Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# oss-plus-v4
+
+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 Passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* ./gpt-oss-20b-BF16
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  # 底層編碼 (0-8)
+  - sources:
+      - layer_range: [0, 8]
+        model: ./gpt-oss-20b-BF16
+
+  # 分析推理核心區 (12-20) - 2層重疊  
+  - sources:
+      - layer_range: [7, 12]
+        model: ./gpt-oss-20b-BF16
+        
+  # 深度推理區 (18-26) - 2層重疊
+  - sources:
+      - layer_range: [9, 17]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [12, 18]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [17, 19]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [18, 22]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [21, 24]
+        model: ./gpt-oss-20b-BF16
+
+include_non_layer_weights: true
+merge_method: passthrough
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,80 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 201088
+}

mergekit_config.yml

@@ -0,0 +1,35 @@
+slices:
+  # 底層編碼 (0-8)
+  - sources:
+      - layer_range: [0, 8]
+        model: ./gpt-oss-20b-BF16
+
+  # 分析推理核心區 (12-20) - 2層重疊  
+  - sources:
+      - layer_range: [7, 12]
+        model: ./gpt-oss-20b-BF16
+        
+  # 深度推理區 (18-26) - 2層重疊
+  - sources:
+      - layer_range: [9, 17]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [12, 18]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [17, 19]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [18, 22]
+        model: ./gpt-oss-20b-BF16
+
+  - sources:
+      - layer_range: [21, 24]
+        model: ./gpt-oss-20b-BF16
+
+include_non_layer_weights: true
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a6ab00c867ec319a45e457eb6f437db851aef43b132411837a6d17b32713cc
+size 4493941904

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68377cfcf781853efc56499516c083830089469bcfed213012703e858cec6ef0
+size 4938949136

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fce50bf836480e8b0cbab96c23534b5bf2e6dcf62b2051768076fdfae0b5ba
+size 4885645736

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24be87825e8deeb56cd676e1bb336c5230c47b8432400ecacc3eab25f9c70a1
+size 4992609608

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2879c721ef73da5fa314d30757ffb85979e6ff5f2557abda248feccd2a425f7
+size 4885645736

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b44d95ae9a9a1882df931033a46ed59645bf05a853ae106b61a4d1f3312ebf6
+size 4992609608

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e164f9e8e08f9a90293a1ca3f21b9673197dad87308e52bbb679698c6c14e4e
+size 4885645736

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3995cb716cd2bf8be9ae1e328006d124752310214e2e134cefc66e99b478356e
+size 4992788232

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6d913b89c850f27fedccf4dc555cadf7af7cacdf0d2ceb80561ca9cfa9efbf
+size 4939127720

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ffbe96dbb152b1184984fcfe7bc82e81316b249410a57609eeb525bab38c53
+size 4939127680

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c0ad36a3f0e0b1e896287c0c3a92db66e54af405736212ae6c903fd1a5adf5
+size 4938949104

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ead7df4634c5fd94c691a3387a4d76516ed2c9f173f83a08457637d2a9b197
+size 4939127656

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c756ab5529253dcf0cd873bf55015bbef2fef63b2f1b281b8b2dc05ebc0de1e9
+size 2761904208

