Hugging Face's logo

lamm-mit
/
Llama-3.2-3B-Instruct-Sparse-GIN-bio

Transformers
PyTorch
llama
trl
sft
text-generation-inference
Inference Endpoints
Model card Files Community
mjbuehler commited on
Commit
e2468d9
·
verified ·
1 Parent(s): a9d9ad7

Upload LlamaForCausalLMWithGNN

Browse files
Files changed (7) hide show
  1. README.md +201 -0
  2. config.json +141 -0
  3. generation_config.json +11 -0
  4. pytorch_model-00001-of-00003.bin +3 -0
  5. pytorch_model-00002-of-00003.bin +3 -0
  6. pytorch_model-00003-of-00003.bin +3 -0
  7. pytorch_model.bin.index.json +626 -0
README.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLMWithGNN"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "gnn_config": {
14
+ "GIN_after_attention": true,
15
+ "GIN_after_attention_pre_GIN_norm": true,
16
+ "GIN_after_attention_skip": true,
17
+ "GIN_edge_weight_scaling": true,
18
+ "GIN_hidden_dim_multiplier": 1,
19
+ "GIN_use_MLP": true,
20
+ "GIN_use_norm": false,
21
+ "LlamaAttentionHierarchicalPerceiverAR_use_rope": true,
22
+ "LlamaAttentionHierarchicalVariant_2_PerceiverAR_use_skip": true,
23
+ "MLP_type": "standard_MLP",
24
+ "N_GNN_from_attention_layers": 3,
25
+ "activation": "prelu",
26
+ "add_rope": false,
27
+ "adj_construction_method": "sum",
28
+ "adj_transform_hidden_dim": 128,
29
+ "attention_GIN_MLP_GIN_MLP_mode": "shared",
30
+ "attention_GIN_MLP_GIN_MLP_pre_aggregate": true,
31
+ "attention_GIN_MLP_GIN_binary_scale": 1.0,
32
+ "attention_GIN_MLP_GIN_fuse_mode": "epsilon",
33
+ "attention_GIN_MLP_GIN_learnable_threshold": false,
34
+ "attention_GIN_MLP_GIN_mode": "default",
35
+ "attention_GIN_MLP_GIN_sharp_softplus_beta": 10.0,
36
+ "attention_GIN_MLP_GIN_softmax_temperature": 1.0,
37
+ "attention_GIN_MLP_GIN_threshold_mode": "none",
38
+ "attention_GIN_MLP_GIN_threshold_value": 0.2,
39
+ "attention_GIN_MLP_GIN_top_k_fraction_of_sequence_length": 0.1,
40
+ "attention_GIN_MLP_GIN_use_ReLU_instead_of_softmax": true,
41
+ "attention_GIN_MLP_GIN_use_softmax": false,
42
+ "attention_GIN_MLP_attention_mix_mode": "A",
43
+ "attention_GIN_MLP_multiplier": 2,
44
+ "attention_GIN_MLP_o_proj_at_end": false,
45
+ "attention_GIN_MLP_scoring_hidden_dim": 512,
46
+ "attention_GIN_MLP_second_order_factor": 0.1,
47
+ "attention_GIN_MLP_separate_attention": false,
48
+ "attention_GIN_MLP_use_scoring_fnct": true,
49
+ "attention_GIN_MLP_use_second_order": false,
50
+ "attention_epsilon_strategy": "default",
51
+ "attention_epsilon_uniform_value": 0.5,
52
+ "combined_norm": false,
53
+ "continuous_transform_alpha": 10.0,
54
+ "distance_scaling_method": "power",
55
+ "distance_weight_strength": 1.0,
56
+ "dropout": 0.1,
57
+ "enforce_causality": true,
58
+ "epsilon_threshold": 0.6,
59
+ "gnn_logic": "before_MLP",
60
+ "gnn_mode": "single",
61
+ "gnn_residual": false,
62
+ "gnn_type": "causal_gin",
63
+ "group_tokens_for_coarse_graining": false,
64
+ "hidden_dim": 155,
65
+ "hierarchical_enc_dec_type": "PerceiverAR",
66
+ "initial_sharpening_value": 1.0,
67
+ "lambda_GNN": 0.5,
68
+ "lambda_GNN_initial": 0.0,
69
+ "learnable_aggregate_activation": "softmax",
70
+ "max_position_embeddings": 2048,
71
+ "mix_weights_initial": 0.5,
72
+ "model_type": "",
73
+ "norm_to_hidden_states": false,
74
+ "num_latent_layers": 4,
75
+ "num_latents": 32,
76
+ "num_latents_list": [
77
+ 64,
78
+ 32,
79
+ 8
80
+ ],
81
+ "num_layers": 1,
82
+ "per_head_ff": false,
83
+ "plot_for_debugging": false,
84
+ "remove_self_connections": false,
85
+ "residual_epsilon_strategy": "default",
86
+ "residual_epsilon_uniform_value": 0.1,
87
+ "rms_norm_eps": 1e-05,
88
+ "sharpening_value_init": "value",
89
+ "soft_masking_initial_threshold": 0.01,
90
+ "soft_masking_k": 10.0,
91
+ "threshold": 0.1,
92
+ "threshold_any_tau": 0.1,
93
+ "tokenizer": null,
94
+ "top_k": 8,
95
+ "use_GNN_from_attention": "none",
96
+ "use_GNN_from_attention_add_RoPE_at_every_layer": false,
97
+ "use_differential_attention": false,
98
+ "use_differential_attention_group_norm": false,
99
+ "use_distance_scaling": false,
100
+ "use_fixed_number_of_tokens_per_latent": false,
101
+ "use_graph_property_modulation": false,
102
+ "use_graph_property_modulation_with_norm": false,
103
+ "use_graph_property_modulation_with_norm_use_causal_clustering": true,
104
+ "use_hierarchical_attention": false,
105
+ "use_layer_norm": true,
106
+ "use_layer_norm_in_GIN_MLP": false,
107
+ "use_no_norm_in_GIN_MLP": false,
108
+ "use_original_hidden_states": false,
109
+ "use_original_hidden_states_add_attention": false,
110
+ "use_projection": true,
111
+ "use_sharpening": false,
112
+ "use_soft_masking": false,
113
+ "zero_below_epsilon_threshold": true
114
+ },
115
+ "head_dim": 128,
116
+ "hidden_act": "silu",
117
+ "hidden_size": 3072,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 8192,
120
+ "max_position_embeddings": 131072,
121
+ "mlp_bias": false,
122
+ "model_type": "llama",
123
+ "num_attention_heads": 24,
124
+ "num_hidden_layers": 28,
125
+ "num_key_value_heads": 8,
126
+ "pretraining_tp": 1,
127
+ "rms_norm_eps": 1e-05,
128
+ "rope_scaling": {
129
+ "factor": 32.0,
130
+ "high_freq_factor": 4.0,
131
+ "low_freq_factor": 1.0,
132
+ "original_max_position_embeddings": 8192,
133
+ "rope_type": "llama3"
134
+ },
135
+ "rope_theta": 500000.0,
136
+ "tie_word_embeddings": true,
137
+ "torch_dtype": "float32",
138
+ "transformers_version": "4.46.1",
139
+ "use_cache": false,
140
+ "vocab_size": 128256
141
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.46.1",
10
+ "use_cache": false
11
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda021aabff872e70e7b5e77331ecec00b4dc92361bd51f467eded2947564a89
3
+ size 4930380804
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fe6c312b8fb976e253a5b28206e2cb3323e7f886eb3422a7cfa333f3daeb57
3
+ size 4981222337
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745bef0a77693df2bd66cd727a7266492df634fd45720317d91cfdba90c82d21
3
+ size 4628399722
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,626 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14539791008
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.0.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.0.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.0.trainable_scale": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.1.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.1.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.1.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.1.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.1.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.1.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.1.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.1.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.1.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.1.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.1.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.1.trainable_scale": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.10.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.10.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.10.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.10.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.10.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.10.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.10.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.10.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.10.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.10.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.10.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.10.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.10.trainable_scale": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.11.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.11.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.11.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.11.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.11.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.11.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.11.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.11.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.11.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.11.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.11.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.11.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.11.trainable_scale": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.12.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.12.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.12.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.12.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.12.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.12.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.12.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.12.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.12.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.12.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.12.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.12.