Upload folder using huggingface_hub

README.md

@@ -0,0 +1,35 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen-7B
+- rinna/nekomata-7b
+---
+
+# without_japanese_apart_from_nekomata-7b_task_arithmetic
+
+without_japanese_apart_from_nekomata-7b_task_arithmetic is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [Qwen/Qwen-7B](https://huggingface.co/Qwen/Qwen-7B)
+* [rinna/nekomata-7b](https://huggingface.co/rinna/nekomata-7b)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: Qwen/Qwen-7B
+    parameters:
+      weight: 0.5
+  - model: rinna/nekomata-7b
+    parameters:
+      weight: 0.5
+
+merge_method: task_arithmetic
+base_model: rinna/nekomata-7b
+parameters:
+  normalize: true
+  int8_mask: true
+
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "rinna/nekomata-7b",
+  "architectures": [
+    "QWenLMHeadModel"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "rinna/nekomata-7b--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "rinna/nekomata-7b--modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": false,
+  "emb_dropout_prob": 0.0,
+  "fp16": false,
+  "fp32": false,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 32768,
+  "model_type": "qwen",
+  "no_bias": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "onnx_safe": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 8192,
+  "softmax_in_fp32": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "QWenTokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "use_cache_kernel": false,
+  "use_cache_quantization": false,
+  "use_dynamic_ntk": true,
+  "use_flash_attn": "auto",
+  "use_logn_attn": true,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+
+models:
+  - model: Qwen/Qwen-7B
+    parameters:
+      weight: 0.5
+  - model: rinna/nekomata-7b
+    parameters:
+      weight: 0.5
+
+merge_method: task_arithmetic
+base_model: rinna/nekomata-7b
+parameters:
+  normalize: true
+  int8_mask: true
+
+dtype: bfloat16

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c85b8e3259241a7c965d4b4ad713780f5dba7c87b23855845880f9c789c0727
+size 1244659840

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb64af4ce540c0eb9506ae6d43d925cecd86d08c083d3f0813af3996176e432
+size 943843544

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea7cada7ebc00dec272a7885e78102bdf4e0d19452cdad0e2f1fd2f00b04195
+size 989939632

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9050489bde18ac24b08c595091a10d64aa2e32a28064e8486c4c8d79c715530a
+size 899786664

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955d98f949dfe229f650761ddbf515b1f98f47f183e6ac4fc3f2fd93bcdcbd71
+size 943818880

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb3430566379b7e875f08c0dd17cc48585b7dae0d8f4193db1c0fbe45ad78f4
+size 989939632

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25352bf8d3e4adf43362b30f90d797c0a17fc1f2b61d28cf056278e026f66a3
+size 899786656

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d562147bc3a1007d477a366f1a5db93381d4c72d04609307ff9d9132d197ca
+size 943818880

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1478f77469dd38dd2e2f1f6694a9dd247c8a43f21881052d75c35b679a806d68
+size 989939632

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ce997593153f3de2b93e0a9222ce301b26a04868a8705ee4cf5db0cc2ed4df
+size 899786664

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2e8642446291ead7031cf01af2ebac0cd9a29721fff5a28b059da497e8035c
+size 943818880

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e4eaa87d506732721f40d7e6d02d5004d64bb704f5acf6cdc173ea0f33e7f2
+size 989939632

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74980c8b6c5175041973e99ea43abb593ae972baea577fa86d06471456925210
+size 899786648

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c308437ebacfe89dd759507c7678b55aa7473b1c01f54bb39b5d9d21e2e59b6
+size 943818864

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86408312d3071bef1e860530559175b6a51f3235e65b81eb4fbeac62f83a9c2
+size 675333400

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aec107b0a188d8b4cbe52bf74e199e8fb69609495d844c623f90dd56ed5455d
+size 1244659848

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 15442649088}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "transformer.h.0.attn.c_attn.bias": "model-00002-of-00016.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00002-of-00016.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00002-of-00016.safetensors", "transformer.h.0.ln_1.weight": "model-00002-of-00016.safetensors", "transformer.h.0.ln_2.weight": "model-00002-of-00016.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00002-of-00016.safetensors", "transformer.h.0.mlp.w1.weight": "model-00002-of-00016.safetensors", "transformer.h.0.mlp.w2.weight": "model-00002-of-00016.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00002-of-00016.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00002-of-00016.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00002-of-00016.safetensors", "transformer.h.1.ln_1.weight": "model-00002-of-00016.safetensors", "transformer.h.1.ln_2.weight": "model-00002-of-00016.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00002-of-00016.safetensors", "transformer.h.1.mlp.w1.weight": "model-00002-of-00016.safetensors", "transformer.h.1.mlp.w2.weight": "model-00002-of-00016.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00002-of-00016.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00002-of-00016.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00002-of-00016.safetensors", "transformer.h.10.ln_1.weight": "model-00002-of-00016.safetensors", "transformer.h.10.ln_2.weight": "model-00002-of-00016.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00003-of-00016.safetensors", "transformer.h.10.mlp.w1.weight": "model-00003-of-00016.safetensors", "transformer.h.10.mlp.w2.weight": "model-00003-of-00016.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00003-of-00016.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00003-of-00016.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00003-of-00016.safetensors", "transformer.h.11.ln_1.weight": "model-00003-of-00016.safetensors", "transformer.h.11.ln_2.weight": "model-00003-of-00016.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00003-of-00016.safetensors", "transformer.h.11.mlp.w1.weight": "model-00003-of-00016.safetensors", "transformer.h.11.mlp.w2.weight": "model-00003-of-00016.safetensors", "transformer.h.12.attn.c_attn.bias": "model-00003-of-00016.safetensors", "transformer.h.12.attn.c_attn.weight": "model-00003-of-00016.safetensors", "transformer.h.12.attn.c_proj.weight": "model-00003-of-00016.safetensors", "transformer.h.12.ln_1.weight": "model-00003-of-00016.safetensors", "transformer.h.12.ln_2.weight": "model-00003-of-00016.safetensors", "transformer.h.12.mlp.c_proj.weight": "model-00003-of-00016.safetensors", "transformer.h.12.mlp.w1.weight": "model-00003-of-00016.safetensors", "transformer.h.12.mlp.w2.weight": "model-00004-of-00016.safetensors", "transformer.h.13.attn.c_attn.bias": "model-00004-of-00016.safetensors", "transformer.h.13.attn.c_attn.weight": "model-00004-of-00016.safetensors", "transformer.h.13.attn.c_proj.weight": "model-00004-of-00016.safetensors", "transformer.h.13.ln_1.weight": "model-00004-of-00016.safetensors", "transformer.h.13.ln_2.weight": "model-00004-of-00016.safetensors", "transformer.h.13.mlp.c_proj.weight": "model-00004-of-00016.safetensors", "transformer.h.13.mlp.w1.weight": "model-00004-of-00016.safetensors", "transformer.h.13.mlp.w2.weight": "model-00004-of-00016.safetensors", "transformer.h.14.attn.c_attn.bias": "model-00004-of-00016.safetensors", "transformer.h.14.attn.c_attn.weight": "model-00004-of-00016.safetensors", "transformer.h.14.attn.c_proj.weight": "model-00004-of-00016.safetensors", "transformer.h.14.ln_1.weight": "model-00004-of-00016.safetensors", "transformer.h.14.ln_2.weight": "model-00004-of-00016.safetensors", "transformer.h.14.mlp.c_proj.weight": "model-00004-of-00016.safetensors", "transformer.h.14.mlp.w1.weight": "model-00004-of-00016.safetensors", "transformer.h.14.mlp.w2.weight": "model-00004-of-00016.safetensors", "transformer.h.15.attn.c_attn.bias": "model-00004-of-00016.safetensors", "transformer.h.15.attn.c_attn.weight": "model-00005-of-00016.safetensors", "transformer.h.15.attn.c_proj.weight": "model-00005-of-00016.safetensors", "transformer.h.15.ln_1.weight": "model-00005-of-00016.safetensors", "transformer.h.15.ln_2.weight": "model-00005-of-00016.safetensors", "transformer.h.15.mlp.c_proj.weight": "model-00005-of-00016.safetensors", "transformer.h.15.mlp.w1.weight": "model-00005-of-00016.safetensors", "transformer.h.15.mlp.w2.weight": "model-00005-of-00016.safetensors", "transformer.h.16.attn.c_attn.bias": "model-00005-of-00016.safetensors", "transformer.h.16.attn.c_attn.weight": "model-00005-of-00016.safetensors", "transformer.h.16.attn.c_proj.weight": "model-00005-of-00016.safetensors", "transformer.h.16.ln_1.weight": "model-00005-of-00016.safetensors", "transformer.h.16.ln_2.weight": "model-00005-of-00016.safetensors", "transformer.h.16.mlp.c_proj.weight": "model-00005-of-00016.safetensors", "transformer.h.16.mlp.w1.weight": "model-00005-of-00016.safetensors", "transformer.h.16.mlp.w2.weight": "model-00005-of-00016.safetensors", "transformer.h.17.attn.c_attn.bias": "model-00005-of-00016.safetensors", "transformer.h.17.attn.c_attn.weight": "model-00005-of-00016.safetensors", "transformer.h.17.attn.c_proj.weight": "model-00005-of-00016.safetensors", "transformer.h.17.ln_1.weight": "model-00005-of-00016.safetensors", "transformer.h.17.ln_2.weight": "model-00005-of-00016.safetensors", "transformer.h.17.mlp.c_proj.weight": "model-00006-of-00016.safetensors", "transformer.h.17.mlp.w1.weight": "model-00006-of-00016.safetensors", "transformer.h.17.mlp.w2.weight": "model-00006-of-00016.safetensors", "transformer.h.18.attn.c_attn.bias": "model-00006-of-00016.safetensors", "transformer.h.18.attn.c_attn.weight": "model-00006-of-00016.safetensors", "transformer.h.18.attn.c_proj.weight": "model-00006-of-00016.safetensors", "transformer.h.18.ln_1.weight": "model-00006-of-00016.safetensors", "transformer.h.18.ln_2.weight": "model-00006-of-00016.safetensors", "transformer.h.18.mlp.c_proj.weight": "model-00006-of-00016.safetensors", "transformer.h.18.mlp.w1.weight": "model-00006-of-00016.safetensors", "transformer.h.18.mlp.w2.weight": "model-00006-of-00016.safetensors", "transformer.h.19.attn.c_attn.bias": "model-00006-of-00016.safetensors", "transformer.h.19.attn.c_attn.weight": "model-00006-of-00016.safetensors", "transformer.h.19.attn.c_proj.weight": "model-00006-of-00016.safetensors", "transformer.h.19.ln_1.weight": "model-00006-of-00016.safetensors", "transformer.h.19.ln_2.weight": "model-00006-of-00016.safetensors", "transformer.h.19.mlp.c_proj.weight": "model-00006-of-00016.safetensors", "transformer.h.19.mlp.w1.weight": "model-00006-of-00016.safetensors", "transformer.h.19.mlp.w2.weight": "model-00007-of-00016.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00007-of-00016.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00007-of-00016.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00007-of-00016.safetensors", "transformer.h.2.ln_1.weight": "model-00007-of-00016.safetensors", "transformer.h.2.ln_2.weight": "model-00007-of-00016.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00007-of-00016.safetensors", "transformer.h.2.mlp.w1.weight": "model-00007-of-00016.safetensors", "transformer.h.2.mlp.w2.weight": "model-00007-of-00016.safetensors", "transformer.h.20.attn.c_attn.bias": "model-00007-of-00016.safetensors", "transformer.h.20.attn.c_attn.weight": "model-00007-of-00016.safetensors", "transformer.h.20.attn.c_proj.weight": "model-00007-of-00016.safetensors", "transformer.h.20.ln_1.weight": "model-00007-of-00016.safetensors", "transformer.h.20.ln_2.weight": "model-00007-of-00016.safetensors", "transformer.h.20.mlp.c_proj.weight": "model-00007-of-00016.safetensors", "transformer.h.20.mlp.w1.weight": "model-00007-of-00016.safetensors", "transformer.h.20.mlp.w2.weight": "model-00007-of-00016.safetensors", "transformer.h.21.attn.c_attn.bias": "model-00007-of-00016.safetensors", "transformer.h.21.attn.c_attn.weight": "model-00008-of-00016.safetensors", "transformer.h.21.attn.c_proj.weight": "model-00008-of-00016.safetensors", "transformer.h.21.ln_1.weight": "model-00008-of-00016.safetensors", "transformer.h.21.ln_2.weight": "model-00008-of-00016.safetensors", "transformer.h.21.mlp.c_proj.weight": "model-00008-of-00016.safetensors", "transformer.h.21.mlp.w1.weight": "model-00008-of-00016.safetensors", "transformer.h.21.mlp.w2.weight": "model-00008-of-00016.safetensors", "transformer.h.22.attn.c_attn.bias": "model-00008-of-00016.safetensors", "transformer.h.22.attn.c_attn.weight": "model-00008-of-00016.safetensors", "transformer.h.22.attn.c_proj.weight": "model-00008-of-00016.safetensors", "transformer.h.22.ln_1.weight": "model-00008-of-00016.safetensors", "transformer.h.22.ln_2.weight": "model-00008-of-00016.safetensors", "transformer.h.22.mlp.c_proj.weight": "model-00008-of-00016.safetensors", "transformer.h.22.mlp.w1.weight": "model-00008-of-00016.safetensors", "transformer.h.22.mlp.w2.weight": "model-00008-of-00016.safetensors", "transformer.h.23.attn.c_attn.bias": "model-00008-of-00016.safetensors", "transformer.h.23.attn.c_attn.weight": "model-00008-of-00016.safetensors", "transformer.h.23.attn.c_proj.weight": "model-00008-of-00016.safetensors", "transformer.h.23.ln_1.weight": "model-00008-of-00016.safetensors", "transformer.h.23.ln_2.weight": "model-00008-of-00016.safetensors", "transformer.h.23.mlp.c_proj.weight": "model-00009-of-00016.safetensors", "transformer.h.23.mlp.w1.weight": "model-00009-of-00016.safetensors", "transformer.h.23.mlp.w2.weight": "model-00009-of-00016.safetensors", "transformer.h.24.attn.c_attn.bias": "model-00009-of-00016.safetensors", "transformer.h.24.attn.c_attn.weight": "model-00009-of-00016.safetensors", "transformer.h.24.attn.c_proj.weight": "model-00009-of-00016.safetensors", "transformer.h.24.ln_1.weight": "model-00009-of-00016.safetensors", "transformer.h.24.ln_2.weight": "model-00009-of-00016.safetensors", "transformer.h.24.mlp.c_proj.weight": "model-00009-of-00016.safetensors", "transformer.h.24.mlp.w1.weight": "model-00009-of-00016.safetensors", "transformer.h.24.mlp.w2.weight": "model-00009-of-00016.safetensors", "transformer.h.25.attn.c_attn.bias": "model-00009-of-00016.safetensors", "transformer.h.25.attn.c_attn.weight": "model-00009-of-00016.safetensors", "transformer.h.25.attn.c_proj.weight": "model-00009-of-00016.safetensors", "transformer.h.25.ln_1.weight": "model-00009-of-00016.safetensors", "transformer.h.25.ln_2.weight": "model-00009-of-00016.safetensors", "transformer.h.25.mlp.c_proj.weight": "model-00009-of-00016.safetensors", "transformer.h.25.mlp.w1.weight": "model-00009-of-00016.safetensors", "transformer.h.25.mlp.w2.weight": "model-00010-of-00016.safetensors", "transformer.h.26.attn.c_attn.bias": "model-00010-of-00016.safetensors", "transformer.h.26.attn.c_attn.weight": "model-00010-of-00016.safetensors", "transformer.h.26.attn.c_proj.weight": "model-00010-of-00016.safetensors", "transformer.h.26.ln_1.weight": "model-00010-of-00016.safetensors", "transformer.h.26.ln_2.weight": "model-00010-of-00016.safetensors", "transformer.h.26.mlp.c_proj.weight": "model-00010-of-00016.safetensors", "transformer.h.26.mlp.w1.weight": "model-00010-of-00016.safetensors", "transformer.h.26.mlp.w2.weight": "model-00010-of-00016.safetensors", "transformer.h.27.attn.c_attn.bias": "model-00010-of-00016.safetensors", "transformer.h.27.attn.c_attn.weight": "model-00010-of-00016.safetensors", "transformer.h.27.attn.c_proj.weight": "model-00010-of-00016.safetensors", "transformer.h.27.ln_1.weight": "model-00010-of-00016.safetensors", "transformer.h.27.ln_2.weight": "model-00010-of-00016.safetensors", "transformer.h.27.mlp.c_proj.weight": "model-00010-of-00016.safetensors", "transformer.h.27.mlp.w1.weight": "model-00010-of-00016.safetensors", "transformer.h.27.mlp.w2.weight": "model-00010-of-00016.safetensors", "transformer.h.28.attn.c_attn.bias": "model-00010-of-00016.safetensors", "transformer.h.28.attn.c_attn.weight": "model-00011-of-00016.safetensors", "transformer.h.28.attn.c_proj.weight": "model-00011-of-00016.safetensors", "transformer.h.28.ln_1.weight": "model-00011-of-00016.safetensors", "transformer.h.28.ln_2.weight": "model-00011-of-00016.safetensors", "transformer.h.28.mlp.c_proj.weight": "model-00011-of-00016.safetensors", "transformer.h.28.mlp.w1.weight": "model-00011-of-00016.safetensors", "transformer.h.28.mlp.w2.weight": "model-00011-of-00016.safetensors", "transformer.h.29.attn.c_attn.bias": "model-00011-of-00016.safetensors", "transformer.h.29.attn.c_attn.weight": "model-00011-of-00016.safetensors", "transformer.h.29.attn.c_proj.weight": "model-00011-of-00016.safetensors", "transformer.h.29.ln_1.weight": "model-00011-of-00016.safetensors", "transformer.h.29.ln_2.weight": "model-00011-of-00016.safetensors", "transformer.h.29.mlp.c_proj.weight": "model-00011-of-00016.safetensors", "transformer.h.29.mlp.w1.weight": "model-00011-of-00016.safetensors", "transformer.h.29.mlp.w2.weight": "model-00011-of-00016.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00011-of-00016.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00011-of-00016.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00011-of-00016.safetensors", "transformer.h.3.ln_1.weight": "model-00011-of-00016.safetensors", "transformer.h.3.ln_2.weight": "model-00011-of-00016.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00012-of-00016.safetensors", "transformer.h.3.mlp.w1.weight": "model-00012-of-00016.safetensors", "transformer.h.3.mlp.w2.weight": "model-00012-of-00016.safetensors", "transformer.h.30.attn.c_attn.bias": "model-00012-of-00016.safetensors", "transformer.h.30.attn.c_attn.weight": "model-00012-of-00016.safetensors", "transformer.h.30.attn.c_proj.weight": "model-00012-of-00016.safetensors", "transformer.h.30.ln_1.weight": "model-00012-of-00016.safetensors", "transformer.h.30.ln_2.weight": "model-00012-of-00016.safetensors", "transformer.h.30.mlp.c_proj.weight": "model-00012-of-00016.safetensors", "transformer.h.30.mlp.w1.weight": "model-00012-of-00016.safetensors", "transformer.h.30.mlp.w2.weight": "model-00012-of-00016.safetensors", "transformer.h.31.attn.c_attn.bias": "model-00012-of-00016.safetensors", "transformer.h.31.attn.c_attn.weight": "model-00012-of-00016.safetensors", "transformer.h.31.attn.c_proj.weight": "model-00012-of-00016.safetensors", "transformer.h.31.ln_1.weight": "model-00012-of-00016.safetensors", "transformer.h.31.ln_2.weight": "model-00012-of-00016.safetensors", "transformer.h.31.mlp.c_proj.weight": "model-00012-of-00016.safetensors", "transformer.h.31.mlp.w1.weight": "model-00012-of-00016.safetensors", "transformer.h.31.mlp.w2.weight": "model-00013-of-00016.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00013-of-00016.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00013-of-00016.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00013-of-00016.safetensors", "transformer.h.4.ln_1.weight": "model-00013-of-00016.safetensors", "transformer.h.4.ln_2.weight": "model-00013-of-00016.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00013-of-00016.safetensors", "transformer.h.4.mlp.w1.weight": "model-00013-of-00016.safetensors", "transformer.h.4.mlp.w2.weight": "model-00013-of-00016.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00013-of-00016.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00013-of-00016.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00013-of-00016.safetensors", "transformer.h.5.ln_1.weight": "model-00013-of-00016.safetensors", "transformer.h.5.ln_2.weight": "model-00013-of-00016.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00013-of-00016.safetensors", "transformer.h.5.mlp.w1.weight": "model-00013-of-00016.safetensors", "transformer.h.5.mlp.w2.weight": "model-00013-of-00016.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00013-of-00016.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00014-of-00016.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00014-of-00016.safetensors", "transformer.h.6.ln_1.weight": "model-00014-of-00016.safetensors", "transformer.h.6.ln_2.weight": "model-00014-of-00016.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00014-of-00016.safetensors", "transformer.h.6.mlp.w1.weight": "model-00014-of-00016.safetensors", "transformer.h.6.mlp.w2.weight": "model-00014-of-00016.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00014-of-00016.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00014-of-00016.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00014-of-00016.safetensors", "transformer.h.7.ln_1.weight": "model-00014-of-00016.safetensors", "transformer.h.7.ln_2.weight": "model-00014-of-00016.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00014-of-00016.safetensors", "transformer.h.7.mlp.w1.weight": "model-00014-of-00016.safetensors", "transformer.h.7.mlp.w2.weight": "model-00014-of-00016.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00014-of-00016.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00014-of-00016.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00014-of-00016.safetensors", "transformer.h.8.ln_1.weight": "model-00014-of-00016.safetensors", "transformer.h.8.ln_2.weight": "model-00014-of-00016.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00015-of-00016.safetensors", "transformer.h.8.mlp.w1.weight": "model-00015-of-00016.safetensors", "transformer.h.8.mlp.w2.weight": "model-00015-of-00016.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00015-of-00016.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00015-of-00016.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00015-of-00016.safetensors", "transformer.h.9.ln_1.weight": "model-00015-of-00016.safetensors", "transformer.h.9.ln_2.weight": "model-00015-of-00016.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00015-of-00016.safetensors", "transformer.h.9.mlp.w1.weight": "model-00015-of-00016.safetensors", "transformer.h.9.mlp.w2.weight": "model-00015-of-00016.safetensors", "transformer.ln_f.weight": "model-00015-of-00016.safetensors", "transformer.wte.weight": "model-00016-of-00016.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|extra_204|>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "rinna/nekomata-7b--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 32768,
+  "pad_token": "<|extra_204|>",
+  "tokenizer_class": "QWenTokenizer"
+}