,
58
+ 1,
59
+ 1,
60
+ 0,
61
+ 1,
62
+ 1,
63
+ 1,
64
+ 0,
65
+ 1,
66
+ 1,
67
+ 1,
68
+ 0,
69
+ 1,
70
+ 1,
71
+ 1,
72
+ 0,
73
+ 1,
74
+ 1,
75
+ 1,
76
+ 0,
77
+ 1,
78
+ 1,
79
+ 1,
80
+ 0,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 0,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 0,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 0
93
+ ],
94
+ "num_attention_heads": 16,
95
+ "num_hidden_layers": 36,
96
+ "num_key_value_heads": 4,
97
+ "pad_token_id": 128012,
98
+ "pretraining_tp": 2,
99
+ "rms_norm_eps": 1e-06,
100
+ "rope_scaling": null,
101
+ "rope_theta": 5000000.0,
102
+ "sliding_window": null,
103
+ "transformers.js_config": {
104
+ "dtype": "q4",
105
+ "kv_cache_dtype": {
106
+ "fp16": "float16",
107
+ "q4f16": "float16"
108
+ },
109
+ "use_external_data_format": true
110
+ },
111
+ "transformers_version": "4.56.0.dev0",
112
+ "use_cache": true,
113
+ "use_sliding_window": false,
114
+ "vocab_size": 128256
115
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 128012,
5
+ 128001
6
+ ],
7
+ "pad_token_id": 128012,
8
+ "transformers_version": "4.56.0.dev0"
9
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b563fbd266b59a2ed3f26ed11f9e29e9a4cf04eac89f2344e25206424dd0202
3
+ size 6150208368
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617bed3d0dc200009032600dd994e047175d5c8edc72ff36dbaa23ff0133b470
3
+ size 87748
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 149504,
4
+ "total_size": 6150197248
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "model.embed_tokens.weight": "pytorch_model-00002-of-00002.bin",
9
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
13
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
16
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
26
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
27
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
29
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
30
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
31
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
33
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
34
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
35
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
36
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
38
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
39
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
40
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
42
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
43
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
44
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
45
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
47
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
48
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
49
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
51
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
52
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
53
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
54
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
56
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
57
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
58
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
60
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
61
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
62
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
63
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
65
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
66
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
67
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
69
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
70
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
71
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
72
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
74
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
75
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
76
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
78
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
79
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
80
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
81
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
83
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
84
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
85
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
87
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
88
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
92
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
94
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
96
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
97
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
98
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
99
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
150
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
152
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
190
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
230
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
235
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
243
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
245
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
246
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
247
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
269
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
270
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
272
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
273
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
274
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
276
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
277
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
278
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
279
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
281
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
282
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
283
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
285
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
286
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
287
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
288
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
290
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
291
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
292
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
294
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
295
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
296
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
297
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
299
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
300
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
301
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
303
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
304
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
305
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
306
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
308
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
309
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
310
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
312
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
313
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
314
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
315
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
317
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
318
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
319
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
321
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
322
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
323
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
324
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
326
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
327
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
328
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
329
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
330
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
331
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
332
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
333
+ "model.norm.weight": "pytorch_model-00001-of-00002.bin"
334
+ }
335
+ }
runs/Aug27_10-51-54_ip-26-0-166-214/events.out.tfevents.1756291925.ip-26-0-166-214.1639603.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bb837a348089862c544b5f4b50a7c57f8022387c5e0bd865b07e412f9dc8ef
3
+ size 7367