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.12.trainable_scale": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.13.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.13.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.13.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.13.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.13.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.13.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.13.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.13.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.13.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.13.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.13.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.13.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.13.trainable_scale": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.14.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.14.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.14.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.14.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.14.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.14.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.14.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.14.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.14.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.14.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.14.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.14.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.14.trainable_scale": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.15.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.15.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.15.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.15.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.15.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.15.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.15.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.15.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.15.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.15.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.15.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.15.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.15.trainable_scale": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.16.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.16.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.16.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.16.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.16.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.16.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.16.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.16.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.16.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.16.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.16.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.16.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.16.trainable_scale": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.17.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.17.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.17.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.17.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.17.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.17.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.17.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.17.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.17.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.17.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.17.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.17.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.17.trainable_scale": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.18.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.18.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.18.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.18.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.18.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.18.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.18.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.18.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.18.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.18.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.18.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.layers.18.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
240
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
242
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
246
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
247
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
248
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.layers.18.trainable_scale": "pytorch_model-00002-of-00003.bin",
250
+ "model.layers.19.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.19.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.19.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
253
+ "model.layers.19.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.19.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.19.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.19.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.19.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.19.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.layers.19.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
260
+ "model.layers.19.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.layers.19.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
262
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
263
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
264
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
266
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
268
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
270
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.19.trainable_scale": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.2.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.2.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.2.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.2.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.2.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.2.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.2.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.2.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.2.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.2.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.2.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.2.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.2.trainable_scale": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.20.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.20.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.20.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.20.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.20.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.20.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.20.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.20.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.20.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.20.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.20.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.20.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
309
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
312
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
313
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
314
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
315
+ "model.layers.20.trainable_scale": "pytorch_model-00002-of-00003.bin",
316
+ "model.layers.21.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.21.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.21.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.21.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.21.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.21.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.21.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.21.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.21.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.21.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.21.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.21.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.21.trainable_scale": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.22.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.22.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.22.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.22.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.22.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.22.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.22.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.22.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.22.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.22.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.22.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
