qingy2024 commited on
Commit
afa6aa6
·
verified ·
1 Parent(s): fb3202f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - tiiuae/Falcon3-10B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [tiiuae/Falcon3-10B-Instruct](https://huggingface.co/tiiuae/Falcon3-10B-Instruct)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - layer_range: [0, 10]
32
+ model: tiiuae/Falcon3-10B-Instruct
33
+ - sources:
34
+ - layer_range: [5, 15]
35
+ model: tiiuae/Falcon3-10B-Instruct
36
+ - sources:
37
+ - layer_range: [10, 20]
38
+ model: tiiuae/Falcon3-10B-Instruct
39
+ - sources:
40
+ - layer_range: [15, 25]
41
+ model: tiiuae/Falcon3-10B-Instruct
42
+ - sources:
43
+ - layer_range: [20, 30]
44
+ model: tiiuae/Falcon3-10B-Instruct
45
+ - sources:
46
+ - layer_range: [25, 35]
47
+ model: tiiuae/Falcon3-10B-Instruct
48
+ - sources:
49
+ - layer_range: [30, 40]
50
+ model: tiiuae/Falcon3-10B-Instruct
51
+ merge_method: passthrough
52
+ dtype: float16
53
+
54
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/Falcon3-10B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 11,
9
+ "eos_token_id": 11,
10
+ "head_dim": 256,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 23040,
15
+ "max_position_embeddings": 32768,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 70,
20
+ "num_key_value_heads": 4,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000042,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.46.2",
28
+ "use_cache": true,
29
+ "vocab_size": 131072
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - layer_range: [0, 10]
4
+ model: tiiuae/Falcon3-10B-Instruct
5
+ - sources:
6
+ - layer_range: [5, 15]
7
+ model: tiiuae/Falcon3-10B-Instruct
8
+ - sources:
9
+ - layer_range: [10, 20]
10
+ model: tiiuae/Falcon3-10B-Instruct
11
+ - sources:
12
+ - layer_range: [15, 25]
13
+ model: tiiuae/Falcon3-10B-Instruct
14
+ - sources:
15
+ - layer_range: [20, 30]
16
+ model: tiiuae/Falcon3-10B-Instruct
17
+ - sources:
18
+ - layer_range: [25, 35]
19
+ model: tiiuae/Falcon3-10B-Instruct
20
+ - sources:
21
+ - layer_range: [30, 40]
22
+ model: tiiuae/Falcon3-10B-Instruct
23
+ merge_method: passthrough
24
+ dtype: float16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2ba30b9913ca041ba2c1938cdbf195eda59425c099881422a6ca402ff8dc82
3
+ size 4885408632
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fb0ad53971da3eff4fe87bbc77cdcf92c2c88fc195b914e5488f39ae34a069
3
+ size 4891740456
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2a13fd177d712de8e590ef5de13918a2f0de362b080713f41a04a2c1aa7484
3
+ size 4942085064
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d85bfeb9d6f7ece0f323e75090eeda442197d0b48d6a8481f111785be002f1e
3
+ size 4891740456
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c811b5f1e0666fc16ec0e0f0bcbd8c188980af20c77603e21b00628bc148ae93
3
+ size 4942085064
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d90d7af062b38115dfcf1d04832b5019843296370a6047a6eee40525c105cd
3
+ size 4891734200
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec4efbe3d42f2d797955ba5cc6cc389229a46d6436dcd8e38e22562ecf4ea1d
3
+ size 4891746648
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d8caa754ae75f0f9514ed1b316453a14d842167751ce64e8f6581ac7ced423
3
+ size 525356616
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 34861824000}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.56.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.62.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.57.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.59.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.69.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>EMAIL_ADDRESS<<",
12
+ ">>IP_ADDRESS<<",
13
+ "<|startoftext|>",
14
+ ">>IP_ADDRESS_0<<",
15
+ ">>IP_ADDRESS_1<<",
16
+ ">>IP_ADDRESS_2<<",
17
+ ">>IP_ADDRESS_3<<",
18
+ ">>IP_ADDRESS_4<<",
19
+ ">>IP_ADDRESS_5<<",
20
+ ">>IP_ADDRESS_6<<",
21
+ ">>IP_ADDRESS_7<<",
22
+ ">>IP_ADDRESS_8<<",
23
+ ">>IP_ADDRESS_9<<",
24
+ ">>PASSWORD<<",
25
+ ">>KEY<<"
26
+ ],
27
+ "eos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<|pad|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff