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 +1,61 @@
+---
+base_model:
+- MaziyarPanahi/calme-2.4-rys-78B
+- Sakalti/ultiima-78B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [Sakalti/ultiima-78B](https://huggingface.co/Sakalti/ultiima-78B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [MaziyarPanahi/calme-2.4-rys-78B](https://huggingface.co/MaziyarPanahi/calme-2.4-rys-78B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: della_linear
+base_model: Sakalti/ultiima-78B
+dtype: float16
+parameters:
+  epsilon: 0.015            # Fine-grain scaling for precision.
+  lambda: 1.6               # Strong emphasis on top-performing models.
+  normalize: true           # Stable parameter integration across models.
+adaptive_merge_parameters:
+  task_weights:
+    tinyArc: 1.75           # Logical reasoning.
+    tinyHellaswag: 1.65     # Contextual predictions.
+    tinyMMLU: 1.8           # Domain knowledge.
+    tinyTruthfulQA: 2.0     # Prioritize truthful reasoning.
+    tinyTruthfulQA_mc1: 1.85
+    tinyWinogrande: 1.9     # Advanced reasoning and predictions.
+    IFEval: 2.1             # Instruction-following and multitasking.
+    BBH: 1.9                # Complex reasoning.
+    MATH: 2.3               # Mathematical reasoning.
+    GPQA: 2.2             # Factual QA.
+    MUSR: 2.0             # Multi-step reasoning.
+    MMLU-PRO: 2.2       # Domain multitask performance.
+  smoothing_factor: 0.1     # Smooth blending across benchmarks.
+models:
+  - model: MaziyarPanahi/calme-2.4-rys-78B
+    parameters:
+      weight: 1
+      density: 1
+  - model: Sakalti/ultiima-78B
+    parameters:
+      weight: 1
+      density: 1
+```

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Sakalti/ultiima-78B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "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": "float16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,31 @@
+merge_method: della_linear
+base_model: Sakalti/ultiima-78B
+dtype: float16
+parameters:
+  epsilon: 0.015            # Fine-grain scaling for precision.
+  lambda: 1.6               # Strong emphasis on top-performing models.
+  normalize: true           # Stable parameter integration across models.
+adaptive_merge_parameters:
+  task_weights:
+    tinyArc: 1.75           # Logical reasoning.
+    tinyHellaswag: 1.65     # Contextual predictions.
+    tinyMMLU: 1.8           # Domain knowledge.
+    tinyTruthfulQA: 2.0     # Prioritize truthful reasoning.
+    tinyTruthfulQA_mc1: 1.85
+    tinyWinogrande: 1.9     # Advanced reasoning and predictions.
+    IFEval: 2.1             # Instruction-following and multitasking.
+    BBH: 1.9                # Complex reasoning.
+    MATH: 2.3               # Mathematical reasoning.
+    GPQA: 2.2             # Factual QA.
+    MUSR: 2.0             # Multi-step reasoning.
+    MMLU-PRO: 2.2       # Domain multitask performance.
+  smoothing_factor: 0.1     # Smooth blending across benchmarks.
+models:
+  - model: MaziyarPanahi/calme-2.4-rys-78B
+    parameters:
+      weight: 1
+      density: 1
+  - model: Sakalti/ultiima-78B
+    parameters:
+      weight: 1
+      density: 1

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3021cb8d3640f2b611f2c0bd11a9b088ce83bc5961e6044c4f5ce7a8c04b6330
+size 4969152856

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1769091e842e931596340135e383321c15a3797b95403f961e560b3917d091fe
+size 4980864368

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebdd457ff0d3b8c9de91135fc31810e3f6ee80f7fec6b8e5da3b24ecb1727e4
+size 4764874336

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe18edad9fd0f1d46cde1313b2ed5940eea9b112ab08b2f913a8ed98ac922ed5
+size 4781670320