349
+ "model.layers.22.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
350
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
351
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
352
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
353
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
354
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
355
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
356
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
357
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
358
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
359
+ "model.layers.22.trainable_scale": "pytorch_model-00003-of-00003.bin",
360
+ "model.layers.23.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
361
+ "model.layers.23.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
362
+ "model.layers.23.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
363
+ "model.layers.23.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
364
+ "model.layers.23.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
365
+ "model.layers.23.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
366
+ "model.layers.23.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
367
+ "model.layers.23.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
368
+ "model.layers.23.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
369
+ "model.layers.23.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
370
+ "model.layers.23.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
371
+ "model.layers.23.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
372
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
373
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
374
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
375
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
376
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
377
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
378
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
379
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
381
+ "model.layers.23.trainable_scale": "pytorch_model-00003-of-00003.bin",
382
+ "model.layers.24.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
383
+ "model.layers.24.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
384
+ "model.layers.24.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
385
+ "model.layers.24.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
386
+ "model.layers.24.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
387
+ "model.layers.24.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
388
+ "model.layers.24.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
389
+ "model.layers.24.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
390
+ "model.layers.24.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
391
+ "model.layers.24.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
392
+ "model.layers.24.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
393
+ "model.layers.24.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
394
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
395
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
396
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
397
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
398
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
399
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
400
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
401
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
402
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
403
+ "model.layers.24.trainable_scale": "pytorch_model-00003-of-00003.bin",
404
+ "model.layers.25.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
405
+ "model.layers.25.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
406
+ "model.layers.25.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
407
+ "model.layers.25.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
408
+ "model.layers.25.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
409
+ "model.layers.25.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
410
+ "model.layers.25.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
411
+ "model.layers.25.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
412
+ "model.layers.25.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.layers.25.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
414
+ "model.layers.25.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.layers.25.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
417
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
419
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
423
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
425
+ "model.layers.25.trainable_scale": "pytorch_model-00003-of-00003.bin",
426
+ "model.layers.26.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.layers.26.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.layers.26.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
429
+ "model.layers.26.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
430
+ "model.layers.26.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.layers.26.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
432
+ "model.layers.26.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
433
+ "model.layers.26.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
434
+ "model.layers.26.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
435
+ "model.layers.26.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
436
+ "model.layers.26.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
437
+ "model.layers.26.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
439
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
441
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
443
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
445
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
447
+ "model.layers.26.trainable_scale": "pytorch_model-00003-of-00003.bin",
448
+ "model.layers.27.gnn.activation.weight": "pytorch_model-00003-of-00003.bin",
449
+ "model.layers.27.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.layers.27.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin",
451
+ "model.layers.27.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin",
452
+ "model.layers.27.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin",
453
+ "model.layers.27.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin",
454
+ "model.layers.27.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin",
455
+ "model.layers.27.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin",
456
+ "model.layers.27.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin",
457
+ "model.layers.27.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin",
458
+ "model.layers.27.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin",
459
+ "model.layers.27.gnn_norm.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
461
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
463
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
465
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
467
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
469
+ "model.layers.27.trainable_scale": "pytorch_model-00003-of-00003.bin",
470
+ "model.layers.3.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
471
+ "model.layers.3.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
472
+ "model.layers.3.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
473
+ "model.layers.3.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
474
+ "model.layers.3.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
475
+ "model.layers.3.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
476
+ "model.layers.3.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
477
+ "model.layers.3.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
478
+ "model.layers.3.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
479
+ "model.layers.3.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
480
+ "model.layers.3.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
481
+ "model.layers.3.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
482
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
483
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
484
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
485
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
486
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
487
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
488
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
489
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
490
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
491
+ "model.layers.3.trainable_scale": "pytorch_model-00001-of-00003.bin",
492
+ "model.layers.4.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
493
