DavidAU commited on
Commit
366bd53
1 Parent(s): 0f3141e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # Nemo-Grand-Gutenburg3
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the passthrough merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * G:/11B/Lyra4-Gutenberg-12B
22
+ * G:/11B/Lyra-Gutenberg-mistral-nemo-12B
23
+ * G:/11B/mistral-nemo-gutenberg-12B-v4
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ # NEMO-Mistral version -> Scaled to 40 layers.
31
+
32
+ # fix one ->
33
+ # Fix 3 point double match @ layers 14,15 all 3 models (remove 2 layers)
34
+
35
+ # fix 2 ?? - restored fix 1,
36
+ # 30-31 -> all models 2nd group.
37
+
38
+ # Fix 3??
39
+ # 36-39 -> second last block.
40
+
41
+ slices:
42
+ - sources:
43
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
44
+ layer_range: [0, 16]
45
+ - sources:
46
+ - model: G:/11B/Lyra4-Gutenberg-12B
47
+ layer_range: [12, 24]
48
+ - sources:
49
+ - model: G:/11B/Lyra-Gutenberg-mistral-nemo-12B
50
+ layer_range: [14, 28]
51
+
52
+ # secondary block
53
+
54
+ - sources:
55
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
56
+ layer_range: [18, 30] # remove layer 30
57
+ - sources:
58
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
59
+ layer_range: [31, 32] # remove layer 30
60
+ - sources:
61
+ - model: G:/11B/Lyra4-Gutenberg-12B
62
+ layer_range: [24, 31] # remove layer 31
63
+ - sources:
64
+ - model: G:/11B/Lyra4-Gutenberg-12B
65
+ layer_range: [32, 39] # remove layer 31
66
+ - sources:
67
+ - model: G:/11B/Lyra-Gutenberg-mistral-nemo-12B
68
+ layer_range: [30, 40]
69
+ merge_method: passthrough
70
+ dtype: bfloat16
71
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "G:/11B/Lyra4-Gutenberg-12B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 79,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.43.3",
25
+ "use_cache": false,
26
+ "vocab_size": 131072
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # NEMO-Mistral version -> Scaled to 40 layers.
2
+
3
+ # fix one ->
4
+ # Fix 3 point double match @ layers 14,15 all 3 models (remove 2 layers)
5
+
6
+ # fix 2 ?? - restored fix 1,
7
+ # 30-31 -> all models 2nd group.
8
+
9
+ # Fix 3??
10
+ # 36-39 -> second last block.
11
+
12
+ slices:
13
+ - sources:
14
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
15
+ layer_range: [0, 16]
16
+ - sources:
17
+ - model: G:/11B/Lyra4-Gutenberg-12B
18
+ layer_range: [12, 24]
19
+ - sources:
20
+ - model: G:/11B/Lyra-Gutenberg-mistral-nemo-12B
21
+ layer_range: [14, 28]
22
+
23
+ # secondary block
24
+
25
+ - sources:
26
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
27
+ layer_range: [18, 30] # remove layer 30
28
+ - sources:
29
+ - model: G:/11B/mistral-nemo-gutenberg-12B-v4
30
+ layer_range: [31, 32] # remove layer 30
31
+ - sources:
32
+ - model: G:/11B/Lyra4-Gutenberg-12B
33
+ layer_range: [24, 31] # remove layer 31
34
+ - sources:
35
+ - model: G:/11B/Lyra4-Gutenberg-12B
36
+ layer_range: [32, 39] # remove layer 31
37
+ - sources:
38
+ - model: G:/11B/Lyra-Gutenberg-mistral-nemo-12B
39
+ layer_range: [30, 40]
40
+ merge_method: passthrough
41
+ dtype: bfloat16
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 45761484800}, "weight_map": {"lm_head.weight": "model-00001-of-00048.safetensors", "model.embed_tokens.weight": "model-00002-of-00048.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00048.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00048.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00048.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00048.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00048.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00048.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00048.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00048.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00048.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00048.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00048.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00048.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00048.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00048.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00048.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00048.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00048.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00048.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00048.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00048.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00048.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00048.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00048.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00048.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00048.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00048.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00048.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00048.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00048.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00048.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00048.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00048.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00048.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00048.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00048.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00048.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00048.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00048.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00048.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00048.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00048.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00048.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00048.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00048.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00048.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00048.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00048.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00048.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00048.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00048.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00048.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00048.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00048.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00048.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00048.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00048.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00010-of-00048.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00048.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00048.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00048.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00048.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00048.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00048.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00048.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00048.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00048.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00048.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00048.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00011-of-00048.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00048.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00048.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00048.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00011-of-00048.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00048.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00048.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00048.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00048.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00048.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00048.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00048.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00048.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00048.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00048.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00048.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00012-of-00048.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00048.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.42.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00013-of-00048.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00048.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00048.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00048.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00048.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00048.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00014-of-00048.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00048.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00048.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00048.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00048.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00048.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00048.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00048.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00048.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00048.