Upload Qwen2ForCausalLM

README.md

@@ -1,9 +1,10 @@
 ---
-license: mit
 language:
 - zh
+license: mit
 tags:
 - medical
+- llama-factory
 ---
 # Model Card for Model ID
 

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.42.3"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157646d4d111e2e14b35fabbffeadc5c7bf52022b859368dc0b2a11920012b1b
+size 1089994896

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cda8d4daf655a295b9a98ecdd8192d7328078719e389386970cbd0993e93271
+size 990964136

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d1befc93126611455e2dbd86e38262ba680d5b11df2320103c41a1ae34418e2
+size 932233880

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c295a2d3bac55d56d07941f4146cafde745a5abdec5b0f88fce04e5029187f0b
+size 932233880

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a989935d4ac6f61b10117357e95513ccc7cdf6e280f6090fd7d9d0ed9e6c02bd
+size 932233880

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1475ed200acfd8befe9d608ff14618f8201dea8dc6977f93c4acd64d7c091120
+size 932233872

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171ed13577da2bd22a90f813cce2bfd2283b4c3efde21f0009cc8c1929eec495
+size 932233904

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b27fd50d87676d6dc2489a903d8e7722471f7ddda5a991273d781cbe111c06e
+size 932233904

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c4fe20ba5a122f93ec9fab06d4808cb664312d361ec1bf8a47cb8b62fa4ff2
+size 932233904

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a3bb835799781608ca98d56d78549f0598cee180a137582af712d1732dd042
+size 932233904

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18620bb15ff22a2ee9557951f23ea7e93f507d595b20fb921e7ad2e15eb7eb7b
+size 932233904

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca4924e0ce2d2624d5c8d90292dacb0f37359cad1076692cbdf3afa1c0df555
+size 932233904

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cceb3ce994f832ba5c88a628cca92254ee0abc9a4c40c697b9018b0a20c513
+size 932233904

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05433667b4ce945c11f1bad831bec4513d9a3a5e67292efac835c2d312bf93a2
+size 932233904

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2d09c439927af4e903ceebc4f350fb45ee891c794475a7001650ff5ca2b998
+size 1089994880

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34809e382016036fe328ad93edebb7a187f94d288620c4958adaa49ae374fc7
+size 873510904

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00016.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.norm.weight": "model-00016-of-00016.safetensors"
+  }
+}