Hugging Face's logo

appledora
/
recast3.1-G16W8H4

Text Generation
Transformers
PyTorch
recast8b_llama
custom_code
Model card Files Community
appledora commited on
Commit
df9697f
·
verified ·
1 Parent(s): 7168432

Add RECASTMLP LLaMA model

Browse files
Files changed (8) hide show
  1. README.md +199 -0
  2. config.json +31 -86
  3. generation_config.json +6 -0
  4. pytorch_model-00001-of-00004.bin +3 -0
  5. pytorch_model-00002-of-00004.bin +3 -0
  6. pytorch_model-00003-of-00004.bin +3 -0
  7. pytorch_model-00004-of-00004.bin +3 -0
  8. pytorch_model.bin.index.json +538 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json CHANGED
@@ -1,99 +1,44 @@
1
  {
2
- "vocab_size": 128256,
3
- "max_position_embeddings": 131072,
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "hidden_size": 4096,
 
5
  "intermediate_size": 14336,
6
- "num_hidden_layers": 32,
 
 
7
  "num_attention_heads": 32,
 
 
 
8
  "num_key_value_heads": 8,
9
- "hidden_act": "silu",
10
- "initializer_range": 0.02,
11
- "rms_norm_eps": 1e-05,
12
  "pretraining_tp": 1,
13
- "use_cache": true,
14
- "mlp_bias": false,
15
- "attention_bias": false,
16
- "attention_dropout": 0.0,
17
- "rope_theta": 500000.0,
18
  "rope_scaling": {
19
  "factor": 32.0,
20
- "low_freq_factor": 1.0,
21
  "high_freq_factor": 4.0,
 
22
  "original_max_position_embeddings": 8192,
23
  "rope_type": "llama3"
24
  },
25
- "torch_dtype": null,
26
- "num_templates": 2,
27
- "num_groups": 16,
28
- "coef_height": 4,
29
- "num_cf": 1,
30
- "return_dict": true,
31
- "output_hidden_states": false,
32
- "output_attentions": false,
33
- "torchscript": false,
34
- "use_bfloat16": false,
35
- "tf_legacy_loss": false,
36
- "pruned_heads": {},
37
  "tie_word_embeddings": false,
38
- "chunk_size_feed_forward": 0,
39
- "is_encoder_decoder": false,
40
- "is_decoder": false,
41
- "cross_attention_hidden_size": null,
42
- "add_cross_attention": false,
43
- "tie_encoder_decoder": false,
44
- "max_length": 20,
45
- "min_length": 0,
46
- "do_sample": false,
47
- "early_stopping": false,
48
- "num_beams": 1,
49
- "num_beam_groups": 1,
50
- "diversity_penalty": 0.0,
51
- "temperature": 1.0,
52
- "top_k": 50,
53
- "top_p": 1.0,
54
- "typical_p": 1.0,
55
- "repetition_penalty": 1.0,
56
- "length_penalty": 1.0,
57
- "no_repeat_ngram_size": 0,
58
- "encoder_no_repeat_ngram_size": 0,
59
- "bad_words_ids": null,
60
- "num_return_sequences": 1,
61
- "output_scores": false,
62
- "return_dict_in_generate": false,
63
- "forced_bos_token_id": null,
64
- "forced_eos_token_id": null,
65
- "remove_invalid_values": false,
66
- "exponential_decay_length_penalty": null,
67
- "suppress_tokens": null,
68
- "begin_suppress_tokens": null,
69
- "architectures": [
70
- "RECAST8b_LlamaForCausalLM"
71
- ],
72
- "finetuning_task": null,
73
- "id2label": {
74
- "0": "LABEL_0",
75
- "1": "LABEL_1"
76
- },
77
- "label2id": {
78
- "LABEL_0": 0,
79
- "LABEL_1": 1
80
- },
81
- "tokenizer_class": null,
82
- "prefix": null,
83
- "bos_token_id": 128000,
84
- "pad_token_id": null,
85
- "eos_token_id": 128001,
86
- "sep_token_id": null,
87
- "decoder_start_token_id": null,
88
- "task_specific_params": null,
89
- "problem_type": null,
90
- "_name_or_path": "",
91
- "transformers_version": "4.43.0.dev0",
92
- "coef_width": 8,
93
- "model_type": "recast8b_llama",
94
- "auto_map": {
95
- "AutoConfig": "configuration_recast_llama.RECAST8b_llama",
96
- "AutoModel": "modeling_recast_llama.RECAST8b_llamaModel",
97
- "AutoModelForCausalLM": "modeling_recast_llama.RECAST8b_LlamaForCausalLM"
98
- }
99
- }
 
