Hugging Face's logo

sudy-super
/
coencoder_test2

Text Generation
Transformers
Safetensors
co_encoder
custom_code
Model card Files Community
sudy-super commited on
Commit
61db68f
•
1 Parent(s): 4ec68b9

Upload CoEncoderForConditionalGeneration

Browse files
Files changed (7) hide show
  1. config.json +130 -0
  2. generation_config.json +10 -0
  3. model-00001-of-00004.safetensors +3 -0
  4. model-00002-of-00004.safetensors +3 -0
  5. model-00003-of-00004.safetensors +3 -0
  6. model-00004-of-00004.safetensors +3 -0
  7. model.safetensors.index.json +602 -0
config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./co_model",
3
+ "architectures": [
4
+ "CoEncoderForConditionalGeneration"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_co_encoder.CoEncoderConfig",
8
+ "AutoModelForCausalLM": "modeling_co_encoder.CoEncoderForConditionalGeneration"
9
+ },
10
+ "begin_of_context_token_id": 128002,
11
+ "connector_hidden_act": "gelu",
12
+ "context_config": {
13
+ "_name_or_path": "Qwen/Qwen2-0.5B",
14
+ "add_cross_attention": false,
15
+ "architectures": [
16
+ "Qwen2ForCausalLM"
17
+ ],
18
+ "attention_dropout": 0.0,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": 151643,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 151643,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 896,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 4864,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 131072,
51
+ "max_window_layers": 24,
52
+ "min_length": 0,
53
+ "model_type": "qwen2",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 14,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 24,
59
+ "num_key_value_heads": 2,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": null,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_scaling": null,
74
+ "rope_theta": 1000000.0,
75
+ "sep_token_id": null,
76
+ "sliding_window": null,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": "bfloat16",
87
+ "torchscript": false,
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "use_sliding_window": false,
92
+ "vocab_size": 151936
93
+ },
94
+ "context_feature_layer": -2,
95
+ "context_feature_select_strategy": "default",
96
+ "end_of_context_token_id": 128003,
97
+ "ignore_index": -100,
98
+ "model_type": "co_encoder",
99
+ "projector_hidden_act": "gelu",
100
+ "text_config": {
101
+ "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
102
+ "architectures": [
103
+ "LlamaForCausalLM"
104
+ ],
105
+ "bos_token_id": 128000,
106
+ "eos_token_id": [
107
+ 128001,
108
+ 128008,
109
+ 128009
110
+ ],
111
+ "intermediate_size": 14336,
112
+ "max_position_embeddings": 131072,
113
+ "model_type": "llama",
114
+ "num_key_value_heads": 8,
115
+ "rms_norm_eps": 1e-05,
116
+ "rope_scaling": {
117
+ "factor": 8.0,
118
+ "high_freq_factor": 4.0,
119
+ "low_freq_factor": 1.0,
120
+ "original_max_position_embeddings": 8192,
121
+ "rope_type": "llama3"
122
+ },
123
+ "rope_theta": 500000.0,
124
+ "torch_dtype": "bfloat16",
125
+ "vocab_size": 128256
126
+ },
127
+ "tie_word_embeddings": false,
128
+ "torch_dtype": "bfloat16",
129
+ "transformers_version": "4.45.2"
130
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.45.2"
10
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a7c5c763ebc562263d25fa55a24bea15b28ceeb0f3f0e60c57895bb962b9e81
3
+ size 4973442402
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13d5f738211d5954cc424baabdf3a4e1001811d63aaf5b33b1ac5453c067ad7
3
+ size 4999804248
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1cd2162ea622494ba04cd4585cf4b6778740e56326a7f3b07a6cf9632b2327
3
+ size 4915917680
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d1f965204f37fcd6abf68368fb3a806c1c8cd03089d2a36b4844372187ff6b
3
+ size 2476814440
model.safetensors.index.json ADDED
@@ -0,0 +1,602 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17365900546
4
+ },
5
+ "weight_map": {
6
+ "connector.dynamic_pooling.scale_param": "model-00001-of-00004.safetensors",
7
+ "connector.dynamic_pooling.size_estimation_attention.k_proj.weight": "model-00001-of-00004.safetensors",
8
+ "connector.dynamic_pooling.size_estimation_attention.o_proj.weight": "model-00001-of-00004.safetensors",
9
+ "connector.dynamic_pooling.size_estimation_attention.q_proj.weight": "model-00001-of-00004.safetensors",
10
+ "connector.dynamic_pooling.size_estimation_attention.v_proj.weight": "model-00001-of-00004.safetensors",
11
+ "connector.dynamic_pooling.weighted_pooling_attention.k_proj.weight": "model-00001-of-00004.safetensors",
12
+ "connector.dynamic_pooling.weighted_pooling_attention.o_proj.weight": "model-00001-of-00004.safetensors",
13
+ "connector.dynamic_pooling.weighted_pooling_attention.q_proj.weight": "model-00001-of-00004.safetensors",
14
+ "connector.dynamic_pooling.weighted_pooling_attention.v_proj.weight": "model-00001-of-00004.safetensors",
15
+ "connector.linear_1.bias": "model-00001-of-00004.safetensors",
16
+ "connector.linear_1.weight": "model-00001-of-00004.safetensors",
17
+ "connector.linear_2.bias": "model-00001-of-00004.safetensors",
18
+ "connector.linear_2.weight": "model-00001-of-00004.safetensors",
19
+ "context_tower.tower.lm_head.weight": "model-00001-of-00004.safetensors",
20
+ "context_tower.tower.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
21
+ "context_tower.tower.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "context_tower.tower.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "context_tower.tower.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "context_tower.tower.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "context_tower.tower.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "context_tower.tower.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "context_tower.tower.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "context_tower.tower.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "context_tower.tower.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "context_tower.tower.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "context_tower.tower.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "context_tower.tower.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "context_tower.tower.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
34
+ "context_tower.tower.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
35
+ "context_tower.tower.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
36
+ "context_tower.tower.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
37
+ "context_tower.tower.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
38
+ "context_tower.tower.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
39
+ "context_tower.tower.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
40
+ "context_tower.tower.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
41
+ "context_tower.tower.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
42
+ "context_tower.tower.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
43
+ "context_tower.tower.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
44
+ "context_tower.tower.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
45
+ "context_tower.tower.model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
46
+ "context_tower.tower.model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
47
+ "context_tower.tower.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
48
+ "context_tower.tower.model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
49
+ "context_tower.tower.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
50
+ "context_tower.tower.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
51
+ "context_tower.tower.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
52
+ "context_tower.tower.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
53
+ "context_tower.tower.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
54
+ "context_tower.tower.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
55
+ "context_tower.tower.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
56
+ "context_tower.tower.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
57
+ "context_tower.tower.model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
58
+ "context_tower.tower.model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
59
+ "context_tower.tower.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
60
+ "context_tower.tower.model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
61
+ "context_tower.tower.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
62
+ "context_tower.tower.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
63
+ "context_tower.tower.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
64
+ "context_tower.tower.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
65
+ "context_tower.tower.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
66
+ "context_tower.tower.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
67
+ "context_tower.tower.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
68
+ "context_tower.tower.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
69
+ "context_tower.tower.model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
70
+ "context_tower.tower.model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
71
+ "context_tower.tower.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
72
+ "context_tower.tower.model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
73
+ "context_tower.tower.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
74
+ "context_tower.tower.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
75
+ "context_tower.tower.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
76
+ "context_tower.tower.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
77
+ "context_tower.tower.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
78
+ "context_tower.tower.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
79
+ "context_tower.tower.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
80
+ "context_tower.tower.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
81
+ "context_tower.tower.model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
82
+ "context_tower.tower.model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
83
+ "context_tower.tower.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
84
+ "context_tower.tower.model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
85
+ "context_tower.tower.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
86
+ "context_tower.tower.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
87
+ "context_tower.tower.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
88
+ "context_tower.tower.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
89
+ "context_tower.tower.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
90
+ "context_tower.tower.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
91
+ "context_tower.tower.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
92
+ "context_tower.tower.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
93
+ "context_tower.tower.model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
94
+ "context_tower.tower.model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
