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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/QwQ-32B-Preview",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda4c716b31d302cb733fbc6a71ebc3fa7206d68a88e8bacf5daded4147f2282
+size 4498420808

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7e1c6f6703868f9ddbca2ebf10158c18ec594c6781389352ba8424edde4249
+size 4718804568

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf0cf14aa30cd04f6291065284c7b5676f5b1090a2fc2226ffebd2e620e260c
+size 4467075728

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d3ab5df013b7c18514d9a561de0e0cdda81c32f151fc23f27670cb0b519b5b
+size 4467075728

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a513ff7fb2875c21f524e3ef6532c1f3cec780fe506d6e6f4c688f357d0594
+size 4718804552

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d68ffda17efc322616abbce39f98ad13a92320d7f58ac15829954c17991c3e
+size 4467075752

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6c84389bb55a912dd7783faac79bf701dabd918734756a6e15d1a63ed91785
+size 4467075752

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c2216bab464263d67369b45394dcfe4481f37a571b0e42b677fadb41d3fc71
+size 4718804600

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25e1c25f14486bd82297c5c575f2dc598ce1dea512d9442d26aa289217ccbf7
+size 4467075752

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71d1d96cd4eb617147e98e0140aa4ece6d37782b08a8975acf7e135cde14ec7
+size 4467075752

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef27e5380ae284f4ba1eda019f4a647ddb0494c73298b4f8eefb9c072360ed0b
+size 4718804600

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83f0d13d93c8f3d77a91aac029e224f1e015fa6eabd385c5f52376ae0cd1719
+size 4467075752

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67457b9a4e9f42bed1d05f4fc824d16a33447083b2d494b31b9a315e469c346e
+size 4467075752

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a2157c64a037c55f21c80e47d066960725d585e4905558cb748173fd2d4d9a
+size 4718804600

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fffac55be2a2f4fbdaa2a58c6a13d047f4dc731ae5bae151c51d638637fafc
+size 4467075752

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191868b2fa53c7783cb4e45549a2e485d193752cac658a73b9c7cbe69b2ab3fc
+size 4467075752

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50802229662d2f3390fe2d4eab3f796e5fdf10529ba42ff0bf6fc357490ea605
+size 4718804600

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecc0e5ec03614cee5d09f39f52dbd016a73406716d645f06a50b1b59e550723
+size 4467075752

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfde602a73e6b799314b8540d735a3e7659ae0bf2d2a54136f872c606ff5a83
+size 4467075752

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c31bec22fa908e5e6237a84e54cce502bb4a2225182fb5f67664a544042a0f
+size 4718804600

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaba5a74d1b06f6051ba0f3e2f646cafc7086b1fe6b3d88cf6990c54ed45d1d6
+size 4467075752

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741bf587fc1cc25e32ec32152cca2f4c19b8d47af56f898f7631564381ae59f2
+size 4467075752

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428f51a23c2c6cbe4938887e27fca3ffef5f7154a1d6da58ee4d0c21acce8e2d
+size 4718804600

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7e5bef5595fe74b0155cba01a51c6e2bc26565a7f180b6393f6cffb6d6ce3d
+size 4467075752

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1305231d26a707a51c4d0abfd0144c7d1c76f86aba2967c63610611d30737c67
+size 4467075752

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbb9a31647e1b1c6d44a0b5bcb5bd8abd0a5ce38b6a4a7bf9d91c7eea57763e
+size 4718804600

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5607fccd8ce2cbb69730cce3ed14da624feb4f3d16ac503f77d48b474cea01
+size 4467075752

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c125e17c40d3a71d4b07c0c8f1c7e16f2fe3a591a7348d2685f6e588d0ca61c
+size 4467075752

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364fd1688ac569ee2927ef7e31f0d80d763d8ace8a2d95ca2c3e2eaa0bb280e7
+size 566292912

model.safetensors.index.json

@@ -0,0 +1,777 @@
+{
+  "metadata": {
+    "total_size": 127941234688
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00029.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "layers.1.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.10.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.11.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.12.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "layers.13.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "layers.15.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.17.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "layers.18.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.19.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.20.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "layers.22.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.24.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "layers.25.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.26.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "layers.27.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "layers.29.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.3.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "layers.30.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.31.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "layers.32.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.33.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "layers.34.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "layers.36.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.38.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "layers.39.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.4.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.40.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "layers.40.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "layers.41.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.42.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "layers.43.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.45.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "layers.45.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "layers.46.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.47.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "layers.47.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "layers.48.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "layers.48.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.48.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.49.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.49.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.49.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "layers.49.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "layers.5.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "layers.50.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.50.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.50.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.51.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.51.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.52.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "layers.52.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.52.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.52.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.52.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "layers.52.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "layers.52.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "layers.53.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "layers.53.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.53.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.54.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "layers.54.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.54.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.54.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.54.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "layers.54.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "layers.54.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "layers.55.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "layers.55.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.55.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.56.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.56.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.56.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "layers.56.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "layers.57.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.57.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.57.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.58.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.58.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.59.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "layers.59.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.59.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.59.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.59.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "layers.59.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "layers.59.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "layers.6.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.60.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "layers.60.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.60.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.61.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "layers.61.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.61.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.61.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.61.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "layers.61.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "layers.61.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "layers.62.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "layers.62.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.62.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "layers.63.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "layers.63.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "layers.63.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "layers.63.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "layers.7.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "layers.8.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}