Upload folder using huggingface_hub

README.md

@@ -0,0 +1,260 @@
+---
+base_model:
+- Undi95/PsyMedRP-v1-20B
+- Undi95/MXLewd-L2-20B
+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:
+* [Undi95/PsyMedRP-v1-20B](https://huggingface.co/Undi95/PsyMedRP-v1-20B)
+* [Undi95/MXLewd-L2-20B](https://huggingface.co/Undi95/MXLewd-L2-20B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+#--DUAL MODEL MERGE SETUP---
+
+# More buffer for the start and end layers (20 non duplicated as apposed to 10)
+# Merging two faves Undi95/PsyMedRP-v1-20B and Undi95/PsyMedRP-v1-20B
+
+
+
+# The models we are going to use.
+const_tag: &BASE_MODEL Undi95/PsyMedRP-v1-20B
+const_tag: &MODEL1 Undi95/MXLewd-L2-20B
+const_tag: &MODEL2 Undi95/PsyMedRP-v1-20B
+
+# The amount to scale the contribution to the residual stream (to hopefully reduce overshoot).
+const_tag: &RESIDUAL_SCALE_FACTOR 0.71 # back to 0.7
+
+model1-filter-env: &MODEL1_FILTER_ENV
+  parameters:
+    scale:
+      - filter: down_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - value: 1.0
+
+model2-filter-env: &MODEL2_FILTER_ENV
+  parameters:
+    scale:
+      - filter: down_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - value: 1.0
+
+slices:
+
+  # The first 20 layers are not duplicated.
+  - sources:
+    - model: *BASE_MODEL
+      layer_range: [0, 20]
+
+  - sources:
+    - model: *MODEL1
+      layer_range: [20, 21]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [20, 21]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [21, 22]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [21, 22]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [22, 23]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [22, 23]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [23, 24]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [23, 24]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [24, 25]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [24, 25]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [25, 26]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [25, 26]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [26, 27]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [26, 27]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [27, 28]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [27, 28]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [28, 29]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [28, 29]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [29, 30]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [29, 30]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [30, 31]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [30, 31]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [31, 32]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [31, 32]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [32, 33]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [32, 33]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [33, 34]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [33, 34]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [34, 35]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [34, 35]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [35, 36]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [35, 36]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [36, 37]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [36, 37]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [37, 38]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [37, 38]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [38, 39]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [38, 39]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [39, 40]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [39, 40]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [40, 41]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [40, 41]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [41, 42]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [41, 42]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [42, 43]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [42, 43]
+      <<: *MODEL2_FILTER_ENV
+  
+
+# The last 20 layers are not duplicated.
+  - sources:
+    - model: *BASE_MODEL
+      layer_range: [42, 62]
+
+merge_method: passthrough
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Undi95/PsyMedRP-v1-20B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,229 @@
+#--DUAL MODEL MERGE SETUP---
+
+# More buffer for the start and end layers (20 non duplicated as apposed to 10)
+# Merging two faves Undi95/PsyMedRP-v1-20B and Undi95/PsyMedRP-v1-20B
+
+
+
+# The models we are going to use.
+const_tag: &BASE_MODEL Undi95/PsyMedRP-v1-20B
+const_tag: &MODEL1 Undi95/MXLewd-L2-20B
+const_tag: &MODEL2 Undi95/PsyMedRP-v1-20B
+
+# The amount to scale the contribution to the residual stream (to hopefully reduce overshoot).
+const_tag: &RESIDUAL_SCALE_FACTOR 0.71 # back to 0.7
+
+model1-filter-env: &MODEL1_FILTER_ENV
+  parameters:
+    scale:
+      - filter: down_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - value: 1.0
+
+model2-filter-env: &MODEL2_FILTER_ENV
+  parameters:
+    scale:
+      - filter: down_proj
+        value: *RESIDUAL_SCALE_FACTOR
+      - value: 1.0
+
+slices:
+
+  # The first 20 layers are not duplicated.
+  - sources:
+    - model: *BASE_MODEL
+      layer_range: [0, 20]
+
+  - sources:
+    - model: *MODEL1
+      layer_range: [20, 21]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [20, 21]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [21, 22]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [21, 22]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [22, 23]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [22, 23]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [23, 24]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [23, 24]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [24, 25]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [24, 25]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [25, 26]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [25, 26]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [26, 27]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [26, 27]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [27, 28]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [27, 28]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [28, 29]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [28, 29]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [29, 30]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [29, 30]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [30, 31]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [30, 31]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [31, 32]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [31, 32]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [32, 33]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [32, 33]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [33, 34]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [33, 34]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [34, 35]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [34, 35]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [35, 36]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [35, 36]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [36, 37]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [36, 37]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [37, 38]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [37, 38]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [38, 39]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [38, 39]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [39, 40]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [39, 40]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [40, 41]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [40, 41]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [41, 42]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [41, 42]
+      <<: *MODEL2_FILTER_ENV
+  - sources:
+    - model: *MODEL1
+      layer_range: [42, 43]
+      <<: *MODEL1_FILTER_ENV
+  - sources:
+    - model: *MODEL2
+      layer_range: [42, 43]
+      <<: *MODEL2_FILTER_ENV
+  
+
+# The last 20 layers are not duplicated.
+  - sources:
+    - model: *BASE_MODEL
+      layer_range: [42, 62]
+
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc30cbeadcd30171ec01b009db91fdfde82af4f6b9cbce29e47ff6b9099f4037
+size 4991372448

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190b900bf0e589b8048acb83f2cd370345e590ff3243cebf61878c2518922bca
+size 4970422248

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c8f3d89b1dbb72c8a1e68abf4b6c2d0072f7a834656c0f16906bb1e4bff59a
+size 4970422256

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b7d5bc3ceb5a308584363b6949fba28aa22ed84945fd81cb54223b6b6eff58
+size 4970422256

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6793e668e726b2671d06f5c7910edc8bf1cf4cb6c60927540e93914c91d63c
+size 4860322112

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fb094ecbc9866b89473dd53ba13324423c7fe390e2dd8908cbb013b96390f0
+size 4970401560

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f640158aca0ee88d23c67e4eecd28065767270aa4f0ee0c8cd1dc69de2a593
+size 4970422256

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecaa32654c8afac4ee7b6c0c465a2f4a4ad93742be71a8fe1127a10f7992eb30
+size 4970422240

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9760fd5c458b1c1a7c8aa6969e7c6eb868af73f1126de241bfb041f9d6979f19
+size 4897011808

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ff8437df7c80198fff8e113082b4ad58c5fcb5df6fe2c731212ee221ea3c27
+size 4933722216

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953001e08ee2e34540ff79ed8d733528fcaea033c3a84f6cb81bc6fc2a5742c0
+size 4970411880

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d0021a727a7704defb3139fc67e0d12847c177e9783e0cffe61e5c95575087
+size 739278176

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 55214540800}, "weight_map": {"lm_head.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.62.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.64.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.81.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}