初始化项目，由ModelHub XC社区提供模型

Model: migtissera/Tess-M-v1.2
Source: Original Platform

.gitattributes

@@ -0,0 +1,65 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+ 
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00011-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00010-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00008-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00013-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00012-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00009-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00015-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00014-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00007-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00015.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00015.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,24 @@
+---
+license: other
+license_name: yi-34b
+license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
+---
+
+# Note:
+This version is experimental and have been depracated. Please use the stable release Tess-M-v1.3: https://huggingface.co/migtissera/Tess-M-v1.3
+
+# Tess
+
+![Tess](https://huggingface.co/migtissera/Tess-M-v1.0/resolve/main/Tess.png)
+
+Tess, short for Tessoro/Tessoso, is a general purpose Large Language Model series. Tess-M-v1.2 was trained on the Yi-34B-200K base.
+
+
+# Prompt Format:
+
+```
+SYSTEM: <ANY SYSTEM CONTEXT>
+USER: 
+ASSISTANT:
+```
+

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 64001,
+  "<s>": 64000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/migel/Yi-34B-200K-Llama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 64000,
+  "eos_token_id": 64001,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.1",
+  "use_cache": false,
+  "vocab_size": 64002
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.1"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d22527f0a1f1ece87fcec031803117b830c28fb2fd83c91f28f1d4940d597c
+size 4793167065

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238fc7b8b14f1afa05cda9d226e37e43c8daef79c18e940376836681a0f838a7
+size 4756468297

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86eb6930984b8fdea20a75d22c1458b98791b75080c3bf47afb9a4ee9f45cf7f
+size 4991380097

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05b9b8787b129c711dca77c0941d583488d7e2f6cf077102e17081d9282deec
+size 4756468333

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ac6ca999bc1bec1ae73267fa203e4b9c775bfbd4f348d3588a70533147ee4d
+size 4756468297

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de4a3ff22a521d4674525b7c30fa22198a829b975150a42ba991d945e5c935d
+size 4991380161

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62277f31e5f7fed726a6776bfd7e147da1b613725d398980934f9861da9d200d
+size 4756468333

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbebb3ba39b87b75b022483b6816f469b288d5695939b91144601387d19e55b8
+size 4756468297

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48be09e908751272d7228c8fb15d8eb30b4512ee57b84eb06155d08080e0bc68
+size 4991380161

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcda07a8838b876fdbbf67a59406c3e6b3455b87439f5fab958d32ba08c35071
+size 4756468333

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6acdcbba28099e0dd1a653892922083b11ab9a2e795fa7c2f5e9bb0e0095c6
+size 4756468297

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8dccc2763ed96f333daf8afd6e71ae2fe7a5802b83b585a66faaebe17dd9c0
+size 4991380161

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0aca3ff0d52ccc2ac2060f78739e08a6295587768a8c060b40724127669024c
+size 4756468333

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9ffd0644ec7febb61f4d023465602fc46265371ec8b391071d15af7ae34f83
+size 4756468297

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7669f981b63a8eda412cefbb26de1c3aa6ee6139d2a1b14eeae767d2198bc7
+size 1211179118

pytorch_model.bin.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777891840
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00015-of-00015.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d22a896da936284f97462519cc81e1a0d0ab761ff2a2535f3d44cd0d84268f3
+size 3561399

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}