Hugging Face's logo

Jennny
/
qwen-math-value-model-combined

Safetensors
qwen2
custom_code
Model card Files
xet
 Community
Jennny commited on
Commit
dc15e33
·
verified ·
1 Parent(s): 3012ad3

Upload mathematical value model

Browse files
Files changed (6) hide show
  1. config.json +105 -0
  2. model-00001-of-00003.safetensors +3 -0
  3. model-00002-of-00003.safetensors +3 -0
  4. model-00003-of-00003.safetensors +3 -0
  5. model.safetensors.index.json +349 -0
  6. value_head.pt +3 -0
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 152064,
3
+ "max_position_embeddings": 4096,
4
+ "hidden_size": 3584,
5
+ "intermediate_size": 18944,
6
+ "num_hidden_layers": 28,
7
+ "num_attention_heads": 28,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
+ "num_key_value_heads": 4,
12
+ "hidden_act": "silu",
13
+ "initializer_range": 0.02,
14
+ "rms_norm_eps": 1e-05,
15
+ "use_cache": true,
16
+ "rope_theta": 10000.0,
17
+ "attention_dropout": 0.0,
18
+ "return_dict": true,
19
+ "output_hidden_states": false,
20
+ "output_attentions": false,
21
+ "torchscript": false,
22
+ "torch_dtype": "bfloat16",
23
+ "use_bfloat16": false,
24
+ "tf_legacy_loss": false,
25
+ "pruned_heads": {},
26
+ "tie_word_embeddings": false,
27
+ "chunk_size_feed_forward": 0,
28
+ "is_encoder_decoder": false,
29
+ "is_decoder": false,
30
+ "cross_attention_hidden_size": null,
31
+ "add_cross_attention": false,
32
+ "tie_encoder_decoder": false,
33
+ "max_length": 20,
34
+ "min_length": 0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "num_beams": 1,
38
+ "num_beam_groups": 1,
39
+ "diversity_penalty": 0.0,
40
+ "temperature": 1.0,
41
+ "top_k": 50,
42
+ "top_p": 1.0,
43
+ "typical_p": 1.0,
44
+ "repetition_penalty": 1.0,
45
+ "length_penalty": 1.0,
46
+ "no_repeat_ngram_size": 0,
47
+ "encoder_no_repeat_ngram_size": 0,
48
+ "bad_words_ids": null,
49
+ "num_return_sequences": 1,
50
+ "output_scores": false,
51
+ "return_dict_in_generate": false,
52
+ "forced_bos_token_id": null,
53
+ "forced_eos_token_id": null,
54
+ "remove_invalid_values": false,
55
+ "exponential_decay_length_penalty": null,
56
+ "suppress_tokens": null,
57
+ "begin_suppress_tokens": null,
58
+ "architectures": [
59
+ "Qwen2ForProcessRewardModel"
60
+ ],
61
+ "finetuning_task": null,
62
+ "id2label": {
63
+ "0": "LABEL_0",
64
+ "1": "LABEL_1"
65
+ },
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1
69
+ },
70
+ "tokenizer_class": null,
71
+ "prefix": null,
72
+ "bos_token_id": 151643,
73
+ "pad_token_id": null,
74
+ "eos_token_id": 151645,
75
+ "sep_token_id": null,
76
+ "decoder_start_token_id": null,
77
+ "task_specific_params": null,
78
+ "problem_type": null,
79
+ "_name_or_path": "Qwen/Qwen2.5-Math-PRM-7B",
80
+ "_attn_implementation_autoset": false,
81
+ "transformers_version": "4.49.0",
82
+ "auto_map": {
83
+ "AutoConfig": "Qwen/Qwen2.5-Math-PRM-7B--configuration_qwen2_rm.Qwen2RMConfig",
84
+ "AutoModel": "Qwen/Qwen2.5-Math-PRM-7B--modeling_qwen2_rm.Qwen2ForProcessRewardModel"
85
+ },
86
+ "model_type": "qwen2",
87
+ "use_mrope": false,
88
+ "value_head": {
89
+ "layers": [
90
+ {
91
+ "type": "linear",
92
+ "in_features": 3584,
93
+ "out_features": 3584
94
+ },
95
+ {
96
+ "type": "relu"
97
+ },
98
+ {
99
+ "type": "linear",
100
+ "in_features": 3584,
101
+ "out_features": 1
102
+ }
103
+ ]
104
+ }
105
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cddf6943eb317b2784574fc975c6df94c904561fb29a0c9ffd7737904cd42bc
3
+ size 4877660776
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34022e8b3756fa42fa78a3d6717a972504243ce0ed2a70047019eded672cb27c
3
+ size 4932751008
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b914c9213891bc0cfce4c098577587d73e37bfc251f27d40d1558518f5aac080
3
+ size 4356577172
model.safetensors.index.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14166949892
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
265
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
268
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
270
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
277
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
280
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
282
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
289
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
292
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
294
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
296
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
297
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
298
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
299
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
300
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
301
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
302
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
303
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
304
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
305
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
306
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
307
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
309
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
310
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
312
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
313
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
314
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
316
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
318
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
324
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
325
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
328
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
330
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
332
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
334
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
336
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
337
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
340
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
342
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.norm.weight": "model-00003-of-00003.safetensors",
344
+ "score.0.bias": "model-00003-of-00003.safetensors",
345
+ "score.0.weight": "model-00003-of-00003.safetensors",
346
+ "score.2.bias": "model-00003-of-00003.safetensors",
347
+ "score.2.weight": "model-00003-of-00003.safetensors"
348
+ }
349
+ }
value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bfb16cc8111a0ee12f4515621a1e4cbcd8bedd684c2d0eb8d6b3a3281ddc06
3
+ size 51411048