Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,91 @@
+---
+base_model:
+- mistralai/Mistral-Nemo-Base-2407
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# out-1
+
+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:
+* [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+
+slices:
+  # untouched intro
+  - sources:
+      - layer_range: [0, 8]
+        model: mistralai/Mistral-Nemo-Base-2407
+
+  # 8–16 baseline
+  - sources:
+      - layer_range: [8, 16]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 8–16 duplicate with projections nulled
+  - sources:
+      - layer_range: [8, 16]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 16–24 baseline
+  - sources:
+      - layer_range: [16, 24]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 24]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 24–32 baseline
+  - sources:
+      - layer_range: [24, 32]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 24–32 duplicate
+  - sources:
+      - layer_range: [24, 32]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # untouched tail
+  - sources:
+      - layer_range: [32, 40]
+        model: mistralai/Mistral-Nemo-Base-2407
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,61 @@
+dtype: bfloat16
+merge_method: passthrough
+
+slices:
+  # untouched intro
+  - sources:
+      - layer_range: [0, 8]
+        model: mistralai/Mistral-Nemo-Base-2407
+
+  # 8–16 baseline
+  - sources:
+      - layer_range: [8, 16]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 8–16 duplicate with projections nulled
+  - sources:
+      - layer_range: [8, 16]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 16–24 baseline
+  - sources:
+      - layer_range: [16, 24]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 16–24 duplicate
+  - sources:
+      - layer_range: [16, 24]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # 24–32 baseline
+  - sources:
+      - layer_range: [24, 32]
+        model: mistralai/Mistral-Nemo-Base-2407
+  # 24–32 duplicate
+  - sources:
+      - layer_range: [24, 32]
+        model: mistralai/Mistral-Nemo-Base-2407
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+  # untouched tail
+  - sources:
+      - layer_range: [32, 40]
+        model: mistralai/Mistral-Nemo-Base-2407

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6c5d35f9e3f481de4aa618ab4a2849aa532110497f6740f8831c83d3d191b1
+size 4865499688

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee75a9145bababad549f430d7829d2a797e87d4c8f377e97968f8a0fac568692
+size 4949451440

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cba24f86585f189a6c8d092c5bd69028cf2b252d1f0f72dbb0856102e4e8ee
+size 4865597128

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b0b68e96bfcbbef0659e782a6194ca2a7eff40bb2c6d1b16749eea131c38a8
+size 4907539808

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6b6314f26bf062f113cf79c6454f54b91786828ab1bbbd3bf222fc07be7143
+size 4949451440

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d859bb7306d32affda82f6e7bf0d272e37fa1af421b061cec5dbcb75ed987f5
+size 4865597120

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579b18fa5aaeb02ee8f22259ffcabd8a9a080dd25c8f080f5d9f47be9e465a90
+size 4907529440

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6c4d47f8adc59eab478f17244c73afe03b23c63eec7f1c2db7d70d5518fd23
+size 3271686248

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 37582284800}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292