1
  {
2
+ "architectures": [
3
+ "RECAST8b_LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_recast_llama.RECAST8b_llama",
9
+ "AutoModel": "modeling_recast_llama.RECAST8b_llamaModel",
10
+ "AutoModelForCausalLM": "modeling_recast_llama.RECAST8b_LlamaForCausalLM"
11
+ },
12
+ "bos_token_id": 128000,
13
+ "coef_height": 4,
14
+ "coef_width": 8,
15
+ "eos_token_id": 128001,
16
+ "hidden_act": "silu",
17
  "hidden_size": 4096,
18
+ "initializer_range": 0.02,
19
  "intermediate_size": 14336,
20
+ "max_position_embeddings": 131072,
21
+ "mlp_bias": false,
22
+ "model_type": "recast8b_llama",
23
  "num_attention_heads": 32,
24
+ "num_cf": 1,
25
+ "num_groups": 16,
26
+ "num_hidden_layers": 32,
27
  "num_key_value_heads": 8,
28
+ "num_templates": 2,
 
 
29
  "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
 
 
 
 
31
  "rope_scaling": {
32
  "factor": 32.0,
 
33
  "high_freq_factor": 4.0,
34
+ "low_freq_factor": 1.0,
35
  "original_max_position_embeddings": 8192,
36
  "rope_type": "llama3"
37
  },
38
+ "rope_theta": 500000.0,
 
 
 
 
 
 
 
 
 
 
 