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00013.safetensors", "model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00013.safetensors", "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00013.safetensors", "model.layers.0.mlp.router.bias": "model-00001-of-00013.safetensors", "model.layers.0.mlp.router.weight": "model-00001-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.sinks": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00013.safetensors", "model.layers.1.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00002-of-00013.safetensors", "model.layers.1.mlp.router.bias": "model-00002-of-00013.safetensors", "model.layers.1.mlp.router.weight": "model-00002-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.sinks": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.11.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.layers.14.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00002-of-00013.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00002-of-00013.safetensors", "model.layers.11.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.layers.14.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00002-of-00013.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00002-of-00013.safetensors", "model.layers.11.mlp.router.bias": "model-00002-of-00013.safetensors", "model.layers.14.mlp.router.bias": "model-00002-of-00013.safetensors", "model.layers.11.mlp.router.weight": "model-00002-of-00013.safetensors", "model.layers.14.mlp.router.weight": "model-00002-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.sinks": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.sinks": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.12.mlp.experts.down_proj": "model-00002-of-00013.safetensors", "model.layers.15.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors", "model.layers.12.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.layers.15.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00003-of-00013.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00003-of-00013.safetensors", "model.layers.12.mlp.router.bias": "model-00003-of-00013.safetensors", "model.layers.15.mlp.router.bias": "model-00003-of-00013.safetensors", "model.layers.12.mlp.router.weight": "model-00003-of-00013.safetensors", "model.layers.15.mlp.router.weight": "model-00003-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.sinks": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.sinks": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.16.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.layers.21.mlp.experts.down_proj": "model-00003-of-00013.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors", "model.layers.16.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", "model.layers.21.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors", "model.layers.16.mlp.router.bias": "model-00004-of-00013.safetensors", "model.layers.21.mlp.router.bias": "model-00004-of-00013.safetensors", "model.layers.16.mlp.router.weight": "model-00004-of-00013.safetensors", "model.layers.21.mlp.router.weight": "model-00004-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.sinks": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.sinks": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.layers.22.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00004-of-00013.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00004-of-00013.safetensors", "model.layers.17.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.layers.22.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors", "model.layers.17.mlp.router.bias": "model-00004-of-00013.safetensors", "model.layers.22.mlp.router.bias": "model-00004-of-00013.safetensors", "model.layers.17.mlp.router.weight": "model-00004-of-00013.safetensors", "model.layers.22.mlp.router.weight": "model-00004-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.sinks": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.sinks": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.18.mlp.experts.down_proj": "model-00004-of-00013.safetensors", "model.layers.23.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors", "model.layers.18.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.layers.23.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00005-of-00013.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00005-of-00013.safetensors", "model.layers.18.mlp.router.bias": "model-00005-of-00013.safetensors", "model.layers.23.mlp.router.bias": "model-00005-of-00013.safetensors", "model.layers.18.mlp.router.weight": "model-00005-of-00013.safetensors", "model.layers.23.mlp.router.weight": "model-00005-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.sinks": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.sinks": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.19.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.layers.24.mlp.experts.down_proj": "model-00005-of-00013.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors", "model.layers.24.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors", "model.layers.19.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", "model.layers.24.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors", "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors", "model.layers.19.mlp.router.bias": "model-00006-of-00013.safetensors", "model.layers.24.mlp.router.bias": "model-00006-of-00013.safetensors", "model.layers.19.mlp.router.weight": "model-00006-of-00013.safetensors", "model.layers.24.mlp.router.weight": "model-00006-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.o_proj.bias": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.sinks": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.sinks": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.layers.25.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00006-of-00013.safetensors", "model.layers.25.mlp.experts.down_proj_bias": "model-00006-of-00013.safetensors", "model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.layers.25.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors", "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors", "model.layers.20.mlp.router.bias": "model-00006-of-00013.safetensors", "model.layers.25.mlp.router.bias": "model-00006-of-00013.safetensors", "model.layers.20.mlp.router.weight": "model-00006-of-00013.safetensors", "model.layers.25.mlp.router.weight": "model-00006-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.o_proj.bias": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.sinks": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.sinks": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.26.mlp.experts.down_proj": "model-00006-of-00013.safetensors", "model.layers.27.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.layers.26.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors", "model.layers.27.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors", "model.layers.26.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.layers.27.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00007-of-00013.safetensors", "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00007-of-00013.safetensors", "model.layers.26.mlp.router.bias": "model-00007-of-00013.safetensors", "model.layers.27.mlp.router.bias": "model-00007-of-00013.safetensors", "model.layers.26.mlp.router.weight": "model-00007-of-00013.safetensors", "model.layers.27.mlp.router.weight": "model-00007-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.o_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.o_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.sinks": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.sinks": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.layers.29.mlp.experts.down_proj": "model-00007-of-00013.safetensors", "model.layers.28.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors", "model.layers.29.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors", "model.layers.28.