Hugging Face's logo

mlx-community
/
SciPhi-Triplex-4bit

Text Generation
MLX
Safetensors
phi3
conversational
custom_code
4-bit precision
Model card Files
xet
 Community
Shahriar Arefin commited on
Commit
f25bd18
·
verified ·
1 Parent(s): 80f892c

Add files using upload-large-folder tool

Browse files
Files changed (11) hide show
  1. README.md +36 -0
  2. added_tokens.json +13 -0
  3. chat_template.jinja +7 -0
  4. config.json +148 -0
  5. generation_config.json +11 -0
  6. model.safetensors +3 -0
  7. model.safetensors.index.json +463 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +132 -0
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ pipeline_tag: text-generation
4
+ base_model: SciPhi/Triplex
5
+ tags:
6
+ - mlx
7
+ library_name: mlx
8
+ ---
9
+
10
+ # mlx-community/SciPhi-Triplex-4bit
11
+
12
+ This model [mlx-community/SciPhi-Triplex-4bit](https://huggingface.co/mlx-community/SciPhi-Triplex-4bit) was
13
+ converted to MLX format from [SciPhi/Triplex](https://huggingface.co/SciPhi/Triplex)
14
+ using mlx-lm version **0.29.1**.
15
+
16
+ ## Use with mlx
17
+
18
+ ```bash
19
+ pip install mlx-lm
20
+ ```
21
+
22
+ ```python
23
+ from mlx_lm import load, generate
24
+
25
+ model, tokenizer = load("mlx-community/SciPhi-Triplex-4bit")
26
+
27
+ prompt = "hello"
28
+
29
+ if tokenizer.chat_template is not None:
30
+ messages = [{"role": "user", "content": prompt}]
31
+ prompt = tokenizer.apply_chat_template(
32
+ messages, add_generation_prompt=True
33
+ )
34
+
35
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
36
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>
2
+ ' + system_message + '<|end|>
3
+ ' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>
4
+ ' + content + '<|end|>
5
+ <|assistant|>
6
+ ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '
7
+ ' }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModel": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "quantization": {
27
+ "group_size": 64,
28
+ "bits": 4,
29
+ "mode": "affine"
30
+ },
31
+ "quantization_config": {
32
+ "group_size": 64,
33
+ "bits": 4,
34
+ "mode": "affine"
35
+ },
36
+ "resid_pdrop": 0.0,
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_scaling": {
39
+ "long_factor": [
40
+ 1.0700000524520874,
41
+ 1.1200000047683716,
42
+ 1.149999976158142,
43
+ 1.4199999570846558,
44
+ 1.5699999332427979,
45
+ 1.7999999523162842,
46
+ 2.129999876022339,
47
+ 2.129999876022339,
48
+ 3.009999990463257,
49
+ 5.910000324249268,
50
+ 6.950000286102295,
51
+ 9.070000648498535,
52
+ 9.930000305175781,
53
+ 10.710000038146973,
54
+ 11.130000114440918,
55
+ 14.609999656677246,
56
+ 15.409998893737793,
57
+ 19.809999465942383,
58
+ 37.279998779296875,
59
+ 38.279998779296875,
60
+ 38.599998474121094,
61
+ 40.12000274658203,
62
+ 46.20000457763672,
63
+ 50.940006256103516,
64
+ 53.66000747680664,
65
+ 54.9373893737793,
66
+ 56.89738845825195,
67
+ 57.28738784790039,
68
+ 59.98738479614258,
69
+ 60.86738586425781,
70
+ 60.887386322021484,
71
+ 61.71739196777344,
72
+ 62.91739273071289,
73
+ 62.957393646240234,
74
+ 63.41739273071289,
75
+ 63.8173942565918,
76
+ 63.83739471435547,
77
+ 63.897396087646484,
78
+ 63.93739700317383,
79
+ 64.06739807128906,
80
+ 64.11434936523438,
81
+ 64.12435150146484,
82
+ 64.15435028076172,
83
+ 64.19435119628906,
84
+ 64.24435424804688,
85
+ 64.57435607910156,
86
+ 64.69000244140625,
87
+ 64.76000213623047
88
+ ],
89
+ "short_factor": [
90
+ 1.1,
91
+ 1.1,
92
+ 1.1,
93
+ 1.3000000000000003,
94
+ 1.3500000000000003,
95
+ 1.3500000000000003,
96
+ 1.4000000000000004,
97
+ 1.5500000000000005,
98
+ 2.000000000000001,
99
+ 2.000000000000001,
100
+ 2.000000000000001,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.0500000000000007,
116
+ 2.0500000000000007,
117
+ 2.0500000000000007,
118
+ 2.0500000000000007,
119
+ 2.0500000000000007,
120
+ 2.0500000000000007,
121
+ 2.1000000000000005,
122
+ 2.1000000000000005,
123
+ 2.1500000000000004,
124
+ 2.25,
125
+ 2.25,
126
+ 2.25,
127
+ 2.25,
128
+ 2.25,
129
+ 2.3999999999999995,
130
+ 2.4499999999999993,
131
+ 2.499999999999999,
132
+ 2.6999999999999984,
133
+ 2.6999999999999984,
134
+ 2.7499999999999982,
135
+ 2.799999999999998,
136
+ 2.8999999999999977,
137
+ 3.049999999999997
138
+ ],
139
+ "type": "longrope"
140
+ },
141
+ "rope_theta": 10000.0,
142
+ "sliding_window": 262144,
143
+ "tie_word_embeddings": false,
144
+ "torch_dtype": "bfloat16",
145
+ "transformers_version": "4.43.0.dev0",
146
+ "use_cache": false,
147
+ "vocab_size": 32064
148
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.43.0.dev0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d58f13107d79edba062f839bd7d79da0f887e886e0e6721f0483c60c4982de6
3
+ size 2149696492
model.safetensors.index.json ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2149644288,
4
+ "total_parameters": 3821079552
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model.safetensors",
8
+ "lm_head.scales": "model.safetensors",
9
+ "lm_head.weight": "model.safetensors",
10
+ "model.embed_tokens.biases": "model.safetensors",
11
+ "model.embed_tokens.scales": "model.safetensors",
12
+ "model.embed_tokens.weight": "model.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.gate_up_proj.biases": "model.safetensors",
18
+ "model.layers.0.mlp.gate_up_proj.scales": "model.safetensors",
19
+ "model.layers.0.mlp.gate_up_proj.weight": "model.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
21
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
22
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
23
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
24