39
  "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.44.0",
42
+ "use_cache": true,
43
+ "vocab_size": 128256
44
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.44.0"
6
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f3f6f5a8769b364caa776b7b47f78e35fe6f5b7e73e0570d6e0176d2b91c5d
3
+ size 8678023876
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3944a6c6cad358c863b36e610d5e363e25d758d85eed0dd9237d2ad5b0b20821
3
+ size 8992602880
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc9b27544ca64c1a9606da6819c5827a44cd2d55478e1775a0dcf12f1ea3f95
3
+ size 8792018251
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d95475b6b8df32c77f9641915f0b665f8d14d0c8a04cf1cb52d70362ad803595
3
+ size 5658568250
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32121065472
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.attn_banks.0.k_templates": "pytorch_model-00002-of-00004.bin",
8
+ "model.attn_banks.0.q_templates": "pytorch_model-00002-of-00004.bin",
9
+ "model.attn_banks.0.v_templates": "pytorch_model-00002-of-00004.bin",
10
+ "model.attn_banks.1.k_templates": "pytorch_model-00002-of-00004.bin",
11
+ "model.attn_banks.1.q_templates": "pytorch_model-00002-of-00004.bin",
12
+ "model.attn_banks.1.v_templates": "pytorch_model-00002-of-00004.bin",
13
+ "model.attn_banks.10.k_templates": "pytorch_model-00003-of-00004.bin",
14
+ "model.attn_banks.10.q_templates": "pytorch_model-00003-of-00004.bin",
15
+ "model.attn_banks.10.v_templates": "pytorch_model-00003-of-00004.bin",
16
+ "model.attn_banks.11.k_templates": "pytorch_model-00003-of-00004.bin",
17
+ "model.attn_banks.11.q_templates": "pytorch_model-00003-of-00004.bin",
18
+ "model.attn_banks.11.v_templates": "pytorch_model-00003-of-00004.bin",
19
+ "model.attn_banks.12.k_templates": "pytorch_model-00003-of-00004.bin",
20
+ "model.attn_banks.12.q_templates": "pytorch_model-00003-of-00004.bin",
21
+ "model.attn_banks.12.v_templates": "pytorch_model-00003-of-00004.bin",
22
+ "model.attn_banks.13.k_templates": "pytorch_model-00003-of-00004.bin",
23
+ "model.attn_banks.13.q_templates": "pytorch_model-00003-of-00004.bin",
24
+ "model.attn_banks.13.v_templates": "pytorch_model-00003-of-00004.bin",
25
+ "model.attn_banks.14.k_templates": "pytorch_model-00003-of-00004.bin",
26
+ "model.attn_banks.14.q_templates": "pytorch_model-00003-of-00004.bin",
27
+ "model.attn_banks.14.v_templates": "pytorch_model-00003-of-00004.bin",
28
+ "model.attn_banks.15.k_templates": "pytorch_model-00003-of-00004.bin",
29
+ "model.attn_banks.15.q_templates": "pytorch_model-00003-of-00004.bin",
30
+ "model.attn_banks.15.v_templates": "pytorch_model-00003-of-00004.bin",
31
+ "model.attn_banks.2.k_templates": "pytorch_model-00003-of-00004.bin",
32
+ "model.attn_banks.2.q_templates": "pytorch_model-00002-of-00004.bin",
33
+ "model.attn_banks.2.v_templates": "pytorch_model-00003-of-00004.bin",
34
+ "model.attn_banks.3.k_templates": "pytorch_model-00003-of-00004.bin",
35
+ "model.attn_banks.3.q_templates": "pytorch_model-00003-of-00004.bin",
36
+ "model.attn_banks.3.v_templates": "pytorch_model-00003-of-00004.bin",
37
+ "model.attn_banks.4.k_templates": "pytorch_model-00003-of-00004.bin",
38
+ "model.attn_banks.4.q_templates": "pytorch_model-00003-of-00004.bin",
39
+ "model.attn_banks.4.v_templates": "pytorch_model-00003-of-00004.bin",
40
+ "model.attn_banks.5.k_templates": "pytorch_model-00003-of-00004.bin",
41
+ "model.attn_banks.5.q_templates": "pytorch_model-00003-of-00004.bin",
42
+ "model.attn_banks.5.v_templates": "pytorch_model-00003-of-00004.bin",
43
+ "model.attn_banks.6.k_templates": "pytorch_model-00003-of-00004.bin",
44
+ "model.attn_banks.6.q_templates": "pytorch_model-00003-of-00004.bin",
45
+ "model.attn_banks.6.v_templates": "pytorch_model-00003-of-00004.bin",
46
+ "model.attn_banks.7.k_templates": "pytorch_model-00003-of-00004.bin",
47
+ "model.attn_banks.7.q_templates": "pytorch_model-00003-of-00004.bin",
48
+ "model.attn_banks.7.v_templates": "pytorch_model-00003-of-00004.bin",
49
+ "model.attn_banks.8.k_templates": "pytorch_model-00003-of-00004.bin",
50
+ "model.attn_banks.8.q_templates": "pytorch_model-00003-of-00004.bin",
51
+ "model.attn_banks.8.v_templates": "pytorch_model-00003-of-00004.bin",
52
+ "model.attn_banks.9.k_templates": "pytorch_model-00003-of-00004.bin",
53
+ "model.attn_banks.9.q_templates": "pytorch_model-00003-of-00004.bin",
54
+ "model.attn_banks.9.v_templates": "pytorch_model-00003-of-00004.bin",
55
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
56
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
57
+ "model.layers.0.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
58
+ "model.layers.0.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
59
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
60
+ "model.layers.0.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
61
+ "model.layers.0.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
62
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
63
+ "model.layers.0.self_attn.bank.k_templates": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.0.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.0.self_attn.bank.v_templates": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.0.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
67
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
68
+ "model.layers.0.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
69
+ "model.layers.0.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
70
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
71
+ "model.layers.1.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
72
+ "model.layers.1.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
73
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
74
+ "model.layers.1.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
75
+ "model.layers.1.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
76
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
77
+ "model.layers.1.self_attn.bank.k_templates": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.1.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.1.self_attn.bank.v_templates": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.1.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
81
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
82
+ "model.layers.1.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
83
+ "model.layers.1.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
84
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
85
+ "model.layers.10.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
86
+ "model.layers.10.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
87
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
88
+ "model.layers.10.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
89
+ "model.layers.10.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
90
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
91
+ "model.layers.10.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
92
+ "model.layers.10.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
93
+ "model.layers.10.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
94
+ "model.layers.10.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
