Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- AiCloser/Qwen2.5-32B-AGI
+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:
+* [AiCloser/Qwen2.5-32B-AGI](https://huggingface.co/AiCloser/Qwen2.5-32B-AGI)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - layer_range: [10, 16]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [18, 24]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [16, 32]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [24, 40]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [32, 48]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [40, 56]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [56, 64]
+    model: AiCloser/Qwen2.5-32B-AGI
+merge_method: passthrough
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "AiCloser/Qwen2.5-32B-AGI",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 84,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,24 @@
+slices:
+- sources:
+  - layer_range: [10, 16]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [18, 24]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [16, 32]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [24, 40]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [32, 48]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [40, 56]
+    model: AiCloser/Qwen2.5-32B-AGI
+- sources:
+  - layer_range: [56, 64]
+    model: AiCloser/Qwen2.5-32B-AGI
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0d46b2a20cb0e0a693a9954edfca3008cf6d2d2502f707007564b19e5ee629
+size 4949338472

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccd66c32e2e96ac4876b67037afb5d912acd61c708b68cb8cc28d976ea12f47
+size 4991425928

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e928b142a70653c581ba3627571c462d575a48e459a3d07d39789e68a5639e8a
+size 4876069736

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6382bb00246a75cd239a0bfec491f5ac76cd065aa336294566d4c2bc0cc982
+size 4750194424

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad2d7b0b2fd2ce9426add8ced568d5a3e11ba6240df5c4ee0b736b713813cd0
+size 4991417800

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c7efb8c64e3e500a4606d04917a74ce6e5848e19837a0a09ec55e9290229b0
+size 4760701016

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170b810bb8bf83fa76dec90914e3e457ff9c8f548f5525529cde888a1d8d8e1a
+size 4991417800

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4804f8ff1756a887806d87bd8cfb6fd0c0fa4d43f60a2ea3d20d067c623a6e2
+size 4760701016

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a887373c46fa85435e9a133d49cc94edbf841dcb0374712908fb560adaf9c
+size 4991417800

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb992ad6682edc97cf1f5c4c3655994621acba9fe2e1045acaf585329e359f1
+size 4760701016

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71696487b19452f7bde212334c9e0c21f94f7c7dcefac0baa071dbad6036a36b
+size 4991417800

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4dc181d83fe8ba56fdb2db8b7a210402cf09a76f67f8307d45aa52bb44b670
+size 4760701016

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5505f39a697516edae73d80c6f574ded8b376a77108b73f0274524a3f50fe826
+size 4991417800

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbcdb0e2141fc2f2322f11f6a9282856bdb4d9eb3bbf8f23790130db89be50a
+size 4760701016

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79945ba2b5d721b63dc399e0cb34fe5f7d93d170a54ec4eb8eb44570e22a895e
+size 4991417800

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0452aece1a0ad90be9662cc056281d90f3ebcf7df2339f1273ab1a635ec3e8a
+size 4886555632

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c431e6d6ded76999572b7bc0f8c6091ab011943ec3c8e2c6ece974203d4142db
+size 4876059408

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494ee5681557810c3ae0094c82afa33b8fb438a707140c159ceb355abddfee2d
+size 1950423752

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 85031962624}, "weight_map": {"lm_head.weight": "model-00001-of-00018.safetensors", "model.embed_tokens.weight": "model-00001-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00018.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00018.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.39.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.42.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.43.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.57.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.58.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.59.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.77.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.82.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00018-of-00018.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00018-of-00018.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.norm.weight": "model-00018-of-00018.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}