Upload folder using huggingface_hub

README.md

@@ -0,0 +1,50 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- vortexmergekit
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Papa-mistral
+
+Hey there! 👋 Welcome to the Papa-mistral! This is a merge of multiple models brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl).
+
+Let's see what we've got in this merge:
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 🚀
+
+## 🧩 Configuration
+
+```yaml
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [4, 12]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [8, 16]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [12, 20]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [16, 24]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [20, 28]
+    model: mistralai/Mistral-7B-Instruct-v0.2

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "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": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [4, 12]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [8, 16]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [12, 20]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [16, 24]
+    model: mistralai/Mistral-7B-Instruct-v0.2
+- sources:
+  - layer_range: [20, 28]
+    model: mistralai/Mistral-7B-Instruct-v0.2

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30d6ca731ea9295f1bdc4f5d6aa4985e3485df666c753a808b60add169d6e9c
+size 1979748192

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f059512e778a28d2e4e51f6095a1088da013f714254cdc645f615f11a2557015
+size 1979798024

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e54ca518619a1c60aa0ec8deab23d2c93299e68d106a7b568a3afdf95259a8
+size 1912689792

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cddd0cbc3e7dcc66f8ff780cf3d617bb2939854ca2b54cd3e557f2931b24cd4
+size 1744900120

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323aa77e6caac9599651a83b4d6941ceca10a578aad39aee0b0f6cedd3549ae5
+size 1889570424

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8edbaeb5b05a9aa83c6f75cb3c01db347bc130a4ccc93f82b8bf81a6960a2c3e
+size 1996575968

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9d27ad75fb00898ceb29f0f20e641358a4b7210d9fa7dfde9db7ea8d56cbc0
+size 1895911944

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd6cbac55e0aed8dfdbd98cd4f8eefee8f23ac0a9d720acd796ff250251fdcd
+size 1979781416

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f641c38b7e3d047cf917f258063003e435e82722d663923318c20dce4d82e54d
+size 1979781432

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29827216a3e8ab9fc51411af41ae420c10ef76c1411a189772a654f558c1785
+size 1889645144

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2b6c99e001d5c9e84dd93a54b3c8b15500c07be484ca0fb65b94a6180f04a6
+size 1979781432

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e1f9dc35eb4a686d7b028ff308e3314b41c9612b6e1c95824bdb437c8c93ed
+size 234914496

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.embed_tokens.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00012.safetensors", "lm_head.weight": "model-00010-of-00012.safetensors", "model.norm.weight": "model-00010-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}