Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+base_model:
+- MaziyarPanahi/calme-2.4-rys-78b
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [MaziyarPanahi/calme-2.4-rys-78b](https://huggingface.co/MaziyarPanahi/calme-2.4-rys-78b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: MaziyarPanahi/calme-2.4-rys-78b
+      layer_range: [0, 39]
+  - sources:
+    - model: MaziyarPanahi/calme-2.4-rys-78b
+      layer_range: [8, 39]
+merge_method: passthrough
+dtype: float16
+
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "MaziyarPanahi/calme-2.4-rys-78b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 70,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: MaziyarPanahi/calme-2.4-rys-78b
+      layer_range: [0, 39]
+  - sources:
+    - model: MaziyarPanahi/calme-2.4-rys-78b
+      layer_range: [8, 39]
+merge_method: passthrough
+dtype: float16

model-00001-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91a15a9bed33520c4b2da36931044d8a0e6a239291bf76ae5bf45ebbec24a57
+size 4969152856

model-00002-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9447db4ed8dac7a7b5c5839c347a0036d11ee08f20cf240ae005530e4f818b
+size 4964084872

model-00003-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a495f0597583d055d913e2ebfc1b01630d73362485d2109bc1f7cba50447c6ef
+size 4997660376

model-00004-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e2e4e93a2938a81e3219380d28d5cf7cc03e55922d9d61517c1e7b1b8ab0b8
+size 4565680272

model-00005-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9a7645150c0bd50a8035412943b3591a77c525691e62dec0256f3b05aa1ec9
+size 4964068400

model-00006-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9f570faa864a445b45d558ea72b521f20213254ad99dde36e69080af3def3f
+size 4915904664

model-00007-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe90e43c6984a3a2bfb74f9210628be93cc18b5f848f3047521a6b67070099f3
+size 4647435984

model-00008-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51994e2ca98b91f5b2d7ed7ab15817ff072d1cb4a6904993951ccea7f391c4a
+size 4964068392

model-00009-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4002f5e3fbad1ceb012a3915ec0aa5554adcfd7d7b7233af6843096cc84fedc2
+size 4599255760

model-00010-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546c34e4e7ea83a5a21b23a04df8646613924afddcabd5379d85248b311522fd
+size 4964101384

model-00011-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528458bae6d7f60ee4f292b365af5c0c1b65d8e2f1b8d4cb7bfe383423758f87
+size 4781653832

model-00012-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896b56885429d2d228517368ddb476f74ab744e1f13b6d0667c4a33ca770d393
+size 4964068392

model-00013-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6f7f4edab7c1e836dce9912354078d0a16be934bac1644b548a32e76279d74
+size 4599272256

model-00014-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a68dd855a6c59f1224a89659ccd368c3e6cd8771bf241310cd57e7d6c59ebe6
+size 4964068400

model-00015-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71e8ee659f7ea17fbc6013c654aa15c7f6b3a2251f2a12dd1132be871a46002
+size 4997660376

model-00016-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb0ba2700e817b9a263d1d0c6e78682fe0310d8da1f92884eeabc3ac733363d
+size 4565680272

model-00017-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401671ace914e220a5ba94c4917538716383d00884128750317fe48002f5108b
+size 4781670320

model-00018-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b6bf5f67361479d892356f86d9c7fc92cca93556ca3546be287bb06e5a5087
+size 4964068400

model-00019-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c8414ce77fb5b6f854f815428a0911d89c1a8e0a4d9ab0e1d085d5ed348751
+size 4997660376

model-00020-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773e99cb6f2840a3d01b6c041901a947df1fe7a2350ebca6da7757d770ec45c5
+size 4565680272

model-00021-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca8a745b5893e42cd40ac65dbf41d769f248450b289510c257b48a02605f70f
+size 4964068400

model-00022-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf70a3552940265d6f339d41096907ce5cf698bd5bd9c060c844b17fe4a3197e
+size 4915904664

model-00023-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9d8c39bda5d2d822827ede3fbae7998df41900396bee79892e7002130e8f0e
+size 4647435984

model-00024-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea02dfe66fe4bd3d55424304a2e6a124490599af2266585f98a3db9a95e383a1
+size 4781653824

model-00025-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e24a9b95ca8c4f15fa3b738d88d87db4f284f792ce0a00d3c33df8b2fa2095a
+size 4781686776

model-00026-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291592d75b41d99a2c744dfeeba6e24015ef97f0d99b0954bf35561e487dd2db
+size 4964068384

model-00027-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a144ee5961829d090b90bd9ecaab8114b9f65302171942257433f3a69ca41269
+size 2057398496

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 127845015552}, "weight_map": {"lm_head.weight": "model-00001-of-00027.safetensors", "model.embed_tokens.weight": "model-00001-of-00027.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00027.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00027.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.21.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.24.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00027.safetensors", "model.layers.57.input_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.input_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.27.input_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.60.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.61.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00027.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.31.input_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.32.input_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.33.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.35.input_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.36.input_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.37.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.38.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00024-of-00027.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.39.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.8.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00026-of-00027.safetensors", "model.layers.40.input_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.9.input_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00027.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00027-of-00027.safetensors", "model.norm.weight": "model-00027-of-00027.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}