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33592f85a488eb5eeec51bd13cfc9aeb7ad24a2b9f7989efccdff075f2e1d2a1
+size 4781670328

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff86964ebb15d8aea09e680a15a7bc4f49cfd5a9470f8f0864da08317aee685f
+size 4980864384

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3097b405534217b75e7369d04091a664d19973a676e1804440075ea3d07ede97
+size 4764874336

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a7f254b58daaedb0a5920a98c09506d97f8febd8bfeb3cfd7eac439d82a8b1
+size 4781670320

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8abe66b0fb0a0067014b4697d37bc1d38ab98d06270ce83a0a91d70692544f8
+size 4781670328

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6232a46a39cf80a5644099dc5535560353dbf8716e9768d1132f1d7b6fae508
+size 4980864384

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62590b0428b951f10363062212d73c1dc1f2160d69391d35c6bf2216aadeb83
+size 4764874336

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec01264f257a047154d48a12cd14925a9630ba43cc2a70e8d2577b0d36d98d3
+size 4781670320

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d173a1b54d6ec43cb7aace21f2c244c8910953400ff41582dd292be0312b279
+size 4781670328

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e2590f8fb1ff8655c48cb8459aad3aa964222eb6c7153367e2aea16c6f30df
+size 4980864384

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c99a37071961fc20091324d2277048f9294079cfdde45a602477a6dfa4fa0c
+size 4764874336

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a7d2bb18eec4ac2bdde2f5810fa79a190500632bfe5e52e342012217cc6bd5
+size 4781670320

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4bce46eef5a7962dddb4121e56b56a62f51c8335d6eb84f19603d064fc1d5e
+size 4781670328

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e6da3527ff7b6b95a545a8c8ef0154d412097c82a0faf802598e9f1aac3fbb
+size 4980864384

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7af75aabf00559c7d7b47b2050433a5d410b8d53d0814ca17989cfae99a1d1
+size 4764874336

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c04056b8af1ecd22567436d0155ca0672bc28d93f2d5e872a9d8b3e9c2678f
+size 4781670320

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b393875cb175c6df5829102ff094a50c709445ac832b55c7f6c8a542e5d9319c
+size 4781670328

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7618c9a3b76152631c2303d5469a4fbac3524460bfacc8bfc096bddcd31bb3
+size 4980864384

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9e0ac4f68504a94e7f2af59f09b40f1c5cec4834f84f8fd191e11e790f5389
+size 4764874336

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a919abc697a30b2a67ecf372a12e26263b533baf4e1d79ec770e2b56926092b3
+size 4781670320

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b7fba56a83cda4d78c6627b7087db461f78e10abbc056e47663831fc26da01
+size 4781670328

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9974032acabee735d8e38fe22514d025dd96b9ebee06b7508e79a6feb94e4850
+size 4980864384

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2944c6d465daba586917ce33af8d51747578e112b15313aa1087352f230c7f5
+size 4764874336

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee74a1d62b1565a00b30480625211a1b1dd504ff56e652b85da77d9d3f2cd6a
+size 4781670320

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3cf05c8ef640eeb84decdd27a65027a145a8380f351ba2589453c456db0786
+size 4781670328

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d67ac5e0dbcb9b665f192d5c8cea8376d8613d35589f01063a5ac65adbbce43
+size 4980864384

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0824a0ab120138e2e11c33302a75ee770db134989926ba1b4b05226e4b18762f
+size 4764874336

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bd5c0a78d63704ebc5244b3f8e0cec1ebca2d962ff678bd05aa46b18aaca3d
+size 4781670320

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127be4ef4cf26423c1c910e008ee14927ef850348dd3c8833d431bd310863f57
+size 1270928608

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 155930927104}, "weight_map": {"lm_head.weight": "model-00001-of-00033.safetensors", "model.embed_tokens.weight": "model-00001-of-00033.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.norm.weight": "model-00033-of-00033.safetensors"}}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}