初始化项目，由ModelHub XC社区提供模型

Model: liuda1/dm7b_sft_gpt88w_merge
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,6 @@
+---
+license: apache-2.0
+---
+---
+license: apache-2.0
+---with English chat dataset added for fine-tuning training, and further reinforcement training based on specific datasets. The trained model has a certain level of chat ability, which was found to be enhanced during self testing. We will continue to train the model in the future to improve our Chinese chat ability

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/data1/yuhuayou/dolphin-2.2.1-mistral-7b",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.34.1"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2082c347cdb5291aa6bd50bc7eb0b8dbadcb2d9b696d1a84994b40dcbb1e6a1
+size 899716728

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fc67a9543afb0e34aac51d65cc8163f1a1c68c7e77de3cfcdd4c8f010fb44a
+size 989895552

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b56727a2edfbd75884a4e4b8fd23f7a2632c03234aad901278adcd0a30434a
+size 989912548

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e87dc2297d0afcaa52880c3746bb4cfc7718822450cfdc5a5f32db317df81ab
+size 956342070

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e181b09c5c6badf9f2852efb526542830e59a8dcc1f62e1d7365c5e6ea276f
+size 989895552

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3036e2d52392d3f5089cda5e83ed1b611a20cd1ec571a2a4aded451699ccad9
+size 989895552

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903de3fd489dcea03531f873c135af7d60c47936036aaa719926995fb4813da8
+size 989912548

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ab1c5b7a11fe73acc337232611e5bbefe013eba240dad71154a372e8464baa
+size 956342070

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e298efc8020413cec466d7bcc393e730081eb0931e92fd61d84dc0574a17453
+size 989895552

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5bbce856afb558a55b90b0506fa5bc5ad6174cedfa70501db1a5f4da1dbabd7
+size 989895552

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6114d6efba61ecee2e33110dbe6c2c62517784198339eeb44c055ec89624a20
+size 989912548

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2724fdc711b51933e9772200523766c89bbdd249fa9f698e02eed8e53255eb4a
+size 956342070

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d6b87cd48e96ecf0beb681b2cd81726f0b180d7030bd07856858c285af3a7b
+size 989895552

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a90e0dc7ce07a6b7518775d5bc7fda8b198953fcef4b1f730c60ddd3d68f2b4
+size 989895552

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05c4e4ded2441008f18423b8175cb7468cc229edd6b81a92bb50b463a2e972e
+size 815854886

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483496960
+  },
+  "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-00002-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-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-00006-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-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-00003-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}