Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- RatanRohith/NeuralPizza-7B-V0.2
+- NeuralNovel/Valor-7B-v0.1
+---
+
+# NeuralPizza-Valor-7B-Merge-slerp
+
+NeuralPizza-Valor-7B-Merge-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [RatanRohith/NeuralPizza-7B-V0.2](https://huggingface.co/RatanRohith/NeuralPizza-7B-V0.2)
+* [NeuralNovel/Valor-7B-v0.1](https://huggingface.co/NeuralNovel/Valor-7B-v0.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: RatanRohith/NeuralPizza-7B-V0.2
+        layer_range: [0, 32]
+      - model: NeuralNovel/Valor-7B-v0.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: RatanRohith/NeuralPizza-7B-V0.2
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "RatanRohith/NeuralPizza-7B-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": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: RatanRohith/NeuralPizza-7B-V0.2
+        layer_range: [0, 32]
+      - model: NeuralNovel/Valor-7B-v0.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: RatanRohith/NeuralPizza-7B-V0.2
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b054333792918d2e1d1b00d891e0c7497696e68d5b3436e1f79d20d91491e629
+size 436225048

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94acf55e67283da2d0845d99762125593c644b41d4019b1e3bacaf55de79f26f
+size 436225048

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2cd8c333fe853f6e698b6a0696db855c43dfbde4c8dd8dce5ccf286ac5ffe88
+size 698369160

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0393a859438136acd0b64cd62c6dbe48d0c89f86f5f6df1f577e65f89db23fe
+size 436225048

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f33cb129faf253071bd65a58d8f9d8003001e0ae748ed5bc99c28e50e0ff446
+size 436225048

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a547d0958a89bd055a4e73216563d1e6bb1e7c08317342ee8d3ccaa18f43e95a
+size 698377432

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138b6029efbac219389cf7a097c2a662d11f7d4776dcaa28a93374bd1dc3b7a5
+size 436225048

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1675842c7bbbb54c5966e4b77b052e59be4d25c353a2a49a4ffe31af8baffc64
+size 436225048

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.0.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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 +1,46 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "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": true
+}