95
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
96
+ "model.layers.10.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
97
+ "model.layers.10.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
98
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
99
+ "model.layers.11.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
100
+ "model.layers.11.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
101
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
102
+ "model.layers.11.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
103
+ "model.layers.11.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
104
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
105
+ "model.layers.11.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
106
+ "model.layers.11.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
107
+ "model.layers.11.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
108
+ "model.layers.11.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
109
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
110
+ "model.layers.11.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
111
+ "model.layers.11.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
112
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
113
+ "model.layers.12.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
114
+ "model.layers.12.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
115
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
116
+ "model.layers.12.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
117
+ "model.layers.12.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
118
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
119
+ "model.layers.12.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
120
+ "model.layers.12.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
121
+ "model.layers.12.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
122
+ "model.layers.12.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
123
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
124
+ "model.layers.12.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
125
+ "model.layers.12.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.13.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
128
+ "model.layers.13.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
129
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.13.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
131
+ "model.layers.13.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
132
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.13.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
134
+ "model.layers.13.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.13.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.13.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.13.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.13.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.14.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
142
+ "model.layers.14.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
143
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.14.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.14.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.14.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.14.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.14.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.14.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.14.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.14.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.15.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
156
+ "model.layers.15.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
157
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.15.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.15.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.15.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.15.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.15.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.15.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.15.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.15.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.16.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
170
+ "model.layers.16.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
171
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.16.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.16.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.16.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.16.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.16.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.16.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.16.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.16.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.17.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
184
+ "model.layers.17.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
185
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.17.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.17.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.17.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.17.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.17.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.17.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.17.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.17.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.18.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
198
+ "model.layers.18.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
199
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.18.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.18.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.18.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.18.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.18.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.18.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.18.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.18.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.19.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
212
+ "model.layers.19.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
213
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.19.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.19.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.19.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.19.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.19.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.19.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.19.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.19.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.2.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
226
+ "model.layers.2.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
227
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.2.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.2.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.2.self_attn.bank.k_templates": "pytorch_model-00002-of-00004.bin",
