Upload folder using huggingface_hub

README.md

@@ -0,0 +1,47 @@
+---
+base_model:
+- mergekit-community/Moist_Theia_21B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mergekit-community/Moist_Theia_21B](https://huggingface.co/mergekit-community/Moist_Theia_21B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mergekit-community/Moist_Theia_21B
+    #no parameters necessary for base model
+  - model: mergekit-community/Moist_Theia_21B
+    parameters:
+      density: 0.2
+      weight: 0.8
+  - model: mergekit-community/Moist_Theia_21B
+    parameters:
+      density: 0.8
+      weight: 0.2
+
+merge_method: ties
+base_model: mergekit-community/Moist_Theia_21B
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mergekit-community/Moist_Theia_21B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 70,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+models:
+  - model: mergekit-community/Moist_Theia_21B
+    #no parameters necessary for base model
+  - model: mergekit-community/Moist_Theia_21B
+    parameters:
+      density: 0.2
+      weight: 0.8
+  - model: mergekit-community/Moist_Theia_21B
+    parameters:
+      density: 0.8
+      weight: 0.2
+
+merge_method: ties
+base_model: mergekit-community/Moist_Theia_21B
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0ccc3fd185ad697db803bf1c11bdc08dee025768c8c7dda753c0b5ae41cc1b
+size 4865489296

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e38cdc6bd20428297239e83c4850a9891eaccc7f2e4814e789380b01ca2a58
+size 4907529376

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa25e8e9d7c1e3fa0d30bf033f3baf33d664b837542f05387909ad41eedbb37c
+size 4907529384

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6eadf1170e4a45653fedbcaec3f89aef97b898d85f4bca9da56f19d5c78136
+size 4907529376

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb6996b10ace65ea438d18cf9c4c8419f3449acac9bcaf8fe786c672f4f8ea4
+size 4907529376

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001eb3d245af979074a53d18096eacf83e62ebe2c056937d25f1c5a9c525eac0
+size 4907529376

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bb4040120ffe69cd8ac1edf38253f66bea32e19e35ac7347f07929fccd8f97
+size 4907529376

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f62996f227e3072336757498d199c1c149ee8bb8a91b1b144672ba71975a091
+size 4907529384

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a86e8eb3e5c374942ab6c7a32972a7801bc8558460da643aced49553d59303
+size 1635843088

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 40853964800}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.61.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}