+ "model.layers.0.self_attn.qkv_proj.biases": "model.safetensors",
25
+ "model.layers.0.self_attn.qkv_proj.scales": "model.safetensors",
26
+ "model.layers.0.self_attn.qkv_proj.weight": "model.safetensors",
27
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
28
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
29
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
30
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
31
+ "model.layers.1.mlp.gate_up_proj.biases": "model.safetensors",
32
+ "model.layers.1.mlp.gate_up_proj.scales": "model.safetensors",
33
+ "model.layers.1.mlp.gate_up_proj.weight": "model.safetensors",
34
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
35
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
36
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
37
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
38
+ "model.layers.1.self_attn.qkv_proj.biases": "model.safetensors",
39
+ "model.layers.1.self_attn.qkv_proj.scales": "model.safetensors",
40
+ "model.layers.1.self_attn.qkv_proj.weight": "model.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
42
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
43
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
44
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
45
+ "model.layers.10.mlp.gate_up_proj.biases": "model.safetensors",
46
+ "model.layers.10.mlp.gate_up_proj.scales": "model.safetensors",
47
+ "model.layers.10.mlp.gate_up_proj.weight": "model.safetensors",
48
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
49
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
50
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
52
+ "model.layers.10.self_attn.qkv_proj.biases": "model.safetensors",
53
+ "model.layers.10.self_attn.qkv_proj.scales": "model.safetensors",
54
+ "model.layers.10.self_attn.qkv_proj.weight": "model.safetensors",
55
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
56
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
57
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
58
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
59
+ "model.layers.11.mlp.gate_up_proj.biases": "model.safetensors",
60
+ "model.layers.11.mlp.gate_up_proj.scales": "model.safetensors",
61
+ "model.layers.11.mlp.gate_up_proj.weight": "model.safetensors",
62
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
63
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
64
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
65
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
66
+ "model.layers.11.self_attn.qkv_proj.biases": "model.safetensors",
67
+ "model.layers.11.self_attn.qkv_proj.scales": "model.safetensors",
68
+ "model.layers.11.self_attn.qkv_proj.weight": "model.safetensors",
69
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
70
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
71
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
72
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
73
+ "model.layers.12.mlp.gate_up_proj.biases": "model.safetensors",
74
+ "model.layers.12.mlp.gate_up_proj.scales": "model.safetensors",
75
+ "model.layers.12.mlp.gate_up_proj.weight": "model.safetensors",
76
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
77
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
78
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
79
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
80
+ "model.layers.12.self_attn.qkv_proj.biases": "model.safetensors",
81
+ "model.layers.12.self_attn.qkv_proj.scales": "model.safetensors",
82
+ "model.layers.12.self_attn.qkv_proj.weight": "model.safetensors",
83
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
84
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
85
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
86
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
87
+ "model.layers.13.mlp.gate_up_proj.biases": "model.safetensors",
88
+ "model.layers.13.mlp.gate_up_proj.scales": "model.safetensors",
89
+ "model.layers.13.mlp.gate_up_proj.weight": "model.safetensors",
90
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
91
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
92
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
93
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
94
+ "model.layers.13.self_attn.qkv_proj.biases": "model.safetensors",
95
+ "model.layers.13.self_attn.qkv_proj.scales": "model.safetensors",
96
+ "model.layers.13.self_attn.qkv_proj.weight": "model.safetensors",
97
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
98
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
99
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
100
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
101
+ "model.layers.14.mlp.gate_up_proj.biases": "model.safetensors",
102
+ "model.layers.14.mlp.gate_up_proj.scales": "model.safetensors",
103
+ "model.layers.14.mlp.gate_up_proj.weight": "model.safetensors",
104
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
105
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
106
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
107
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
108
+ "model.layers.14.self_attn.qkv_proj.biases": "model.safetensors",
109
+ "model.layers.14.self_attn.qkv_proj.scales": "model.safetensors",
110
+ "model.layers.14.self_attn.qkv_proj.weight": "model.safetensors",
111
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
112
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
113
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
114
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