95
+ "context_tower.tower.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
96
+ "context_tower.tower.model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
97
+ "context_tower.tower.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
98
+ "context_tower.tower.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
99
+ "context_tower.tower.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
100
+ "context_tower.tower.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
101
+ "context_tower.tower.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
102
+ "context_tower.tower.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
103
+ "context_tower.tower.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
104
+ "context_tower.tower.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
105
+ "context_tower.tower.model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
106
+ "context_tower.tower.model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
107
+ "context_tower.tower.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
108
+ "context_tower.tower.model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
109
+ "context_tower.tower.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
110
+ "context_tower.tower.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
111
+ "context_tower.tower.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
112
+ "context_tower.tower.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
113
+ "context_tower.tower.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
114
+ "context_tower.tower.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
115
+ "context_tower.tower.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
116
+ "context_tower.tower.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
117
+ "context_tower.tower.model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "context_tower.tower.model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "context_tower.tower.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "context_tower.tower.model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "context_tower.tower.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "context_tower.tower.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
123
+ "context_tower.tower.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
124
+ "context_tower.tower.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
125
+ "context_tower.tower.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
126
+ "context_tower.tower.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
127
+ "context_tower.tower.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
128
+ "context_tower.tower.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
129
+ "context_tower.tower.model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
130
+ "context_tower.tower.model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
131
+ "context_tower.tower.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
132
+ "context_tower.tower.model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
133
+ "context_tower.tower.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
134
+ "context_tower.tower.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
135
+ "context_tower.tower.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
136
+ "context_tower.tower.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
137
+ "context_tower.tower.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
138
+ "context_tower.tower.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
139
+ "context_tower.tower.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
140
+ "context_tower.tower.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
141
+ "context_tower.tower.model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "context_tower.tower.model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "context_tower.tower.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "context_tower.tower.model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "context_tower.tower.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "context_tower.tower.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
147
+ "context_tower.tower.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "context_tower.tower.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "context_tower.tower.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
150
+ "context_tower.tower.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "context_tower.tower.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
152
+ "context_tower.tower.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
153
+ "context_tower.tower.model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "context_tower.tower.model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "context_tower.tower.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "context_tower.tower.model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "context_tower.tower.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "context_tower.tower.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "context_tower.tower.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "context_tower.tower.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "context_tower.tower.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "context_tower.tower.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "context_tower.tower.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "context_tower.tower.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "context_tower.tower.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
166
+ "context_tower.tower.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
167
+ "context_tower.tower.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
168
+ "context_tower.tower.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
169
+ "context_tower.tower.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
170
+ "context_tower.tower.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
171
+ "context_tower.tower.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
172
+ "context_tower.tower.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
173
+ "context_tower.tower.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
174
+ "context_tower.tower.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
175
+ "context_tower.tower.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
176
+ "context_tower.tower.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
177
+ "context_tower.tower.model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
178
+ "context_tower.tower.model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
179
+ "context_tower.tower.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
180
+ "context_tower.tower.model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
181
+ "context_tower.tower.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
182
+ "context_tower.tower.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
183
+ "context_tower.tower.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
184
+ "context_tower.tower.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
185
+ "context_tower.tower.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
186
+ "context_tower.tower.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
187
+ "context_tower.tower.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
188
+ "context_tower.tower.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
189
+ "context_tower.tower.model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
190
+ "context_tower.tower.model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
191
+ "context_tower.tower.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
192
+ "context_tower.tower.model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
193
+ "context_tower.tower.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
194
+ "context_tower.tower.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
195
+ "context_tower.tower.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
196
+ "context_tower.tower.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
197
+ "context_tower.tower.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
198
+ "context_tower.tower.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
199
+ "context_tower.tower.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
200
+ "context_tower.tower.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
201
+ "context_tower.tower.model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "context_tower.tower.model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
203
+ "context_tower.tower.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
204
+ "context_tower.tower.model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
205
+ "context_tower.tower.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "context_tower.tower.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
207
+ "context_tower.tower.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
208
+ "context_tower.tower.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
209
+ "context_tower.tower.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
210
+ "context_tower.tower.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
211
+ "context_tower.tower.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
212
+ "context_tower.tower.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
213
+ "context_tower.tower.model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
214
+ "context_tower.tower.model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
215
+ "context_tower.tower.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
216
+ "context_tower.tower.model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
217
+ "context_tower.tower.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
218
+ "context_tower.tower.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
219
+ "context_tower.tower.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "context_tower.tower.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "context_tower.tower.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
222
+ "context_tower.tower.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "context_tower.tower.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
224
+ "context_tower.tower.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "context_tower.tower.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
226
+ "context_tower.tower.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
227
+ "context_tower.tower.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
228
+ "context_tower.tower.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
229
+ "context_tower.tower.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
230
+ "context_tower.tower.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
231
+ "context_tower.tower.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
232
+ "context_tower.tower.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
233
+ "context_tower.tower.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
