初始化项目，由ModelHub XC社区提供模型

Model: Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+datasets:
+- Locutusque/inst_mix_v2_top_100k
+language:
+- en
+pipeline_tag: text-generation
+widget:
+- text: >-
+    <|USER|> Design a Neo4j database and Cypher function snippet to Display
+    Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners.
+    Implement if/else or switch/case statements to handle different conditions
+    related to the Consent. Provide detailed comments explaining your control
+    flow and the reasoning behind each decision. <|ASSISTANT|> 
+- text: '<|USER|> Write me a story about a magical place. <|ASSISTANT|> '
+- text: >-
+    <|USER|> Write me an essay about the life of George Washington
+    <|ASSISTANT|> 
+- text: '<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> '
+- text: >-
+    <|USER|> Craft me a list of some nice places to visit around the world.
+    <|ASSISTANT|> 
+- text: >-
+    <|USER|> How to manage a lazy employee: Address the employee verbally. Don't
+    allow an employee's laziness or lack of enthusiasm to become a recurring
+    issue. Tell the employee you're hoping to speak with them about workplace
+    expectations and performance, and schedule a time to sit down together.
+    Question: To manage a lazy employee, it is suggested to talk to the
+    employee. True, False, or Neither? <|ASSISTANT|> 
+inference:
+  parameters:
+    temperature: 0.5
+    do_sample: true
+    top_p: 0.5
+    top_k: 30
+    max_new_tokens: 250
+    repetition_penalty: 1.15
+tags:
+- merge
+---
+# LocutusqueXFelladrin-TinyMistral248M-Instruct
+This model was created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using mergekit. After the two models were merged, the resulting model was further trained on ~20,000 examples on the Locutusque/inst_mix_v2_top_100k at a low learning rate to further normalize weights. The following is the YAML config used to merge:
+
+```yaml
+models:
+  - model: Felladrin/TinyMistral-248M-SFT-v4
+    parameters:
+      weight: 0.5
+  - model: Locutusque/TinyMistral-248M-Instruct
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16
+```
+
+The resulting model combines the best of both worlds. With Locutusque/TinyMistral-248M-Instruct's coding capabilities and reasoning skills, and Felladrin/TinyMistral-248M-SFT-v4's low hallucination and instruction-following capabilities. The resulting model has an incredible performance considering its size.
+
+## Evaluation
+Found in the Open LLM Leaderboard.

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|ASSISTANT|>": 32003,
+  "<|USER|>": 32004,
+  "<|bos|>": 32000,
+  "<|endoftext|>": 32001,
+  "[PAD]": 32002
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/sebastian/Desktop/mergekit/merged",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32005
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568d8306a2c70680557ac6be9999377d71982cd9740013d7718c107025929c6d
+size 496060584

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4c12460c6c3f3f2ca6bcdff81fd3e1a521820876631df78c804392ef2f6603
+size 496085574

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|ASSISTANT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|USER|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|ASSISTANT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|USER|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 1536,
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}