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00048.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00048.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00048.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00048.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00015-of-00048.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00048.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00048.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00048.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00048.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00048.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00016-of-00048.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00016-of-00048.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00048.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00048.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00048.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00048.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00048.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00048.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00048.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00048.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00048.safetensors", "model.layers.2.input_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00016-of-00048.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00017-of-00048.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00017-of-00048.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00017-of-00048.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00017-of-00048.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00017-of-00048.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00048.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00048.safetensors", "model.layers.24.input_layernorm.weight": "model-00017-of-00048.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00048.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00048.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00017-of-00048.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00048.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00048.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00018-of-00048.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00018-of-00048.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00018-of-00048.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00018-of-00048.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00048.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00018-of-00048.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00048.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00048.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00048.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00048.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00048.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00048.safetensors", "model.layers.25.input_layernorm.weight": "model-00019-of-00048.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00048.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00048.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00019-of-00048.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00048.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00048.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00019-of-00048.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00020-of-00048.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00020-of-00048.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00020-of-00048.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", "model.layers.46.input_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.36.input_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.26.input_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00048.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00021-of-00048.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00021-of-00048.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00048.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00048.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00048.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00021-of-00048.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00048.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00048.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", "model.layers.47.input_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.37.input_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00022-of-00048.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00022-of-00048.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00048.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00023-of-00048.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00023-of-00048.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00048.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00023-of-00048.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00023-of-00048.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00024-of-00048.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", "model.layers.55.input_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.48.input_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.38.input_layernorm.weight": "model-00024-of-00048.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00024-of-00048.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00024-of-00048.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00024-of-00048.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00048.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00025-of-00048.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00025-of-00048.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00025-of-00048.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00025-of-00048.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00025-of-00048.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00048.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00025-of-00048.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00025-of-00048.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00026-of-00048.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00026-of-00048.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00026-of-00048.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00048.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00026-of-00048.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00026-of-00048.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00026-of-00048.safetensors", "model.layers.56.input_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.49.input_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.39.input_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00026-of-00048.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00026-of-00048.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00026-of-00048.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00026-of-00048.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00048.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00027-of-00048.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00027-of-00048.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00027-of-00048.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00027-of-00048.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", "model.layers.57.input_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.50.input_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.40.input_layernorm.weight": "model-00027-of-00048.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00028-of-00048.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00028-of-00048.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00028-of-00048.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00028-of-00048.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00028-of-00048.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00028-of-00048.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00029-of-00048.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00029-of-00048.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00029-of-00048.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", "model.layers.58.input_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.51.input_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.41.input_layernorm.weight": "model-00029-of-00048.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00029-of-00048.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00030-of-00048.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00030-of-00048.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00030-of-00048.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00048.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00048.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00030-of-00048.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00031-of-00048.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00031-of-00048.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", "model.layers.59.input_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.52.input_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00031-of-00048.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00031-of-00048.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00032-of-00048.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00032-of-00048.