232
+ "model.layers.2.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
233
+ "model.layers.2.self_attn.bank.v_templates": "pytorch_model-00002-of-00004.bin",
234
+ "model.layers.2.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.2.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.2.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
239
+ "model.layers.20.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
240
+ "model.layers.20.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
241
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
242
+ "model.layers.20.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.20.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
245
+ "model.layers.20.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.20.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.20.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.20.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.20.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.20.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
253
+ "model.layers.21.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
254
+ "model.layers.21.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
255
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
256
+ "model.layers.21.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
257
+ "model.layers.21.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
258
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
259
+ "model.layers.21.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.21.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
261
+ "model.layers.21.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
262
+ "model.layers.21.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
263
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
264
+ "model.layers.21.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
265
+ "model.layers.21.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
266
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
267
+ "model.layers.22.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
268
+ "model.layers.22.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
269
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
270
+ "model.layers.22.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
271
+ "model.layers.22.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
272
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
273
+ "model.layers.22.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
274
+ "model.layers.22.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
275
+ "model.layers.22.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
276
+ "model.layers.22.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
277
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
278
+ "model.layers.22.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
279
+ "model.layers.22.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
280
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
281
+ "model.layers.23.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
282
+ "model.layers.23.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
283
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
284
+ "model.layers.23.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
285
+ "model.layers.23.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
286
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
287
+ "model.layers.23.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
288
+ "model.layers.23.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
289
+ "model.layers.23.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
290
+ "model.layers.23.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
291
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
292
+ "model.layers.23.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
293
+ "model.layers.23.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
294
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
295
+ "model.layers.24.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
296
+ "model.layers.24.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
297
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
298
+ "model.layers.24.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
299
+ "model.layers.24.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
300
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
301
+ "model.layers.24.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
302
+ "model.layers.24.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
303
+ "model.layers.24.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
304
+ "model.layers.24.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
305
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
306
+ "model.layers.24.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
307
+ "model.layers.24.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
308
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
309
+ "model.layers.25.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
310
+ "model.layers.25.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
311
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
312
+ "model.layers.25.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
313
+ "model.layers.25.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
314
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
315
+ "model.layers.25.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
316
+ "model.layers.25.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
317
+ "model.layers.25.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
318
+ "model.layers.25.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
319
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
320
+ "model.layers.25.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
321
+ "model.layers.25.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
322
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
323
+ "model.layers.26.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
324
+ "model.layers.26.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
325
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
326
+ "model.layers.26.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
327
+ "model.layers.26.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
328
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
329
+ "model.layers.26.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
330
+ "model.layers.26.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
331
+ "model.layers.26.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
332
+ "model.layers.26.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
333
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
334
+ "model.layers.26.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
335
+ "model.layers.26.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
336
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
337
+ "model.layers.27.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
338
+ "model.layers.27.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
339
