初始化项目，由ModelHub XC社区提供模型

Model: kainatq/ksong-1-12b_v1_m3
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 +1,25 @@
+---
+library_name: transformers
+license: apache-2.0
+tags:
+- merge
+- mergekit
+---
+
+# ksong-1-12b_v1_m3
+
+Merged via [mergekit](https://github.com/cg123/mergekit).
+
+## 🧩 Configuration
+
+```yamlmerge_method: slerp
+base_model: Gryphe/Pantheon-RP-1.5-12b-Nemo
+dtype: bfloat16
+slices:
+  - sources:
+      - model: Gryphe/Pantheon-RP-1.5-12b-Nemo
+        layer_range: [0, 32]
+      - model: DarwinAnim8or/Trouper-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": 128,
+  "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
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 128,
+  "transformers_version": "4.44.0.dev0"
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+merge_method: slerp
+base_model: Gryphe/Pantheon-RP-1.5-12b-Nemo
+dtype: bfloat16
+slices:
+  - sources:
+      - model: Gryphe/Pantheon-RP-1.5-12b-Nemo
+        layer_range: [0, 32]
+      - model: DarwinAnim8or/Trouper-12B
+        layer_range: [0, 32]
+    parameters:
+      t: 0.5

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484e64bd506789a964d64904fde32073efaf4d570b627cf5e53446044cea9470
+size 1342177408

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca602f8de68ced26d4c1d1f8b5f695172783458b0aa456403fe12961c9ddfefa
+size 1887468816

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b1dec64c4a1d8d877ab69acc2cc731b606749d5c1b76e767eabc19f37b0be0
+size 1929444664

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d0e182357e26240f52ba2831290d7bbec54782db0e629ee2dc218c68417e15
+size 1887522696

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f002a899ff01d20bf3c8a98e3d0279c27f0e24436dc6d6fcb386d13849541db
+size 1929444672

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b91a352a2fd35e5da77bf323adae6ac5cdce9802bdb8a43cbeda5bc1dd3641f
+size 1887522680

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fae3246af25475f3cb77eaaba3592ea7f41ff5bac7d0e6284498e318bc4b20f
+size 1929444672

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d474beabf1875554644627d5bfc9b353630eb238092ffb8b16ccd4a1bc310d8
+size 1887522696

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066ef12333bc0832e1e1b2883d6509c85297a7600b389e45ca2d77c810c824d2
+size 1929444664

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7a9f317c4a3379fb0d5f44cc3e023a279b1ed63da671279c8638c5588b3d48
+size 1887522664

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb8f796ae27aec7a6ba74cc90aece578ea6b916d13662ef33629820cb5b6c17
+size 1635843112

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-00011.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}