Upload 24 files

README.md

@@ -1,21 +1,13 @@
 ---
-license: other
 license_name: qwen
-license_link: https://huggingface.co/Qwen/Qwen1.5-14B-Chat/blob/main/LICENSE
+license_link: https://huggingface.co/Qwen/Qwen1.5-72B-Chat/blob/main/LICENSE
 tags:
 - love
 - philosophy
 - literature
-- roleplay
-- character
-- Chat
-language:
-- en
-- zh
 ---
 
 
-
 ## IA 14B
 
 ![image/png](IA.png)

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 35,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.37.0"
+}

pytorch_model-00001-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db10975255bc35ba92f980dfe25a7f7efb8d68e60c75ebcf6c9c10d6d1db724e
+size 1926945220

pytorch_model-00002-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10246b3c80ea37f2f15e8d4c5739222aa8f472c5cfb175feda458d1c7d5f5438
+size 1891566696

pytorch_model-00003-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad87f145a4c08606bd1a44917c5b731eafcee9da8f9e407551611232925152a
+size 1173226494

pytorch_model-00004-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d249c13c2126cce37b207630cd69dbdcbedd8401d0a1cf6b3d0ab35ff44b53d
+size 1977910443

pytorch_model-00005-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d9c1c50015b186c7172f4e37405d4a937c26ae458c4705e6b44ddb2f60de8b
+size 1996446064

pytorch_model-00006-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042cd31e7a791f5ea01c48ce4b7654ec214d838ede12a05ee834d04d1e654408
+size 945150298

pytorch_model-00007-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be2536bee87d906b1f479495d5bf15081453b7977112e8c92943c33f2737c73
+size 1977910443

pytorch_model-00008-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1025a1f3b04a569652c924414a2382ba0f708d620a9cc03085e3e08a68f681a8
+size 1996456642

pytorch_model-00009-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3610665573f6793e327cd00b1bf9379ccfbe2c2396d40e96bf7de9658577496
+size 1944006412

pytorch_model-00010-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db60029f521373967d628592a4c6358ea4b361547b5ab804770fa49c6f8a06e5
+size 1891566696

pytorch_model-00011-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55237a1b98a7f15f585ee5e4b1f256342aa2f047abe97b6e7ded39cf07b4551
+size 1891566696

pytorch_model-00012-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3045be5a6fc795f4624c86c3c9cfda7378559805fac6fa3c36d42b61250ec4ef
+size 1979374358

pytorch_model-00013-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9eb602b3e8f721cb9678e108d1b27750777f4373752e437ac1391a101fc6d9
+size 1891566696

pytorch_model-00014-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c85b45fbbefa22f2630dd18d19b5d5b8edb8033647c7ac47f197562378d55c6
+size 1874494926

pytorch_model-00015-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be334c1d84cc5acd092bdc00068f15c4d23076e24489ef35ff3a86e378abb30
+size 1891566696

pytorch_model-00016-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dd7e171b1f1b5797d2f0103716282b5a6a61c07ea123b03ac219ef13ca8949
+size 1085418768

pytorch_model.bin.index.json

@@ -0,0 +1,530 @@
+{
+  "metadata": {
+    "total_size": 28334991360
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00016.bin",
+    "model.embed_tokens.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.o_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.o_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.o_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.o_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.o_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.self_attn.o_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.o_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.o_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.o_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.o_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.o_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.o_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.o_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.o_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.21.self_attn.o_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00016-of-00016.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00016-of-00016.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.o_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.o_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00016.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.o_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.o_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.o_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.o_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.o_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.o_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.o_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.o_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.o_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.o_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.v_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.k_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.o_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.q_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.k_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.o_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.q_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.k_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.o_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.q_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.k_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.o_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.q_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.v_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.self_attn.k_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.o_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.q_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.k_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.o_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.q_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.k_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.o_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.q_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.o_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.o_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.o_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.o_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.o_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.o_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00016.bin"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}