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
340
+ "model.layers.27.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
341
+ "model.layers.27.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
342
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
343
+ "model.layers.27.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
344
+ "model.layers.27.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
345
+ "model.layers.27.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
346
+ "model.layers.27.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
347
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
348
+ "model.layers.27.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
349
+ "model.layers.27.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
350
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
351
+ "model.layers.28.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
352
+ "model.layers.28.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
353
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
354
+ "model.layers.28.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
355
+ "model.layers.28.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
356
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
357
+ "model.layers.28.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
358
+ "model.layers.28.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
359
+ "model.layers.28.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
360
+ "model.layers.28.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
361
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
362
+ "model.layers.28.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
363
+ "model.layers.28.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
364
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
365
+ "model.layers.29.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
366
+ "model.layers.29.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
367
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
368
+ "model.layers.29.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
369
+ "model.layers.29.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
370
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
371
+ "model.layers.29.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
372
+ "model.layers.29.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
373
+ "model.layers.29.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
374
+ "model.layers.29.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
375
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
376
+ "model.layers.29.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
377
+ "model.layers.29.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
378
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
379
+ "model.layers.3.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
380
+ "model.layers.3.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
381
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
382
+ "model.layers.3.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
383
+ "model.layers.3.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
384
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
385
+ "model.layers.3.self_attn.bank.k_templates": "pytorch_model-00002-of-00004.bin",
386
+ "model.layers.3.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
387
+ "model.layers.3.self_attn.bank.v_templates": "pytorch_model-00002-of-00004.bin",
388
+ "model.layers.3.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
389
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
390
+ "model.layers.3.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
391
+ "model.layers.3.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
392
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
393
+ "model.layers.30.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
394
+ "model.layers.30.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
395
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
396
+ "model.layers.30.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
397
+ "model.layers.30.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
398
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
399
+ "model.layers.30.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
400
+ "model.layers.30.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
401
+ "model.layers.30.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
402
+ "model.layers.30.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
403
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
404
+ "model.layers.30.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
405
+ "model.layers.30.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
406
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
407
+ "model.layers.31.mlp.bank.gate_templates": "pytorch_model-00002-of-00004.bin",
408
+ "model.layers.31.mlp.bank.up_templates": "pytorch_model-00002-of-00004.bin",
409
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
410
+ "model.layers.31.mlp.gate_coefficients": "pytorch_model-00004-of-00004.bin",
411
+ "model.layers.31.mlp.up_coefficients": "pytorch_model-00004-of-00004.bin",
412
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
413
+ "model.layers.31.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
414
+ "model.layers.31.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
415
+ "model.layers.31.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
416
+ "model.layers.31.self_attn.k_coefficients": "pytorch_model-00004-of-00004.bin",
417
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
418
+ "model.layers.31.self_attn.q_coefficients": "pytorch_model-00004-of-00004.bin",
419
+ "model.layers.31.self_attn.v_coefficients": "pytorch_model-00004-of-00004.bin",
420
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
421
+ "model.layers.4.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
422
+ "model.layers.4.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
423
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
424
+ "model.layers.4.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
425
+ "model.layers.4.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
426
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
427
+ "model.layers.4.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
428
+ "model.layers.4.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
429
+ "model.layers.4.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
430
+ "model.layers.4.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
431
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
432
+ "model.layers.4.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
433
+ "model.layers.4.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
434
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
435
+ "model.layers.5.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
436
+ "model.layers.5.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
437
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
438
+ "model.layers.5.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
439
+ "model.layers.5.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
440
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
441
+ "model.layers.5.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
442
+ "model.layers.5.self_attn.bank.q_templates": "pytorch_model-00002-of-00004.bin",
443
+ "model.layers.5.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
444
+ "model.layers.5.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
445
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
446
+ "model.layers.5.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
447
+ "model.layers.5.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
448
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
449
+ "model.layers.6.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
450
+ "model.layers.6.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
451
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
452
+ "model.layers.6.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
453
+ "model.layers.6.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
454
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
455
+ "model.layers.6.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
456
+ "model.layers.6.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
457
+ "model.layers.6.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
458
+ "model.layers.6.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
459
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
460
+ "model.layers.6.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
461
+ "model.layers.6.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
462
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
463
+ "model.layers.7.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
464
+ "model.layers.7.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
465
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
466
+ "model.layers.7.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
467
+ "model.layers.7.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
468
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
469
+ "model.layers.7.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
470
+ "model.layers.7.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
471
+ "model.layers.7.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
472
+ "model.layers.7.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
473
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
474
+ "model.layers.7.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
475
+ "model.layers.7.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
476
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
477
+ "model.layers.8.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
478
+ "model.layers.8.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
479
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
480
+ "model.layers.8.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
481
+ "model.layers.8.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
482
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
483
+ "model.layers.8.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
484
+ "model.layers.8.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
485
+ "model.layers.8.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
486
+ "model.layers.8.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
487
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
488
+ "model.layers.8.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
489
+ "model.layers.8.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
490
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
491
+ "model.layers.9.mlp.bank.gate_templates": "pytorch_model-00001-of-00004.bin",
492
+ "model.layers.9.mlp.bank.up_templates": "pytorch_model-00001-of-00004.bin",
493
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
494
+ "model.layers.9.mlp.gate_coefficients": "pytorch_model-00003-of-00004.bin",
495
+ "model.layers.9.mlp.up_coefficients": "pytorch_model-00003-of-00004.bin",
496
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
497
+ "model.layers.9.self_attn.bank.k_templates": "pytorch_model-00003-of-00004.bin",
498
+ "model.layers.9.self_attn.bank.q_templates": "pytorch_model-00003-of-00004.bin",
499
+ "model.layers.9.self_attn.bank.v_templates": "pytorch_model-00003-of-00004.bin",
500
+ "model.layers.9.self_attn.k_coefficients": "pytorch_model-00003-of-00004.bin",
501
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
502
+ "model.layers.9.self_attn.q_coefficients": "pytorch_model-00003-of-00004.bin",
503
+ "model.layers.9.self_attn.v_coefficients": "pytorch_model-00003-of-00004.bin",
504
+ "model.mlp_banks.0.gate_templates": "pytorch_model-00001-of-00004.bin",
505
+ "model.mlp_banks.0.up_templates": "pytorch_model-00001-of-00004.bin",
506
+ "model.mlp_banks.1.gate_templates": "pytorch_model-00001-of-00004.bin",
507
+ "model.mlp_banks.1.up_templates": "pytorch_model-00001-of-00004.bin",
508
+ "model.mlp_banks.10.gate_templates": "pytorch_model-00002-of-00004.bin",
509
+ "model.mlp_banks.10.up_templates": "pytorch_model-00002-of-00004.bin",
510
+ "model.mlp_banks.11.gate_templates": "pytorch_model-00002-of-00004.bin",
511
+ "model.mlp_banks.11.up_templates": "pytorch_model-00002-of-00004.bin",
512
+ "model.mlp_banks.12.gate_templates": "pytorch_model-00002-of-00004.bin",
513
+ "model.mlp_banks.12.up_templates": "pytorch_model-00002-of-00004.bin",
514
+ "model.mlp_banks.13.gate_templates": "pytorch_model-00002-of-00004.bin",
515
+ "model.mlp_banks.13.up_templates": "pytorch_model-00002-of-00004.bin",
516
+ "model.mlp_banks.14.gate_templates": "pytorch_model-00002-of-00004.bin",
517
+ "model.mlp_banks.14.up_templates": "pytorch_model-00002-of-00004.bin",
518
+ "model.mlp_banks.15.gate_templates": "pytorch_model-00002-of-00004.bin",
519
+ "model.mlp_banks.15.up_templates": "pytorch_model-00002-of-00004.bin",
520
+ "model.mlp_banks.2.gate_templates": "pytorch_model-00001-of-00004.bin",
521
+ "model.mlp_banks.2.up_templates": "pytorch_model-00001-of-00004.bin",
522
+ "model.mlp_banks.3.gate_templates": "pytorch_model-00001-of-00004.bin",
523
+ "model.mlp_banks.3.up_templates": "pytorch_model-00001-of-00004.bin",
524
+ "model.mlp_banks.4.gate_templates": "pytorch_model-00001-of-00004.bin",
525
+ "model.mlp_banks.4.up_templates": "pytorch_model-00001-of-00004.bin",
526
+ "model.mlp_banks.5.gate_templates": "pytorch_model-00001-of-00004.bin",
527
+ "model.mlp_banks.5.up_templates": "pytorch_model-00001-of-00004.bin",
528
+ "model.mlp_banks.6.gate_templates": "pytorch_model-00001-of-00004.bin",
529
+ "model.mlp_banks.6.up_templates": "pytorch_model-00001-of-00004.bin",
530
+ "model.mlp_banks.7.gate_templates": "pytorch_model-00002-of-00004.bin",
531
+ "model.mlp_banks.7.up_templates": "pytorch_model-00002-of-00004.bin",
532
+ "model.mlp_banks.8.gate_templates": "pytorch_model-00002-of-00004.bin",
533
+ "model.mlp_banks.8.up_templates": "pytorch_model-00002-of-00004.bin",
534
+ "model.mlp_banks.9.gate_templates": "pytorch_model-00002-of-00004.bin",
535
+ "model.mlp_banks.9.up_templates": "pytorch_model-00002-of-00004.bin",
536
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
537
+ }
538
+ }