Upload folder using huggingface_hub

README.md

@@ -0,0 +1,64 @@
+---
+base_model:
+- migtissera/SynthIA-70B-v1.2b
+- 152334H/miqu-1-70b-sf
+- Xwin-LM/Xwin-LM-70B-V0.1
+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 [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [migtissera/SynthIA-70B-v1.2b](https://huggingface.co/migtissera/SynthIA-70B-v1.2b)
+* [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
+* [Xwin-LM/Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: linear
+parameters:
+  weight: 1.0
+slices:
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [0, 24]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [0, 24]
+  - sources:
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [10, 34]
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [25, 49]
+  - sources: 
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [50, 74]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [25, 49]
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [35, 59]
+  - sources: 
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [79, 80]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [50, 51]
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [60, 61]
+dtype: float16
+tokenizer_source: model:152334H/miqu-1-70b-sf
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "migtissera/SynthIA-70B-v1.2b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 97,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,31 @@
+merge_method: linear
+parameters:
+  weight: 1.0
+slices:
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [0, 24]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [0, 24]
+  - sources:
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [10, 34]
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [25, 49]
+  - sources: 
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [50, 74]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [25, 49]
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [35, 59]
+  - sources: 
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [79, 80]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [50, 51]
+      - model: migtissera/SynthIA-70B-v1.2b
+        layer_range: [60, 61]
+dtype: float16
+tokenizer_source: model:152334H/miqu-1-70b-sf

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd1c3dd15f58e2447fefa6352d267eab6046a67fc60bac944d8ca019b82b824
+size 9684785016

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16312647de27b97ba03eaaeccfa66ee138fa79ff916f0787829e8b1e6ecd2f1
+size 9965885208

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba70fdef2710450cba8e8ad20a8aa722809031f889fe34b9c9071b28a4670bce
+size 9663862536

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35720834bc16b8d0e8592a588f64ef983c707c08a575bddba47358ea1ab95fa2
+size 9965852216

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543dd03ae75063d8a9621fa803a7956b13861fad03050d79f9069aba3d40a76c
+size 9932298248

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b132281c53a8aa42500c36ca4579d0dcc1c2a284080436451604ecc34f6687a0
+size 9798096912

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309ad1690dec602e8d3af66e3f5343ed214c3b1bb061a868e839c0590d772788
+size 9965852232

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ebb76f826f4ea420ea3a1db8cb6bc2f925a570fa6397afc65ed59d9c1ed7f2
+size 9965885904

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2092771f6db41fdb3a74e410f39d053c70840dd2111c155705b15e83457b0d92
+size 9630291392

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d39a3c0266c10f8cf2123811c8338e4fc0b5f5097e732d30f17c29418d1bcd
+size 9965902416

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adad351da91159240e7fde6752e6ef391b2a35b2bd9ad7a956e626d70c9f07f
+size 9798063208

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eaff13ca1240680208a81c72a7481e6578dcf00cf976bd6807ca8b311c2a66
+size 9630325104

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2084746ac2f237ae5e05152b9c0fa37cdd3aef038f7e29236703d96df8a0b477
+size 9831650864

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac09d3e86561fbe3c44b740862495743e20be0786b95e1fc544e90073bed6bb0
+size 9932281752

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53232eb1fb1ddbecaf6ff441f9a37294a7901bb39b94a10bf210e45f9699c324
+size 9663879064

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc06a8d16ee1c6002dcca17a66340b7f79c4faf8ca93553b8150ebf512c671e
+size 9965852216

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ef4fb6ff801d5f4cca2ac7e8cf6a9d6fd16ae1f11ef02f291ac60094faa0c4
+size 9684883304

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.embed_tokens.weight": "model-00001-of-00017.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.58.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.61.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.59.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.66.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.65.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.64.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.69.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.68.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.67.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.70.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.74.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.73.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.72.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.76.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.75.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.79.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.78.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.77.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.82.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.81.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.80.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.85.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.84.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.83.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.88.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.87.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.86.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.90.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.89.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.93.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.92.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.91.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.95.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.94.input_layernorm.weight": "model-00017-of-00017.safetensors", "lm_head.weight": "model-00017-of-00017.safetensors", "model.norm.weight": "model-00017-of-00017.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00017-of-00017.safetensors", "model.layers.96.input_layernorm.weight": "model-00017-of-00017.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}