Upload folder using huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen2-7B
+---
+
+# gemma-2-13b-it
+
+gemma-2-13b-it is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+
+## 🧩 Configuration
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [4, 12]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [8, 16]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [12, 20]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [16, 24]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [20, 28]
+    model: Qwen/Qwen2-7B
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [4, 12]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [8, 16]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [12, 20]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [16, 24]
+    model: Qwen/Qwen2-7B
+- sources:
+  - layer_range: [20, 28]
+    model: Qwen/Qwen2-7B

model-00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91df406a3064145fd8ab743856ee37f52eeff891e3de91de58eca32c2862112c
+size 1089994880

model-00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ada397ac390aa4bebeb3f080eac603884b5c6c99cc01b95eeef3a2bd801bac
+size 1089994896

model-00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bcf6fbfce7f9743774659f615d5544d0d9cca720f9c75633642b968f8e05f55
+size 932248440

model-00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595a1c40d37384647a08ddded080f52bffce16ebc56e12bb972fd73e3edd3b88
+size 932233912

model-00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e658665e2e8c2e33369c1ca1c4f664ad5cf36d6d0d6286a28d1e0cce64164b27
+size 932233912

model-00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c58d401c3e3ab574b0a01a9a769bcad28cf817a12da31ec28c5923385c51268
+size 932233912

model-00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42afdea151b6c871050a3c4e2befd18893a5a5c42baa0394f1457fae4522d368
+size 932233912

model-00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c349e8a387bddb06058b66978226ddba308df76b6089f126c6771d718303e66e
+size 932233912

model-00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741fae0cde0011bb98fdfc34b5ea699ef87882f055ea0314d9399b2137b706d3
+size 932233912

model-00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654d2a255bafdc0aa973f9f03399704168d9c641aee2631e3b552b572b5b43f0
+size 932233912

model-00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e564ccda5695b08ad7d3025c064913a5dc85b720cd274e6720cbacd1db6a94
+size 932233912

model-00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe9c425db1d90c532ca914b35f828dce81554cfe5a9416db5d0afd1696df085
+size 932233912

model-00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8467e1cc640bf3ef8a4e99be8b7591e376fa21d5a68bb53fccc1a9632b7f0a4e
+size 932226624

model-00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490a37a22c05c07f6a77a523058d5610accee9a522d759b9addef8f6a24ae340
+size 873496360

model-00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbd31a73694f407d5ed2ca724ee456cf3e2535a4179d64373f7b737ce6d083c
+size 932233912

model-00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112a2be9621adbc6f0f044ededbc8220c9a7af40df1ae3f15be02eda28d3442c
+size 932233912

model-00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7122dd5ecc6ce3295300a377a13fe1379420d90c53db642874457e26d6b5b2eb
+size 932233912

model-00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783824764d29b1c6a451b245f7663124236f16dd15588328761a8ceb55f130be
+size 990971456

model-00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea96491c8715b0c0adaf29b1079705965da2389f26ef5990a17913a8755382f
+size 932233912

model-00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244c0e7b737e8a50dad92541dd0057da21f012630d52fa73e5d49b882c897db8
+size 932241168

model-00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d10ebc11e0edd154a6e30436313dc5bf76b6ebef83b825f147d187982d2707b
+size 932233888

model-00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6787c895fab44df32979cd681ee58746b37f45e05a5a281e233a68567e89f2
+size 932233880

model-00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9f3bf2f27a3d12ed6122c6e7197f683f25a2c09f00a3cb571aae3d54779403
+size 932233904

model-00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd68687232398e13a879ac0ab5e1cda545934bdbca4b50afe047201618476530
+size 932233904

model-00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960624a887697cc859420dea40e5a5feb1ec4e4173ac0a620f6a0420d3751215
+size 932233912

model-00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eed4f687cd5dd119e044a3c6fa58bbbd02ae987733e3569e85cffd59ea37b2e
+size 932226616

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 24553544704}, "weight_map": {"lm_head.weight": "model-00001-of-00026.safetensors", "model.embed_tokens.weight": "model-00002-of-00026.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00026.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00026.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00026.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00026.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00026.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00026.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00026.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00010-of-00026.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00026.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00013-of-00026.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", "model.layers.2.input_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00014-of-00026.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00026.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00026.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00026.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00026.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00015-of-00026.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00026.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00015-of-00026.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00026.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00026.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00026.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00026.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00016-of-00026.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00016-of-00026.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00016-of-00026.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", "model.layers.42.input_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.38.input_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00016-of-00026.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00016-of-00026.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00026.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00026.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00017-of-00026.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00017-of-00026.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00017-of-00026.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", "model.layers.43.input_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.39.input_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00017-of-00026.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00017-of-00026.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00026.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00026.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00026.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00018-of-00026.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.45.input_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00019-of-00026.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00019-of-00026.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", "model.layers.47.input_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00020-of-00026.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00020-of-00026.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.8.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00021-of-00026.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", "model.layers.9.input_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00022-of-00026.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", "model.layers.10.input_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00023-of-00026.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", "model.layers.11.input_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.7.input_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", "model.layers.16.input_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.12.input_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.17.input_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.13.input_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00026-of-00026.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00026-of-00026.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00026-of-00026.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00026-of-00026.safetensors", "model.norm.weight": "model-00026-of-00026.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}