初始化项目，由ModelHub XC社区提供模型

Model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-Combined-Thinker
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+base_model:
+- SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0
+- SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-RPThink0
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Arcee Fusion](https://arcee.ai) merge method using [SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0](https://huggingface.co/SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-RPThink0](https://huggingface.co/SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-RPThink0)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+name: ColdBrew-Nemo-12B-Arcane-Fusion-Combined-Thinker
+base_model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0
+models:
+  - model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0
+  - model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-RPThink0
+
+merge_method: arcee_fusion
+chat_template: chatml
+dtype: bfloat16
+
+```

chat_template.jinja

@@ -0,0 +1,2 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}
+{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "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": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 131075
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+name: ColdBrew-Nemo-12B-Arcane-Fusion-Combined-Thinker
+base_model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0
+models:
+  - model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-KBThink0
+  - model: SvalTek/ColdBrew-Nemo-12B-Arcane-Fusion-RPThink0
+
+merge_method: arcee_fusion
+chat_template: chatml
+dtype: bfloat16

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcb51d83b55cabc1b08ee7dfa9cac722abb22564ec960a89d6dbf87a3a1a9c1
+size 2684416128

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3f737a78a438a53cc10612f207437209e95d8e4943ff1562c5bf1345ab0d60
+size 4865558800

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbdab7a28cbf4fe6e8286f3802ab485cee9a139dee7973e08bb2100f610cde72
+size 4949446984

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbc92352cf75ed54d9f36b9f721d45d7155b55de4b63686c8ee7d5081a0ba61
+size 4865602440

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67400c0dc51d1b2497d2d6a40b2958477c2acf90c1e74332c447f5c97beaa438
+size 4949446968

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd607f508ebb3690890e78aedff8fc1a3e9a3557aa4b82903e6559e3a58c581
+size 4865602440

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6522181df5882972198f1a913317804fabd7c21e639eb0cff52b6f014631e095
+size 4949446968

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f11b7e2f28501b0b7327d6777030826691fd971a9841b09964d5f5d4b7b5c66
+size 4865602440

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4e09e9644e7cf94d450e5ee85d19e876b60a6c722a7a842cee62848fae2536
+size 4949446984

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8bcff70129072b340e8679d76e2f0fa94e2a326421fc5448bd492037f6d245
+size 4865602400

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cc78052f64004321de66c7cfbb6ca1266509b3584ff72d705d0089a0b69225
+size 2181122072

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 48991252480,
+    "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-00002-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-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-00003-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-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-00004-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-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-00005-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.39.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-00010-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-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 +1,30 @@
+{
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63faffcb63d620707a1c45d2398e77296f345dfed14efe2458e1c06747de31b
+size 17078890