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", "model.layers.60.input_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.53.input_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00032-of-00048.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00033-of-00048.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00033-of-00048.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00033-of-00048.safetensors", "model.layers.3.input_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00034-of-00048.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00034-of-00048.safetensors", "model.layers.69.input_layernorm.weight": "model-00034-of-00048.safetensors", "model.layers.61.input_layernorm.weight": "model-00034-of-00048.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00034-of-00048.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00034-of-00048.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00034-of-00048.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00035-of-00048.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00035-of-00048.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00035-of-00048.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00035-of-00048.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00035-of-00048.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00035-of-00048.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00035-of-00048.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00035-of-00048.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00035-of-00048.safetensors", "model.layers.70.input_layernorm.weight": "model-00035-of-00048.safetensors", "model.layers.54.input_layernorm.weight": "model-00035-of-00048.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00035-of-00048.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00035-of-00048.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00036-of-00048.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00036-of-00048.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", "model.layers.71.input_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.62.input_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00036-of-00048.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00037-of-00048.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00037-of-00048.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00037-of-00048.safetensors", "model.layers.72.input_layernorm.weight": "model-00037-of-00048.safetensors", "model.layers.63.input_layernorm.weight": "model-00037-of-00048.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00038-of-00048.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00038-of-00048.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00038-of-00048.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00038-of-00048.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00038-of-00048.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00038-of-00048.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00039-of-00048.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00039-of-00048.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00039-of-00048.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00039-of-00048.safetensors", "model.layers.73.input_layernorm.weight": "model-00039-of-00048.safetensors", "model.layers.64.input_layernorm.weight": "model-00039-of-00048.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00039-of-00048.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00039-of-00048.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00039-of-00048.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00039-of-00048.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00039-of-00048.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00039-of-00048.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00039-of-00048.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00040-of-00048.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", "model.layers.74.input_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.65.input_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00040-of-00048.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00040-of-00048.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00040-of-00048.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00040-of-00048.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00040-of-00048.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00041-of-00048.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00041-of-00048.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00041-of-00048.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00041-of-00048.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00041-of-00048.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00041-of-00048.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00041-of-00048.safetensors", "model.layers.75.input_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.66.input_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00041-of-00048.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00041-of-00048.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00041-of-00048.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00041-of-00048.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00042-of-00048.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00042-of-00048.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00042-of-00048.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00042-of-00048.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00042-of-00048.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00042-of-00048.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00042-of-00048.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00042-of-00048.safetensors", "model.layers.76.input_layernorm.weight": "model-00042-of-00048.safetensors", "model.layers.67.input_layernorm.weight": "model-00042-of-00048.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00042-of-00048.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00042-of-00048.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00042-of-00048.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00043-of-00048.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00043-of-00048.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00043-of-00048.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00043-of-00048.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00043-of-00048.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00043-of-00048.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00043-of-00048.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00043-of-00048.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00043-of-00048.safetensors", "model.layers.77.input_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.68.input_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00043-of-00048.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00043-of-00048.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00044-of-00048.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00044-of-00048.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", "model.layers.78.input_layernorm.weight": "model-00044-of-00048.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00044-of-00048.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00045-of-00048.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00045-of-00048.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00045-of-00048.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00045-of-00048.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.input_layernorm.weight": "model-00045-of-00048.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00045-of-00048.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00045-of-00048.safetensors", "model.layers.5.input_layernorm.weight": "model-00045-of-00048.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00046-of-00048.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00046-of-00048.safetensors", "model.layers.6.input_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00046-of-00048.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00046-of-00048.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00046-of-00048.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00046-of-00048.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00047-of-00048.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.input_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00047-of-00048.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00047-of-00048.safetensors", "model.layers.8.input_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00047-of-00048.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00047-of-00048.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00048-of-00048.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00048-of-00048.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00048-of-00048.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00048-of-00048.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.input_layernorm.weight": "model-00048-of-00048.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00048-of-00048.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00048-of-00048.safetensors", "model.norm.weight": "model-00048-of-00048.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff