初始化项目，由ModelHub XC社区提供模型

Model: mrcuddle/Mistral-Heretica-12B
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

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,45 @@
+---
+base_model:
+- NeverSleep/Lumimaid-v0.2-12B
+- mistralai/Mistral-Nemo-Instruct-2407
+- MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Mistral-Heretica-12B
+
+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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B)
+* [MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy](https://huggingface.co/MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+  - model: NeverSleep/Lumimaid-v0.2-12B
+    parameters:
+      weight: 0.5
+  - model: MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
+    parameters:
+      weight: 0.5
+merge_method: task_arithmetic
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+parameters:
+  normalize: true
+dtype: bfloat16
+```

README.md

@@ -0,0 +1,45 @@
+---
+base_model:
+- NeverSleep/Lumimaid-v0.2-12B
+- mistralai/Mistral-Nemo-Instruct-2407
+- MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Mistral-Heretica-12B
+
+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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B)
+* [MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy](https://huggingface.co/MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+  - model: NeverSleep/Lumimaid-v0.2-12B
+    parameters:
+      weight: 0.5
+  - model: MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
+    parameters:
+      weight: 0.5
+merge_method: task_arithmetic
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+parameters:
+  normalize: true
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "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": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "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": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.0.dev0"
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+  - model: NeverSleep/Lumimaid-v0.2-12B
+    parameters:
+      weight: 0.5
+  - model: MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
+    parameters:
+      weight: 0.5
+merge_method: task_arithmetic
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+parameters:
+  normalize: true
+dtype: bfloat16

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7a66269607f385f9eac0698f00ed2d4f56a89e52984dbc7942dc416467898d
+size 1342177408

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb15aa471981958f3c47fa32149d3f03461813da211ca93769adc763480a93a
+size 1342177424

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf66366bec1378a1a2edf869b5c8bf35442072b7193e2634d80d131647d721d
+size 996189888

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f036d2a9369d0873a97d2724a042bab7f23a0fe492a128560b557aa0ea1341
+size 933265104

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744784aca09cfefe88faf546b4e2212034f00bbf8ba1449f0d339375021bb0ec
+size 943761344

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e857f58de116a802f6ed2ae11f595c8812b818e62d6299016cf585340a8bcd
+size 943761344

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4899507ab2dcbf6373d92c0472f4e0eacd63b9f3b2992d23ed181816f6215df
+size 996179560

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f852791825b989cb1d1a3e6260ed34cba0d3c1ab35f0d340931c83dbfae040e6
+size 933265104

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a56fd1e267a8263182530f191b14bc9e709f6bba74ab9eb0ac18880d4abc019
+size 943761344

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aebf146e95f42976fe02d11b9c027dda865cace3c8471842e2762ea5dc05ea3
+size 943761344

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a7c6e28399de2fe506ee6df5f1685f50a82f265b0ccac780da94b9d0ea555c
+size 996179560

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e38be10893dc8fe7bb7364f53203c07bc9e27e7a7cb93d0eaff4dff0193e192
+size 933265104

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab45f7124e1c9d7144be919f5fb4aa98cd2e3b44938957cb588196fc3a8de705
+size 943761344

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c4c1a3166e93218152aea9f47621cef82e1cf126c861c6f63effd84f167dd1
+size 943761344

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cc4a412145d0296929b879ffc7adab452fd281361d8c3d43b8dbd9fef0364b
+size 996179560

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3aafb9308fc4fe69d8845afbe527a2ae9992dea79f02680d3fdb613fed8198
+size 933265096

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670194f3e3188601a5b93aa64f05ac6ab0a49a37ce192763465ab53012252301
+size 943761344

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b467b9321962a6f47635ea50c68737bb442b04a864d33bf9a91e9feb4d2935
+size 943761344

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6a95af4d4e6606b95355f2c4ce7b445c621387651da13770d450de4669715a
+size 996179560

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f5fb42fe4b9063e193847054d9634c27ea3ad2976944f544cf97e5dc07cc69
+size 933265104

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501d76ada090cf684249ab697cbf289704329becf0e83e6ff3e1aae4e127c63a
+size 943761344

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd87e21ac4f568e68ab44dbc7879d982c63a97d8ae06079084a5635918a300d
+size 943761336

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c042b6e3e23f7c5aaf5547f7a922f7518be0b738d6b324b158e6d188f7c14b
+size 996179552

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5617d0b6b716fa1977673f4e47f7ac590854e2b74ac628649e6b440be9eef1
+size 933265088

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540cc1326d7743f66e39bf3e1d68e24da3bb7fc90cb363019be8f55129878953
+size 796960560

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 24495564800,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00025.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00025.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.norm.weight": "model-00025-of-00025.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}