115
+ "model.layers.15.mlp.gate_up_proj.biases": "model.safetensors",
116
+ "model.layers.15.mlp.gate_up_proj.scales": "model.safetensors",
117
+ "model.layers.15.mlp.gate_up_proj.weight": "model.safetensors",
118
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
119
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
120
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
121
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
122
+ "model.layers.15.self_attn.qkv_proj.biases": "model.safetensors",
123
+ "model.layers.15.self_attn.qkv_proj.scales": "model.safetensors",
124
+ "model.layers.15.self_attn.qkv_proj.weight": "model.safetensors",
125
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
126
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
127
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
128
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
129
+ "model.layers.16.mlp.gate_up_proj.biases": "model.safetensors",
130
+ "model.layers.16.mlp.gate_up_proj.scales": "model.safetensors",
131
+ "model.layers.16.mlp.gate_up_proj.weight": "model.safetensors",
132
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
133
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
134
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
135
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
136
+ "model.layers.16.self_attn.qkv_proj.biases": "model.safetensors",
137
+ "model.layers.16.self_attn.qkv_proj.scales": "model.safetensors",
138
+ "model.layers.16.self_attn.qkv_proj.weight": "model.safetensors",
139
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
140
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
141
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
142
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
143
+ "model.layers.17.mlp.gate_up_proj.biases": "model.safetensors",
144
+ "model.layers.17.mlp.gate_up_proj.scales": "model.safetensors",
145
+ "model.layers.17.mlp.gate_up_proj.weight": "model.safetensors",
146
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
147
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
148
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
149
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
150
+ "model.layers.17.self_attn.qkv_proj.biases": "model.safetensors",
151
+ "model.layers.17.self_attn.qkv_proj.scales": "model.safetensors",
152
+ "model.layers.17.self_attn.qkv_proj.weight": "model.safetensors",
153
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
154
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
155
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
156
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
157
+ "model.layers.18.mlp.gate_up_proj.biases": "model.safetensors",
158
+ "model.layers.18.mlp.gate_up_proj.scales": "model.safetensors",
159
+ "model.layers.18.mlp.gate_up_proj.weight": "model.safetensors",
160
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
161
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
162
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
163
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
164
+ "model.layers.18.self_attn.qkv_proj.biases": "model.safetensors",
165
+ "model.layers.18.self_attn.qkv_proj.scales": "model.safetensors",
166
+ "model.layers.18.self_attn.qkv_proj.weight": "model.safetensors",
167
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
168
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
169
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
170
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
171
+ "model.layers.19.mlp.gate_up_proj.biases": "model.safetensors",
172
+ "model.layers.19.mlp.gate_up_proj.scales": "model.safetensors",
173
+ "model.layers.19.mlp.gate_up_proj.weight": "model.safetensors",
174
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
175
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
176
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
177
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
178
+ "model.layers.19.self_attn.qkv_proj.biases": "model.safetensors",
179
+ "model.layers.19.self_attn.qkv_proj.scales": "model.safetensors",
180
+ "model.layers.19.self_attn.qkv_proj.weight": "model.safetensors",
181
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
182
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
183
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
184
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
185
+ "model.layers.2.mlp.gate_up_proj.biases": "model.safetensors",
186
+ "model.layers.2.mlp.gate_up_proj.scales": "model.safetensors",
187
+ "model.layers.2.mlp.gate_up_proj.weight": "model.safetensors",
188
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
189
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
190
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
191
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
192
+ "model.layers.2.self_attn.qkv_proj.biases": "model.safetensors",
193
+ "model.layers.2.self_attn.qkv_proj.scales": "model.safetensors",
194
+ "model.layers.2.self_attn.qkv_proj.weight": "model.safetensors",
195
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
196
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
197
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
198
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
199
+ "model.layers.20.mlp.gate_up_proj.biases": "model.safetensors",
200
+ "model.layers.20.mlp.gate_up_proj.scales": "model.safetensors",
201
+ "model.layers.20.mlp.gate_up_proj.weight": "model.safetensors",
202
