初始化项目，由ModelHub XC社区提供模型

Model: Infermatic/MN-12B-Inferor-v0.0
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
+- nothingiisreal/MN-12B-Starcannon-v3
+- anthracite-org/magnum-v4-12b
+- Fizzarolli/MN-12b-Sunrose
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64be962a38953777feaabfc0/DncyZQ6V2NAEfFeEerxcw.png)
+
+
+# Inferor
+
+My first merge yay!
+
+#### This was made thanks to [infermatic.ai](https://infermatic.ai/)
+
+### Recommended settings on: [Infermatic/MN 12B Inferor v0.0 Article](https://infermatic.ai/infermatic-mn-12b-inferor-v0-0/)
+
+Thanks everyone that is using it and providing feedback. ily - svak
+
+Our discord server is open for discussions for this model.
+---
+
+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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2](https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2)
+* [nothingiisreal/MN-12B-Starcannon-v3](https://huggingface.co/nothingiisreal/MN-12B-Starcannon-v3)
+* [Fizzarolli/MN-12b-Sunrose](https://huggingface.co/Fizzarolli/MN-12b-Sunrose)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: anthracite-org/magnum-v4-12b
+dtype: bfloat16
+merge_method: model_stock
+slices:
+- sources:
+  - layer_range: [0, 40]
+    model: Fizzarolli/MN-12b-Sunrose
+  - layer_range: [0, 40]
+    model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
+  - layer_range: [0, 40]
+    model: nothingiisreal/MN-12B-Starcannon-v3
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v4-12b
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "anthracite-org/magnum-v4-12b",
+  "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": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+base_model: anthracite-org/magnum-v4-12b
+dtype: bfloat16
+merge_method: model_stock
+slices:
+- sources:
+  - layer_range: [0, 40]
+    model: Fizzarolli/MN-12b-Sunrose
+  - layer_range: [0, 40]
+    model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
+  - layer_range: [0, 40]
+    model: nothingiisreal/MN-12B-Starcannon-v3
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v4-12b

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e10d64982958f184e04279c4c82675d3f5b7ea3e57233894d0fe6de82b51f2b
+size 4865489336

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de3ec07cda9713bdbab30b40d56fae42ec4ff1fb76599f31fa471bac6ab911d
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286019109c933ca9bceabcdb307b95a4afd152569e4af9c7482f117729a4756e
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8611a3c6dd3850a7b265d3cf1d371e5581239075f4952152e69bba8e7c032dbd
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a66672b49bc5c0284978816a5aa6990df00fcd7519f1861ba48add6e108799
+size 4907529392

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba3c07c153070f7da72cf185508260ca07d9a037a703a44a42da9c790924271
+size 9264441