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", "model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors", "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors", "model.layers.28.mlp.router.bias": "model-00008-of-00013.safetensors", "model.layers.29.mlp.router.bias": "model-00008-of-00013.safetensors", "model.layers.28.mlp.router.weight": "model-00008-of-00013.safetensors", "model.layers.29.mlp.router.weight": "model-00008-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.o_proj.bias": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.o_proj.bias": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.sinks": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.sinks": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.30.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.layers.30.mlp.experts.down_proj_bias": "model-00008-of-00013.safetensors", "model.layers.30.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors", "model.layers.30.mlp.router.bias": "model-00008-of-00013.safetensors", "model.layers.30.mlp.router.weight": "model-00008-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.o_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.sinks": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.2.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00008-of-00013.safetensors", "model.layers.2.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors", "model.layers.2.mlp.router.bias": "model-00008-of-00013.safetensors", "model.layers.2.mlp.router.weight": "model-00008-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.sinks": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.31.mlp.experts.down_proj": "model-00008-of-00013.safetensors", "model.layers.31.mlp.experts.down_proj_bias": "model-00008-of-00013.safetensors", "model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00009-of-00013.safetensors", "model.layers.31.mlp.router.bias": "model-00009-of-00013.safetensors", "model.layers.31.mlp.router.weight": "model-00009-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.o_proj.bias": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.sinks": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.layers.33.mlp.experts.down_proj_bias": "model-00009-of-00013.safetensors", "model.layers.32.mlp.experts.down_proj_bias": "model-00009-of-00013.safetensors", "model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00009-of-00013.safetensors", "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00009-of-00013.safetensors", "model.layers.32.mlp.router.bias": "model-00009-of-00013.safetensors", "model.layers.33.mlp.router.bias": "model-00009-of-00013.safetensors", "model.layers.33.mlp.router.weight": "model-00009-of-00013.safetensors", "model.layers.32.mlp.router.weight": "model-00009-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.o_proj.bias": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.o_proj.bias": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.sinks": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.sinks": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.34.mlp.experts.down_proj": "model-00009-of-00013.safetensors", "model.layers.34.mlp.experts.down_proj_bias": "model-00009-of-00013.safetensors", "model.layers.34.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00010-of-00013.safetensors", "model.layers.34.mlp.router.bias": "model-00010-of-00013.safetensors", "model.layers.34.mlp.router.weight": "model-00010-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.o_proj.bias": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.sinks": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.layers.35.mlp.experts.down_proj_bias": "model-00010-of-00013.safetensors", "model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00010-of-00013.safetensors", "model.layers.35.mlp.router.bias": "model-00010-of-00013.safetensors", "model.layers.35.mlp.router.weight": "model-00010-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.o_proj.bias": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.sinks": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.3.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00010-of-00013.safetensors", "model.layers.3.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00010-of-00013.safetensors", "model.layers.3.mlp.router.bias": "model-00010-of-00013.safetensors", "model.layers.3.mlp.router.weight": "model-00010-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.sinks": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.4.mlp.experts.down_proj": "model-00010-of-00013.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00010-of-00013.safetensors", "model.layers.4.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00011-of-00013.safetensors", "model.layers.4.mlp.router.bias": "model-00011-of-00013.safetensors", "model.layers.4.mlp.router.weight": "model-00011-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.sinks": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.5.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00011-of-00013.safetensors", "model.layers.5.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00011-of-00013.safetensors", "model.layers.5.mlp.router.bias": "model-00011-of-00013.safetensors", "model.layers.5.mlp.router.weight": "model-00011-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.sinks": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.6.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00011-of-00013.safetensors", "model.layers.6.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00011-of-00013.safetensors", "model.layers.6.mlp.router.bias": "model-00011-of-00013.safetensors", "model.layers.6.mlp.router.weight": "model-00011-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.sinks": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.7.mlp.experts.down_proj": "model-00011-of-00013.safetensors", "model.layers.8.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00012-of-00013.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00012-of-00013.safetensors", "model.layers.7.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.layers.8.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00012-of-00013.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00012-of-00013.safetensors", "model.layers.7.mlp.router.bias": "model-00012-of-00013.safetensors", "model.layers.8.mlp.router.bias": "model-00012-of-00013.safetensors", "model.layers.7.mlp.router.weight": "model-00012-of-00013.safetensors", "model.layers.8.mlp.router.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.sinks": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.sinks": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00012-of-00013.safetensors", "model.layers.9.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00012-of-00013.safetensors", "model.layers.9.mlp.router.bias": "model-00012-of-00013.safetensors", "model.layers.9.mlp.router.weight": "model-00012-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.sinks": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.mlp.experts.down_proj": "model-00012-of-00013.safetensors", "model.layers.13.mlp.experts.down_proj": "model-00013-of-00013.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00013-of-00013.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00013-of-00013.safetensors", "model.layers.10.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", "model.layers.13.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00013-of-00013.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00013-of-00013.safetensors", "model.layers.10.mlp.router.bias": "model-00013-of-00013.safetensors", "model.layers.13.mlp.router.bias": "model-00013-of-00013.safetensors", "model.layers.10.mlp.router.weight": "model-00013-of-00013.safetensors", "model.layers.13.mlp.router.weight": "model-00013-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.sinks": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.sinks": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00013-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.norm.weight": "model-00013-of-00013.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}