234
+ "context_tower.tower.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
235
+ "context_tower.tower.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
236
+ "context_tower.tower.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
237
+ "context_tower.tower.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
238
+ "context_tower.tower.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
239
+ "context_tower.tower.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
240
+ "context_tower.tower.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
241
+ "context_tower.tower.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
242
+ "context_tower.tower.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
243
+ "context_tower.tower.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
244
+ "context_tower.tower.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
245
+ "context_tower.tower.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
246
+ "context_tower.tower.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
247
+ "context_tower.tower.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
248
+ "context_tower.tower.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
249
+ "context_tower.tower.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
250
+ "context_tower.tower.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
251
+ "context_tower.tower.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
252
+ "context_tower.tower.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
253
+ "context_tower.tower.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
254
+ "context_tower.tower.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
255
+ "context_tower.tower.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
256
+ "context_tower.tower.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
257
+ "context_tower.tower.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
258
+ "context_tower.tower.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "context_tower.tower.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
260
+ "context_tower.tower.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "context_tower.tower.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "context_tower.tower.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "context_tower.tower.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "context_tower.tower.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "context_tower.tower.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "context_tower.tower.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "context_tower.tower.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "context_tower.tower.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "context_tower.tower.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "context_tower.tower.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "context_tower.tower.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "context_tower.tower.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "context_tower.tower.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "context_tower.tower.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "context_tower.tower.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "context_tower.tower.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "context_tower.tower.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "context_tower.tower.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "context_tower.tower.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "context_tower.tower.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "context_tower.tower.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "context_tower.tower.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "context_tower.tower.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "context_tower.tower.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "context_tower.tower.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "context_tower.tower.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "context_tower.tower.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "context_tower.tower.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "context_tower.tower.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "context_tower.tower.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "context_tower.tower.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "context_tower.tower.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "context_tower.tower.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "context_tower.tower.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "context_tower.tower.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "context_tower.tower.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "context_tower.tower.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "context_tower.tower.model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "context_tower.tower.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "context_tower.tower.model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "context_tower.tower.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "context_tower.tower.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "context_tower.tower.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "context_tower.tower.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "context_tower.tower.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "context_tower.tower.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "context_tower.tower.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "context_tower.tower.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "context_tower.tower.model.norm.weight": "model-00001-of-00004.safetensors",
310
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
311
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
312
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
314
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
315
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
316
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
317
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
318
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
319
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
320
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
322
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
323
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
324
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
325
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
326
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
329
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
330
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
331
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
332
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
333
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
334
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
335
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
336
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
337
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
338
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
339
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
340
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
341
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
342
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
343
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
344
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
345
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
346
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
347
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
348
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
349
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
350
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
351
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
352
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
353
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
354
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
355
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
356
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
357
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
358
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
359
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
360
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
361
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
362
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
363
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
364
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
365
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
366
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
367
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
368
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
369
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
370
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
371
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
372
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
373
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
374
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
375
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
376
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
377
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
378
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
379
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
380
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
381
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
382
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
383
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
384
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
385
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
386
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
387
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
388
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
389
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
390
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
391
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
392
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
393
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
394
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
395
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
396
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
397
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
398
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
399
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
400
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
401
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
402
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
403
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
404
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
405
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