+ "model.layers.4.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
494
+ "model.layers.4.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
495
+ "model.layers.4.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
496
+ "model.layers.4.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
497
+ "model.layers.4.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
498
+ "model.layers.4.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
499
+ "model.layers.4.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
500
+ "model.layers.4.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
501
+ "model.layers.4.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
502
+ "model.layers.4.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
503
+ "model.layers.4.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
504
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
505
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
506
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
507
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
508
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
509
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
510
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
511
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
512
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
513
+ "model.layers.4.trainable_scale": "pytorch_model-00001-of-00003.bin",
514
+ "model.layers.5.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
515
+ "model.layers.5.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
516
+ "model.layers.5.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
517
+ "model.layers.5.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
518
+ "model.layers.5.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
519
+ "model.layers.5.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
520
+ "model.layers.5.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
521
+ "model.layers.5.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
522
+ "model.layers.5.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
523
+ "model.layers.5.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
524
+ "model.layers.5.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
525
+ "model.layers.5.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
526
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
527
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
528
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
529
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
530
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
531
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
532
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
533
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
534
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
535
+ "model.layers.5.trainable_scale": "pytorch_model-00001-of-00003.bin",
536
+ "model.layers.6.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
537
+ "model.layers.6.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
538
+ "model.layers.6.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
539
+ "model.layers.6.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
540
+ "model.layers.6.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
541
+ "model.layers.6.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
542
+ "model.layers.6.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
543
+ "model.layers.6.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
544
+ "model.layers.6.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
545
+ "model.layers.6.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
546
+ "model.layers.6.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
547
+ "model.layers.6.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
548
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
549
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
550
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
551
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
552
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
553
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
554
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
555
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
556
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
557
+ "model.layers.6.trainable_scale": "pytorch_model-00001-of-00003.bin",
558
+ "model.layers.7.gnn.activation.weight": "pytorch_model-00001-of-00003.bin",
559
+ "model.layers.7.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin",
560
+ "model.layers.7.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin",
561
+ "model.layers.7.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
562
+ "model.layers.7.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
563
+ "model.layers.7.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
564
+ "model.layers.7.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
565
+ "model.layers.7.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin",
566
+ "model.layers.7.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin",
567
+ "model.layers.7.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin",
568
+ "model.layers.7.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin",
569
+ "model.layers.7.gnn_norm.weight": "pytorch_model-00001-of-00003.bin",
570
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
571
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
572
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
573
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
574
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
575
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
576
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
577
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
578
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
579
+ "model.layers.7.trainable_scale": "pytorch_model-00001-of-00003.bin",
580
+ "model.layers.8.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
581
+ "model.layers.8.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
582
+ "model.layers.8.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
583
+ "model.layers.8.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
584
+ "model.layers.8.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
585
+ "model.layers.8.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
586
+ "model.layers.8.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
587
+ "model.layers.8.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
588
+ "model.layers.8.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
589
+ "model.layers.8.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
590
+ "model.layers.8.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
591
+ "model.layers.8.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
592
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
593
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
594
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
595
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
596
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
597
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
598
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
599
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
600
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
601
+ "model.layers.8.trainable_scale": "pytorch_model-00001-of-00003.bin",
602
+ "model.layers.9.gnn.activation.weight": "pytorch_model-00002-of-00003.bin",
603
+ "model.layers.9.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin",
604
+ "model.layers.9.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin",
605
+ "model.layers.9.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin",
606
+ "model.layers.9.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin",
607
+ "model.layers.9.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin",
608
+ "model.layers.9.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin",
609
+ "model.layers.9.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin",
610
+ "model.layers.9.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin",
611
+ "model.layers.9.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin",
612
+ "model.layers.9.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin",
613
+ "model.layers.9.gnn_norm.weight": "pytorch_model-00002-of-00003.bin",
614
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
615
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
616
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
617
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
618
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
619
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
620
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
621
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
622
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
623
+ "model.layers.9.trainable_scale": "pytorch_model-00002-of-00003.bin",
624
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
625
+ }
626
+ }