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
203
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
204
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
205
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
206
+ "model.layers.20.self_attn.qkv_proj.biases": "model.safetensors",
207
+ "model.layers.20.self_attn.qkv_proj.scales": "model.safetensors",
208
+ "model.layers.20.self_attn.qkv_proj.weight": "model.safetensors",
209
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
210
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
211
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
212
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
213
+ "model.layers.21.mlp.gate_up_proj.biases": "model.safetensors",
214
+ "model.layers.21.mlp.gate_up_proj.scales": "model.safetensors",
215
+ "model.layers.21.mlp.gate_up_proj.weight": "model.safetensors",
216
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
217
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
218
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
219
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
220
+ "model.layers.21.self_attn.qkv_proj.biases": "model.safetensors",
221
+ "model.layers.21.self_attn.qkv_proj.scales": "model.safetensors",
222
+ "model.layers.21.self_attn.qkv_proj.weight": "model.safetensors",
223
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
224
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
225
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
226
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
227
+ "model.layers.22.mlp.gate_up_proj.biases": "model.safetensors",
228
+ "model.layers.22.mlp.gate_up_proj.scales": "model.safetensors",
229
+ "model.layers.22.mlp.gate_up_proj.weight": "model.safetensors",
230
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
231
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
232
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
233
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
234
+ "model.layers.22.self_attn.qkv_proj.biases": "model.safetensors",
235
+ "model.layers.22.self_attn.qkv_proj.scales": "model.safetensors",
236
+ "model.layers.22.self_attn.qkv_proj.weight": "model.safetensors",
237
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
238
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
239
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
240
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
241
+ "model.layers.23.mlp.gate_up_proj.biases": "model.safetensors",
242
+ "model.layers.23.mlp.gate_up_proj.scales": "model.safetensors",
243
+ "model.layers.23.mlp.gate_up_proj.weight": "model.safetensors",
244
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
245
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
246
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
247
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
248
+ "model.layers.23.self_attn.qkv_proj.biases": "model.safetensors",
249
+ "model.layers.23.self_attn.qkv_proj.scales": "model.safetensors",
250
+ "model.layers.23.self_attn.qkv_proj.weight": "model.safetensors",
251
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
252
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
253
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
254
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
255
+ "model.layers.24.mlp.gate_up_proj.biases": "model.safetensors",
256
+ "model.layers.24.mlp.gate_up_proj.scales": "model.safetensors",
257
+ "model.layers.24.mlp.gate_up_proj.weight": "model.safetensors",
258
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
259
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
260
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
261
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
262
+ "model.layers.24.self_attn.qkv_proj.biases": "model.safetensors",
263
+ "model.layers.24.self_attn.qkv_proj.scales": "model.safetensors",
264
+ "model.layers.24.self_attn.qkv_proj.weight": "model.safetensors",
265
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
266
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
267
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
268
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
269
+ "model.layers.25.mlp.gate_up_proj.biases": "model.safetensors",
270
+ "model.layers.25.mlp.gate_up_proj.scales": "model.safetensors",
271
+ "model.layers.25.mlp.gate_up_proj.weight": "model.safetensors",
272
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
273
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
274
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
275
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
276
+ "model.layers.25.self_attn.qkv_proj.biases": "model.safetensors",
277
+ "model.layers.25.self_attn.qkv_proj.scales": "model.safetensors",
278
+ "model.layers.25.self_attn.qkv_proj.weight": "model.safetensors",
279
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
280
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
281
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
282
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
283
+ "model.layers.26.mlp.gate_up_proj.biases": "model.safetensors",
284
+ "model.layers.26.mlp.gate_up_proj.scales": "model.safetensors",
285
+ "model.layers.26.mlp.gate_up_proj.weight": "model.safetensors",
286
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
287
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
288
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
289
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
290
+ "model.layers.26.self_attn.qkv_proj.biases": "model.safetensors",
