初始化项目，由ModelHub XC社区提供模型

Model: kainatq/ksong-1-12b_v1_m1
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 +1,26 @@
+---
+library_name: transformers
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+---
+
+# ksong-1-12b_v1_m1
+
+ksong-1-12b_v1_m1 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+
+## 🧩 Configuration
+
+```yamlmerge_method: slerp
+base_model: elinas/Chronos-Gold-12B-1.0
+dtype: bfloat16
+slices:
+  - sources:
+      - model: elinas/Chronos-Gold-12B-1.0
+        layer_range: [0, 32]
+      - model: LatitudeGames/Wayfarer-12B
+        layer_range: [0, 32]
+    parameters:
+      t: 0.5```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 15,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+merge_method: slerp
+base_model: elinas/Chronos-Gold-12B-1.0
+dtype: bfloat16
+slices:
+  - sources:
+      - model: elinas/Chronos-Gold-12B-1.0
+        layer_range: [0, 32]
+      - model: LatitudeGames/Wayfarer-12B
+        layer_range: [0, 32]
+    parameters:
+      t: 0.5

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49580015748f5dee2a20424470420801a2f6f8dfcf396df1f30bf1c5ed9f2581
+size 1342177408

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bfdc49ea84296a9bd651d1bed75132edd569b7c1ed1b4e654c299f8888c9c6
+size 1342177424

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1cf9f7899dc9590d1a7019c293d7ecb34a8863a0bdbc841881dbea9fa4921a
+size 996189888

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38ae7b164a7b3a0168fb643553da0ba495137b0ce815c88a984fe8c79cc7c1c
+size 933265104

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1053a8b3bfb9211fb061882274f64a15c7e721812ba05017c1d1cce9302e3997
+size 943761344

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b2ce4c394f107eb80a15333d5379ba53c81b9dfe37e119efd380975792b974
+size 943761344

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfd3f3db140a9729a0b75fda406558f7e1958e51b8ed658f4058d243f272472
+size 996179560

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6ae4f3d90a0cc2a9c039341bde7db6236118b9063d558e63cea41b77959ef2
+size 933265104

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e86bf8597282c31c03f94622502357c5be1d9dbd53e07fe91b369b47626e8b
+size 943761344

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f451154f43169e7b6267dc5d449cb488abd16fd439e606948a0c9dfcc50cdd0d
+size 943761344

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e0870c195f3b0f49f1b296af9ba49e9fa89a69a4f89cb7c3d36de694891369
+size 996179560

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2caf08af5ce8ec400406d35b6cd1214908b93a70fd314cbc48103414eaa183
+size 933265104

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736797ae128c0575743d04cd4b1ea8518dad685ad148a54dded452b5476d0942
+size 943761344

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc0caf6d9ed023e5a490587e23b9df3133568f08fa835e47df84b6e6b18eebc
+size 943761344

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a7c1143831f0b6c8db2cb8415b22732cdea744667c34b6c66da1ba39d738c3
+size 996179560

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4852c61857ef7741d19348854e9646fede7f562ced7230288a4db958ad8921be
+size 933265096

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5182bb9f5cc66ea6b9ac37b0b4408041a78aaa4df2caeb761c189c7577c59a
+size 943761344

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda5a71402234206e5bd314524fbe42ab5d3f00b7d166f5bca8061f4be0c08b6
+size 943761328

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dd1fbef9760ba2f4f17d31db2bb587387f746e5bd3178eaf4c1c12ecd8cec6
+size 996179552

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbaba578fac2f143f6b8bbba9bc275922f798bc7a20eeeabc99c0e47c005dcf5
+size 933265088

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a331166991079b4d4be5a162d5a79d511b9456ab4fb98674064f8a1bef7c8233
+size 251679536

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 20133324800,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00021.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.norm.weight": "model-00021-of-00021.safetensors"
+  }
+}

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}