初始化项目，由ModelHub XC社区提供模型

Model: Joseph717171/Mistral-10.7B-v0.2
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
+Mistral-10.7B-v0.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: apache-2.0
+---
+# Credit for the model card's description goes to ddh0 and mergekit
+# Looking for [Mistral-10.7B-Instruct-v0.2?](https://huggingface.co/ddh0/Mistral-10.7B-Instruct-v0.2)
+# Credit for access and conversion of Mistral-7B-v0.2 goes to alpindale (from MistalAI's weights to HF Transformers)
+# Mistral-10.7B-v0.2
+This is Mistral-10.7B-v0.2, a depth-upscaled version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf).
+
+This model is intended to be used as a basis for further fine-tuning, or as a drop-in upgrade from the original 7 billion parameter model.
+
+Paper detailing how Depth-Up Scaling works:  [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://arxiv.org/abs/2312.15166)
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 24]
+    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
+- sources:
+  - layer_range: [8, 32]
+    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf 
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf",
+  "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": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 24]
+    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
+- sources:
+  - layer_range: [8, 32]
+    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf 

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047e4f8f6b83c98bda1bba9fb505efce062266aaafa726e1987db1bc301f7615
+size 3925992176

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0440373a67457dca606ab05f7e129e95be20f5e099adf020bf9880f9fcaccd6
+size 3986826216

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d3c12dcf61eed3304aa0a98662d49a5b36b2413efa1c971c1af0b1907110a4
+size 3976357448

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b972121be9c7a6c21939baa47c3d4755123dd0ba5f6e5c0d1a62b10b634efe42
+size 3976357464

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fddabb592451364d4ea28ab8023e0d076d5c5c17f9f0b564553a36140da6f114
+size 3986875576

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0e73ba1620a8802e2d53710ab0c8928f2a713d598e5caa32293f306b45dd1d
+size 1610689944

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_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "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": false
+}