llmixer commited on
Commit
d3dfc93
1 Parent(s): 7eb9666

Model upload

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llmixer/BigWeave-v12-90b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 102,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
model-00001-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29746674bc1d39057bf04b3aa8bd788ef5bd5eadd4848a7653ba7e033a24cd89
3
+ size 9852622800
model-00002-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4d22e10a999ca53729edd6b57d6dff22b26e631acd539f19dc0d5ce4c6ddcd
3
+ size 9680639176
model-00003-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68837a48f2baab1fb139b7570417192e84c4846e8c0407b119d906581429ab66
3
+ size 9932331248
model-00004-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01310a7b7f104be99ae6bf611cb02ac64f32738357d11227f075f6dc3daf2c6
3
+ size 9647052248
model-00005-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644a8af9bfa2dd23245356427ced3c8314d93273c68bb73276bed2ff7918c371
3
+ size 9798096912
model-00006-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef93ca9f1401f6ffa53d530c63eacafdacfb6bbe7e426d838722cf839378486
3
+ size 9798096912
model-00007-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50382c54f66bf8851468867fb47c0145a617ac754aec16d14b5e25e0d16db659
3
+ size 9982629568
model-00008-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a6697076973af7bdbe0014e17efbe5a5e1dd219feabdad0bb4eb48f1e67898
3
+ size 9781303080
model-00009-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84def3ab5fd607627c7493260a3840eef541fc3a55e284f8297b34224a314d84
3
+ size 9798096912
model-00010-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90baebd635d4c2ba7dd5394d066d881b06914f808b2aa7a7fe6abe8eebabe60d
3
+ size 9798096912
model-00011-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826b5714de4a1eaedb78d458f49897fcb75beacde88065fbf6697883698aa416
3
+ size 9982646056
model-00012-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81de0d88bdeef08fe205f5d46523490854fbd3f9e75b1d1d86a763587cfd551
3
+ size 9630291408
model-00013-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ff45b047bbc221af97b8e1d892fd56b15f6fe63921deafdc1595ccdbe37992
3
+ size 9663879072
model-00014-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c3c46a88ebe06bbfcb53636cf679cf03e1fed4b6a823845c893e0a9be89cb1
3
+ size 9781303080
model-00015-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a524850537266c03d96c3cf4a07ef61ab18ebedf04461ed7b5f343311686ae
3
+ size 9798096904
model-00016-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e5199ee0068edf8902ae56350847f4d1dd5eca1a5b2f125ab00454a326db3c
3
+ size 9982629552
model-00017-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c89dd2622c4ba8f1d68c1e18b95e6d871fdc1ac9d55aaca7743eca35841748d
3
+ size 9613547768
model-00018-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a0ee6f05d0e31ecb2f80bb6d38ca5cb17c4d6e2d187b3e9b13a78cfe82fc58
3
+ size 9080837328
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.51.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.57.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.61.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.67.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.68.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.71.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.66.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.74.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.77.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.86.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.80.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.89.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.83.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.91.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.97.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "lm_head.weight": "model-00018-of-00018.safetensors", "model.layers.100.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.norm.weight": "model-00018-of-00018.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": false,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": null,
41
+ "sp_model_kwargs": {},
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": true
45
+ }