406
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
407
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
408
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
409
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
410
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
411
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
412
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
413
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
414
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
415
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
416
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
417
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
418
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
419
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
420
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
421
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
422
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
423
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
424
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
425
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
426
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
427
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
428
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
429
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
430
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
431
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
432
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
433
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
434
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
435
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
436
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
437
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
438
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
439
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
440
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
441
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
442
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
443
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
444
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
445
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
446
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
447
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
448
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
449
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
450
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
451
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
452
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
453
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
454
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
455
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
456
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
457
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
458
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
459
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
460
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
461
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
462
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
463
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
464
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
465
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
466
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
467
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
468
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
469
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
470
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
471
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
472
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
473
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
474
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
475
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
476
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
477
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
478
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
479
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
480
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
481
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
482
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
483
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
484
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
485
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
486
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
487
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
488
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
489
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
490
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
491
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
492
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
493
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
494
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
495
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
496
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
497
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
498
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
499
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
500
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
501
+ "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
502
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
503
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
504
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
505
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
506
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
507
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
508
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
509
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
510
+ "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
511
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
512
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
513
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
514
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
515
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
516
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
517
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
518
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
519
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
520
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
521
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
523
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
524
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
525
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
526
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
528
+ "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
529
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
530
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
531
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
532
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
533
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
534
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
535
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
536
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
537
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
538
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
539
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
540
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
541
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
542
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
543
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
544
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
545
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
546
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
547
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
548
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
549
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
550
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
551
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
552
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
553
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
554
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
555
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
556
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
557
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
559
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
560
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
561
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
562
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
563
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
564
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
565
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
566
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
567
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
568
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
569
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
570
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
571
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
572
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
573
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
574
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
575
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
576
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
577
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
578
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
579
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
580
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
581
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
582
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
583
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
584
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
585
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
586
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
587
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
588
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
589
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
590
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
591
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
592
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
593
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
594
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
595
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
596
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
597
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
598
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
599
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
600
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors"
601
+ }
602
+ }