291
+ "model.layers.26.self_attn.qkv_proj.scales": "model.safetensors",
292
+ "model.layers.26.self_attn.qkv_proj.weight": "model.safetensors",
293
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
294
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
295
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
296
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
297
+ "model.layers.27.mlp.gate_up_proj.biases": "model.safetensors",
298
+ "model.layers.27.mlp.gate_up_proj.scales": "model.safetensors",
299
+ "model.layers.27.mlp.gate_up_proj.weight": "model.safetensors",
300
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
301
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
302
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
303
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
304
+ "model.layers.27.self_attn.qkv_proj.biases": "model.safetensors",
305
+ "model.layers.27.self_attn.qkv_proj.scales": "model.safetensors",
306
+ "model.layers.27.self_attn.qkv_proj.weight": "model.safetensors",
307
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
308
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
309
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
310
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
311
+ "model.layers.28.mlp.gate_up_proj.biases": "model.safetensors",
312
+ "model.layers.28.mlp.gate_up_proj.scales": "model.safetensors",
313
+ "model.layers.28.mlp.gate_up_proj.weight": "model.safetensors",
314
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
315
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
316
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
317
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
318
+ "model.layers.28.self_attn.qkv_proj.biases": "model.safetensors",
319
+ "model.layers.28.self_attn.qkv_proj.scales": "model.safetensors",
320
+ "model.layers.28.self_attn.qkv_proj.weight": "model.safetensors",
321
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
322
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
323
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
324
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
325
+ "model.layers.29.mlp.gate_up_proj.biases": "model.safetensors",
326
+ "model.layers.29.mlp.gate_up_proj.scales": "model.safetensors",
327
+ "model.layers.29.mlp.gate_up_proj.weight": "model.safetensors",
328
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
329
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
330
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
331
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
332
+ "model.layers.29.self_attn.qkv_proj.biases": "model.safetensors",
333
+ "model.layers.29.self_attn.qkv_proj.scales": "model.safetensors",
334
+ "model.layers.29.self_attn.qkv_proj.weight": "model.safetensors",
335
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
336
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
337
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
338
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
339
+ "model.layers.3.mlp.gate_up_proj.biases": "model.safetensors",
340
+ "model.layers.3.mlp.gate_up_proj.scales": "model.safetensors",
341
+ "model.layers.3.mlp.gate_up_proj.weight": "model.safetensors",
342
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
343
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
344
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
345
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
346
+ "model.layers.3.self_attn.qkv_proj.biases": "model.safetensors",
347
+ "model.layers.3.self_attn.qkv_proj.scales": "model.safetensors",
348
+ "model.layers.3.self_attn.qkv_proj.weight": "model.safetensors",
349
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
350
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
351
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
352
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
353
+ "model.layers.30.mlp.gate_up_proj.biases": "model.safetensors",
354
+ "model.layers.30.mlp.gate_up_proj.scales": "model.safetensors",
355
+ "model.layers.30.mlp.gate_up_proj.weight": "model.safetensors",
356
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
357
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
358
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
359
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
360
+ "model.layers.30.self_attn.qkv_proj.biases": "model.safetensors",
361
+ "model.layers.30.self_attn.qkv_proj.scales": "model.safetensors",
362
+ "model.layers.30.self_attn.qkv_proj.weight": "model.safetensors",
363
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
364
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
365
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
366
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
367
+ "model.layers.31.mlp.gate_up_proj.biases": "model.safetensors",
368
+ "model.layers.31.mlp.gate_up_proj.scales": "model.safetensors",
369
+ "model.layers.31.mlp.gate_up_proj.weight": "model.safetensors",
370
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
371
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
372
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
373
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
374
+ "model.layers.31.self_attn.qkv_proj.biases": "model.safetensors",
375
+ "model.layers.31.self_attn.qkv_proj.scales": "model.safetensors",
376
+ "model.layers.31.self_attn.qkv_proj.weight": "model.safetensors",
377
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
378
