Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+base_model:
+- DazzlingXeno/MS-Drummer-Sunfall-22b
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [DazzlingXeno/MS-Drummer-Sunfall-22b](https://huggingface.co/DazzlingXeno/MS-Drummer-Sunfall-22b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: DazzlingXeno/MS-Drummer-Sunfall-22b
+      layer_range: [0, 42]
+  - sources:
+    - model: DazzlingXeno/MS-Drummer-Sunfall-22b
+      layer_range: [14, 56]
+merge_method: passthrough
+dtype: float16
+name: cydonia
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "DazzlingXeno/MS-Drummer-Sunfall-22b",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 84,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+slices:
+  - sources:
+    - model: DazzlingXeno/MS-Drummer-Sunfall-22b
+      layer_range: [0, 42]
+  - sources:
+    - model: DazzlingXeno/MS-Drummer-Sunfall-22b
+      layer_range: [14, 56]
+merge_method: passthrough
+dtype: float16
+name: cydonia

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cad547bc8dfceafaa4fbb227a4520822f824b2e10a24752eb61415e0edecde
+size 4907476488

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2028a451e0bd9b2b61289d18dc41b8f6a302574d134216e7f7787ff7c704ecab
+size 4932667632

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58846e2060d339537e4bd9e8f19450227ead9c48b0c7bee3d15f67f096e3b1b
+size 4995570360

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71542a0ba319b42559d9908e071c9b8c054737ce5dab2ac0cac4a8640560d8d8
+size 4920072168

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7cee8d2ce6e59ef4ebfc05fe2cc0a6164e60319da00531c16d362a5d783d29
+size 4983012152

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854c5d46996265c8e86dfca9386697fc8d922b1fc992f5b20917210d51408c43
+size 4932680600

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6ee97a8a8999da8a559dcf8fae0ddd4e876b19a40d59473d7904bce725c237
+size 4907464352

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fca3a11e7fca2c5a57779ce10d219826b33a81d71f1f7b84d5769e8f46bbd0
+size 4983012152

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ec87a57e057b8fb64caa6d808b48f55a0eaada69f3bf1ad75add84522eb0e5
+size 4932680600

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829c5c5c8ef4ded0ca7290c22b4259270b8735d33c8be7a401891296b18d5f21
+size 4907464352

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f74129c89cddd0257ea29a1b7475b583a1a484e4349561116d6dd027f9950d
+size 4857170624

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef0db5fb25c29010bf4666440c533a8281baa3529c94f9b542a104b2d2917b0
+size 4970416696

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39f63c1b7f5fcb351a709818242bd9a8772b0d2a98ce35cacfc267a479133dc
+size 4970416688

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb9d506a989bcaab6ef4b0bc4fe6d3d15e586d9bd4782d231752d443506b100
+size 2139171744

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 66339188736}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.62.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.66.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.68.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583