Upload folder using huggingface_hub

README.md

@@ -0,0 +1,610 @@
+---
+base_model:
+- unsloth/Mistral-Small-Instruct-2409
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+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:
+* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 19]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Original L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# ... REPEAT UNTIL 41
+- sources:
+  - layer_range: [41, 55]
+    model: unsloth/Mistral-Small-Instruct-2409
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "unsloth/Mistral-Small-Instruct-2409",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 99,
+  "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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,581 @@
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 19]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Original L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L19
+- sources:
+  - layer_range: [19, 20]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L20
+- sources:
+  - layer_range: [20, 21]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L21
+- sources:
+  - layer_range: [21, 22]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L22
+- sources:
+  - layer_range: [22, 23]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L23
+- sources:
+  - layer_range: [23, 24]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L24
+- sources:
+  - layer_range: [24, 25]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L25
+- sources:
+  - layer_range: [25, 26]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L26
+- sources:
+  - layer_range: [26, 27]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L27
+- sources:
+  - layer_range: [27, 28]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L28
+- sources:
+  - layer_range: [28, 29]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L29
+- sources:
+  - layer_range: [29, 30]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L30
+- sources:
+  - layer_range: [30, 31]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L31
+- sources:
+  - layer_range: [31, 32]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L32
+- sources:
+  - layer_range: [32, 33]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L33
+- sources:
+  - layer_range: [33, 34]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L34
+- sources:
+  - layer_range: [34, 35]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L35
+- sources:
+  - layer_range: [35, 36]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L36
+- sources:
+  - layer_range: [36, 37]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L37
+- sources:
+  - layer_range: [37, 38]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L38
+- sources:
+  - layer_range: [38, 39]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L39
+- sources:
+  - layer_range: [39, 40]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Original L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+# Dupe A of L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# Dupe B of L40
+- sources:
+  - layer_range: [40, 41]
+    model: unsloth/Mistral-Small-Instruct-2409
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+# ... REPEAT UNTIL 41
+- sources:
+  - layer_range: [41, 55]
+    model: unsloth/Mistral-Small-Instruct-2409

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff50d62ecaf4826b998e558aee7a30881d340a018dd012ceddc5dc7d558a1fe
+size 4907476544

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f24f206c20330a64f9451786488fc7412ee92000b9a402f2e34a80e2b88d8cc
+size 4882348552

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f51306f7ece3194c0c4f473f964bc9f8d7c9b52bcc324ca639992155ed25829
+size 4945225904

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d5a621c278d0adafe135486dfe6329232fbbcf782866df12673af7f7b3f9ba
+size 4995607616

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2deab57e1f3cf20f24712853952d72e85d52737d81168b84d092a0ec90b90d2c
+size 4882323752

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00cb4c82c04f97dd5a88af0ade1045fc74c80672ee89a8b43864ba63d7c64e67
+size 4882323752

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18b89d8b300ab395e679e9083d70d43292c8498ff0cc721c98be823f099e3ea
+size 4882323744

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f65f6fcb8aa5ac781ab4a995d66f72beb7748b16f4114a3e3b1448f066eb1b
+size 4857183072

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea6a85f7ab7639d8fbd11c87a105bab00a69c22229ad231f1c0401ca618d62f
+size 4882323752

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7ac515df8dde66571822476a7b37386a0d47735d183c177d08e1be95479a3f
+size 4882323752

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4319980d0eea13197a43a1c1361974dd651e7b979044ff68518cec22afedc81b
+size 4882323744

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445788f0a5835159e56f0c58cc454b662507221aa2f3930103cc21a698dbefd6
+size 4882323744

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1042296855565962d6226c2f721b6d428d07ee692f113c3294a3a33e7496604c
+size 4857158272

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d760012ed000d7bb2e52261783200d92b84404c6a1c9e401aa201e16e4eb13
+size 4970416768

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d2c19a5904bcdd9ecfd5d12caf3cdc66d827d247d27d3ef91d61efcd24936a
+size 4970416744

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11efaac6943a776bd2bde73794eb188a17387105cb9fc9f6e89a72f4a3ebd0c2
+size 4479670264

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 78041665536}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.51.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.50.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.49.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.57.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.56.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.55.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.59.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.63.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.62.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.61.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.65.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.64.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.69.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.68.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.67.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.71.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.70.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.74.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.76.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.81.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.80.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.79.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.83.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.82.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.85.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.97.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_748]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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