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
379
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
380
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
381
+ "model.layers.4.mlp.gate_up_proj.biases": "model.safetensors",
382
+ "model.layers.4.mlp.gate_up_proj.scales": "model.safetensors",
383
+ "model.layers.4.mlp.gate_up_proj.weight": "model.safetensors",
384
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
385
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
386
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
387
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
388
+ "model.layers.4.self_attn.qkv_proj.biases": "model.safetensors",
389
+ "model.layers.4.self_attn.qkv_proj.scales": "model.safetensors",
390
+ "model.layers.4.self_attn.qkv_proj.weight": "model.safetensors",
391
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
392
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
393
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
394
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
395
+ "model.layers.5.mlp.gate_up_proj.biases": "model.safetensors",
396
+ "model.layers.5.mlp.gate_up_proj.scales": "model.safetensors",
397
+ "model.layers.5.mlp.gate_up_proj.weight": "model.safetensors",
398
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
399
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
400
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
402
+ "model.layers.5.self_attn.qkv_proj.biases": "model.safetensors",
403
+ "model.layers.5.self_attn.qkv_proj.scales": "model.safetensors",
404
+ "model.layers.5.self_attn.qkv_proj.weight": "model.safetensors",
405
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
406
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
407
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
408
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
409
+ "model.layers.6.mlp.gate_up_proj.biases": "model.safetensors",
410
+ "model.layers.6.mlp.gate_up_proj.scales": "model.safetensors",
411
+ "model.layers.6.mlp.gate_up_proj.weight": "model.safetensors",
412
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
413
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
414
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
415
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
416
+ "model.layers.6.self_attn.qkv_proj.biases": "model.safetensors",
417
+ "model.layers.6.self_attn.qkv_proj.scales": "model.safetensors",
418
+ "model.layers.6.self_attn.qkv_proj.weight": "model.safetensors",
419
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
420
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
421
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
422
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
423
+ "model.layers.7.mlp.gate_up_proj.biases": "model.safetensors",
424
+ "model.layers.7.mlp.gate_up_proj.scales": "model.safetensors",
425
+ "model.layers.7.mlp.gate_up_proj.weight": "model.safetensors",
426
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
427
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
428
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
429
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
430
+ "model.layers.7.self_attn.qkv_proj.biases": "model.safetensors",
431
+ "model.layers.7.self_attn.qkv_proj.scales": "model.safetensors",
432
+ "model.layers.7.self_attn.qkv_proj.weight": "model.safetensors",
433
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
434
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
435
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
436
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
437
+ "model.layers.8.mlp.gate_up_proj.biases": "model.safetensors",
438
+ "model.layers.8.mlp.gate_up_proj.scales": "model.safetensors",
439
+ "model.layers.8.mlp.gate_up_proj.weight": "model.safetensors",
440
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
441
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
442
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
443
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
444
+ "model.layers.8.self_attn.qkv_proj.biases": "model.safetensors",
445
+ "model.layers.8.self_attn.qkv_proj.scales": "model.safetensors",
446
+ "model.layers.8.self_attn.qkv_proj.weight": "model.safetensors",
447
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
448
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
449
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
450
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
451
+ "model.layers.9.mlp.gate_up_proj.biases": "model.safetensors",
452
+ "model.layers.9.mlp.gate_up_proj.scales": "model.safetensors",
453
+ "model.layers.9.mlp.gate_up_proj.weight": "model.safetensors",
454
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
455
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
456
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
457
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
458
+ "model.layers.9.self_attn.qkv_proj.biases": "model.safetensors",
459
+ "model.layers.9.self_attn.qkv_proj.scales": "model.safetensors",
460
+ "model.layers.9.self_attn.qkv_proj.weight": "model.safetensors",
461
+ "model.norm.weight": "model.safetensors"
462
+ }
463
+ }
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": "<|end|>",
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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": "<|end|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "right",
127
+ "sp_model_kwargs": {},
128
+ "split_special_tokens": false,
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }