matchaaaaa commited on
Commit
2b55be8
1 Parent(s): 3ecafb9

Upload 23 files

Browse files
README.md CHANGED
@@ -1,3 +1,42 @@
1
  ---
2
- license: cc-by-nc-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
  ---
9
+ # Chaifighter-20B-v2.1
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
+ * D:/MLnonsense/models/SanjiWatsuki_Kunoichi-7B
22
+ * mega\Mytho-Lemon-11B
23
+ * D:/MLnonsense/models/Sao10K_Fimbulvetr-11B-v2.1-16K
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+ dtype: float32
31
+ merge_method: passthrough
32
+ slices:
33
+ - sources:
34
+ - layer_range: [0, 40]
35
+ model: D:/MLnonsense/models/Sao10K_Fimbulvetr-11B-v2.1-16K
36
+ - sources:
37
+ - layer_range: [8, 16]
38
+ model: D:/MLnonsense/models/SanjiWatsuki_Kunoichi-7B
39
+ - sources:
40
+ - layer_range: [8, 48]
41
+ model: mega\Mytho-Lemon-11B
42
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "matchaaaaa/Chaifighter-20B-v2.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 88,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.42.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb2ac3a2f4cb433fc3438e4628a7221501be9c109ef320af4ac394bbb99dc15
3
+ size 4957835536
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77143511014921abadf4b772961e2ca31eef634bedd7ccec0912335b106c0fd4
3
+ size 4949431616
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74906546b72ed29460e4697eb3777d35ae3cbdca88a7b98db7fe34bb0d17b37f
3
+ size 4999813128
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e404884254165e311c66a4daacad4e82bf18c1426632eb64588d8da2ae1b34
3
+ size 4999829640
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac0699c919c5cbe9765cd3dce2e6065394c09c87221f001b5fd1d28b33f1fc1
3
+ size 4999780112
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89525f8614a442605c570196ed6f04431fd5b1e3b38a4388aac4816cca45af6d
3
+ size 4932737608
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5970d3344c24a9a5d717f0f74b9961c7b5fab1dad6353d631f3244988a424a6d
3
+ size 4999779672
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6636036095ba7baa684f63399b9d5dbdcc6780a1dcfa7819644ff0576d7488
3
+ size 4899116472
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431758f69ba4d510146e4797253fc61fac3fcb033fffa682f5ad0351b85dd0d7
3
+ size 4932737608
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4f1b6f3b0a41211e4120a10a0439d5df6f6689aca8f48dd73cd58740ae0eb1
3
+ size 4999779672
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5c78bf33407983cb9f292224a68ae908c7a41bf264d216bdada7265d22737f
3
+ size 4899116472
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87596d187a86e65329b0274219c3deae0b2d32786229e36cd26dd23e396ef256
3
+ size 4999813128
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edaa7bb0e178173d0b2dbc5b3602c0021767fbe5ea5b77d6ee6564add3b41bff
3
+ size 4999813128
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f266bdc9dee46567beb8b88aaf3c581ea8c068cd80cc08689346ea6ad909c87
3
+ size 4999796616
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23351e2531beb2109d3ab7b5f91bb2ce9484bc1a69a86461d1f54c6d6ceb76da
3
+ size 4899115976
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737ae0abf1b4a280cdb0c595843bd07c794b88c12f8a4b0f99ff92e298a16f29
3
+ size 3355612120
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 77824016384}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.45.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.46.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.47.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.40.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.41.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }