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 +1,38 @@
+---
+base_model:
+- fblgit/TheBeagle-v2beta-32B-MGS
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [fblgit/TheBeagle-v2beta-32B-MGS](https://huggingface.co/fblgit/TheBeagle-v2beta-32B-MGS)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: fblgit/TheBeagle-v2beta-32B-MGS
+  - model: fblgit/TheBeagle-v2beta-32B-MGS
+merge_method: slerp
+base_model: fblgit/TheBeagle-v2beta-32B-MGS
+dtype: float32
+parameters:
+  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
+
+```

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 +1,28 @@
+{
+  "_name_or_path": "fblgit/TheBeagle-v2beta-32B-MGS",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "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": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,8 @@
+models:
+  - model: fblgit/TheBeagle-v2beta-32B-MGS
+  - model: fblgit/TheBeagle-v2beta-32B-MGS
+merge_method: slerp
+base_model: fblgit/TheBeagle-v2beta-32B-MGS
+dtype: float32
+parameters:
+  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d727eeb99bbebd8c369edfd43208bc278b35dbcc761315336dba87f759543df
+size 3114270848

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c964d2f02908d2f6af45003ab581d3573cc786bcde0b24bf6fdd6697e11f0bc0
+size 4938859656

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0a2225e34b181fee6c06e1d663041b4d03d0c7441ac3a0bb7ca88dedc54ddb
+size 4592930040

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da089bd67f9c643d73b8db8de6e3bcd6dc61b23d804ac56a06ae28cae5a55493
+size 4467075912

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee57a0b997e40cf73feca4c38ae344e0c86e5d866e39bc8de47fbd3872e8f7d
+size 4718804800

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5a8c14f9e7dbe50447b912cb074261984b25363d408d88461afaba676fdcb5
+size 4467075912

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f953b2a7fe50610d1683a7df16732bc6fd8934aadaebbec0f07f4d48acbfae8
+size 4467075912

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e69f52788f6fef61e6758385f5fb2318dde14bc1206362d4233c6f4fc2eaaa1
+size 4718804784

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421ce9a34a3fc390e985bedf74aecec43e1c70f5369a314bddf84d0567aa7b31
+size 4467075912

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2117a44df0798a26c7518fa4805bbcc761d15a20a22168a13d9f41d7c06fe6d
+size 4467075912

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79689f0cc99327dfbf860c655583fac7c0dd4fb75b5ca315c3cdf893d34413f
+size 4718804800

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3781f3c6d557d5f192b7bdf2fa5bf88c75639e8eaa19f4a00831465e68c1e820
+size 4467075904

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af55193502323d27a33a719606e4fbaf5f8ee7565d829d7a4d3cecb73127ecf
+size 4467075912

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2646cf781b3352f7eb4195105bb2e9ee0f439678bc8c9fc4292e1ff3c096336
+size 4718804800

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84249b1721cbeebec026ee34681599f30b6e974a5622b03f872fd853790d30b4
+size 4467075912

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53898aa4915d2a52a7282d7c686d00562f5e93e5404fd6d7f0f59bd7e70e06f1
+size 4467075912

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc9136e963eb99b919aadf6f75bd88f2b7e1f44e7cac9135196da3ebc2e874c
+size 4718804784

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236e90b555be81bf473db54223582bf247813262a3476e03548fe94a5a9cdddc
+size 4467075912

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6212f2e63446f4e2a00c6399a8040e7c9c1043d6a2d826913455f8e3b3bfc01f
+size 4467075912

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a98754c4560abdd1a510d5bc45690d65ef2d3dc29b5c294f26b4e2171b92905
+size 4718804800

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d45d0fad311e4858e9227b14744ec6e8c8511c7240badecfb2c7a0101b5e80
+size 4467075912

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84885269376dba7429331d29b78e0cdb255f8dd1768d7a246c4e1d4b5bf239e
+size 4467075904

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849aefef5aa1552738864320c75f2df43b7a1167b2a8a2e2e06417397bedf7fe
+size 4718804800

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcdf88233b2f8cc3c596da55c1c899643945c7789647667604850b5cb02f270
+size 4467075912

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067ac94f95810e449de803f570c7f5cf07c77fcf47f3e882aa0a9cc62465f453
+size 4467075912

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce1c5318b2937b20707aa77381407a1ed7420f7945b035de03b456f2ad16f3f
+size 4718804784

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfda276e4bbe8874bba87f90fdb597d441652105d19f447a58e8bd4a360e0f6
+size 4467075912

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dfcaff99cdece5ea960632d927d9db0f100632ee31e9c838419e0eb84c1c60
+size 4467075912

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2552c05f4c03ae9fd74cda48e3d70e4397e5883dd968619b3b0b9b72320413c0
+size 4718804744

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 131055505408}, "weight_map": {"lm_head.weight": "model-00001-of-00029.safetensors", "model.embed_tokens.weight": "model-00002-of-00029.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00029.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00029.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00029.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00029.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00029.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00029.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00029.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00029.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00029.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00029.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00008-of-00029.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00029.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00029.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00029.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00029.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00029.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00029.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00029.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00029.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00011-of-00029.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00029.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00012-of-00029.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00013-of-00029.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00013-of-00029.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00014-of-00029.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00014-of-00029.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00014-of-00029.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00015-of-00029.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00015-of-00029.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00016-of-00029.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00016-of-00029.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00017-of-00029.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00017-of-00029.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00017-of-00029.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00018-of-00029.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00018-of-00029.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00019-of-00029.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00019-of-00029.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00020-of-00029.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00020-of-00029.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00020-of-00029.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.48.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00021-of-00029.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00021-of-00029.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00022-of-00029.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00022-of-00029.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.51.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00023-of-00029.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00023-of-00029.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00023-of-00029.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.54.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00024-of-00029.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00024-of-00029.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.56.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00025-of-00029.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00025-of-00029.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.58.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00026-of-00029.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00026-of-00029.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00026-of-00029.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.60.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00027-of-00029.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00027-of-00029.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.62.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00028-of-00029.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00028-of-00029.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.7.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00029-of-00029.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.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": "<|endoftext|>",
+    "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 assistant.' }}\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 assistant.<|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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}