初始化项目，由ModelHub XC社区提供模型

Model: viethq188/Rabbit-7B-DPO-Chat
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 +1,35 @@
+---
+license: apache-2.0
+---
+Merge AIDC-ai-business/Marcoroni-7B-v3 and rwitz/go-bruins-v2 using slerp merge from https://github.com/cg123/mergekit.
+After that we trained DPO with HF data
+
+*config.yaml*
+```
+slices:
+  - sources:
+      - model: AIDC-ai-business/Marcoroni-7B-v3
+        layer_range: [0, 32]
+      - model: rwitz/go-bruins-v2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: AIDC-ai-business/Marcoroni-7B-v3
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5 
+dtype: float16
+```
+
+You can use alpaca template.
+```
+template_format = """{system}
+### Instruction:
+{prompt}
+
+### Response:
+"""
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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:cd15c73dd1ac4c72e6930ce29851439f73cdc33d6c199227f7a80cb77ddd1b42
+size 899700344

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b81d43584aa7c8d3f22c2d6fe17a549dc3966e85c268e267c29db99ff388b5e
+size 989895552

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfeb2e9b27679a79678080df1ee7d3ba9399794c9fa214ca52e5f186d95183be
+size 989912548

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515b2815725213099119f1628d10ba9971f9ecb406cbc35af7a217b027dd5920
+size 956342070

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c819b0eb3a47ea0733125e18a1f4f00024d042ff5a7507936e32d85319e9b41
+size 989895552

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c7b7d621defef5a2cc5b588d3ee884a64047a41717e53b750f833b371bda97
+size 989895552

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e9da2a4a806ad9a77761291850dceda1bb03a6685c21b38627a596a24c926f
+size 989912548

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812fe19c3588fd4779c5812182317d68c4c00300e89b556d3d921f5196f933a5
+size 956342070

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6781ab8c08307f48fde1303d819e59dcfbfc267f52d8ba6af87df7accb1d60
+size 989895552

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03da7dc98c772a0eb51967df83c35865b984da66455ea4b3e5fcb48d63cb9685
+size 989895552

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1ea8c5245c5633ad4377f734631b0e817d21a55be26cf18ff38e23c2c7ae6f
+size 989912548

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ee87dd69ff30569e2f71f6692e74907429db24378c34bac9ed7b25e7ef72c5
+size 956342070

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ed28e4e08e6bb243cf191ba6877d8d61ce91706d7d9cb6ff13f5df7ccd5129
+size 989895552

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffba32571cfd38221f3dc49b0d9718abbda0fe075d374f72cb3902155359798
+size 989895552

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598a96b46b6066145e79560ec9237440aebde23daecd56fee72d5f2b37492fac
+size 815838502

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "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 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}