Upload folder using huggingface_hub

README.md

@@ -0,0 +1,29 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- scb10x/typhoon-7b
+- chargoddard/storytime-13b
+---
+
+# TyphoonTime-passthrough
+
+TyphoonTime-passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [scb10x/typhoon-7b](https://huggingface.co/scb10x/typhoon-7b)
+* [chargoddard/storytime-13b](https://huggingface.co/chargoddard/storytime-13b)
+
+## 🧩 Configuration
+
+\```yaml
+slices:
+  - sources:
+    - model: scb10x/typhoon-7b
+      layer_range: [0, 32]
+  - sources:
+    - model: chargoddard/storytime-13b
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+\```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "chargoddard/storytime-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+    - model: scb10x/typhoon-7b
+      layer_range: [0, 32]
+  - sources:
+    - model: chargoddard/storytime-13b
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab1fa3f0a555b4ffc71923963d9b3fac605d4a0a5dbeb5546fe884c0a8e387e
+size 1924877704

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759ce6559ab671b047246e1832908a8a9846890c08e01702eb11bc04942c5a12
+size 1979781456

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d3d994c078af287ef4b11989eb50c058b3fe127fd057f3a909616a0d6ee304
+size 1946243992

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bf687930d00b5e29682148eea161bf09808f02c8c3cc5c3690be882950dcf4
+size 1979781448

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd52e589f9467a2d968533138c5544986c60fce9ecb1b25f55a8b6b06b03f02
+size 1931544088

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca905c610241edd4d37cf5147d14fb7b4323a247d9e2b0fcd28d068c1c2499a7
+size 1999712240

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f982f27265f2e29d4be480f868354ac83fc5a2f033fac3a055c087fb16e8a06
+size 1882271616

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdff2d336b8031573305297c128a86d58cc92dd616f7db1ceacba58611e20d70
+size 1907416480

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32174f5f6eeb5178c2583e1820416b216071761b9ee2c4c0dcd07b7846393d3e
+size 1917929920

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aba6591d304bfb8d9d23a57190850af6c7dd20fa09c6213c58f94d560e17fcf
+size 1979781416

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58284d2b49f6e7eb1f22e5153a9518c2cb7353c9081175ca83f03a0f8ac5b355
+size 201345840

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 19650643968}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}