LeroyDyer commited on
Commit
f063d32
1 Parent(s): 90eef9a

(Trained with Unsloth)

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LeroyDyer/Mixtral_AI_MiniTron_II",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 16,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.38.2",
25
+ "unsloth_version": "2024.4",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a344d3d5b6f66a741fe87610d4b13b73d3007b4a5bcc98c5b82812f55bebb2
3
+ size 4943162240
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eba5b41a90193917542b1f33adc6ade41cb9100733c8621177e6b65a96f1fc6
3
+ size 2560734832
model.safetensors.index.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7503880192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.norm.weight": "model-00002-of-00002.safetensors"
153
+ }
154
+ }
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc460a0129515b7579ec9f63218012601729de4fbd1b5de8d56dc47e8a204a29
3
+ size 493449
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
+ "model_max_length": 32768,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "left",
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }