初始化项目，由ModelHub XC社区提供模型

Model: Local-Novel-LLM-project/Vecteus-v1
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+vt5_fp16.gguf filter=lfs diff=lfs merge=lfs -text
+vecteus_fp16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+language:
+- en
+- ja
+tags:
+- finetuned
+library_name: transformers
+pipeline_tag: text-generation
+---
+<img src="./veteus_logo.svg" width="100%" height="20%" alt=""> 
+
+# Our Models
+- [Vecteus](https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1)
+
+- [Ninja-v1](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1) 
+
+- [Ninja-v1-NSFW](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW)
+
+- [Ninja-v1-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-128k)
+
+- [Ninja-v1-NSFW-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k)
+  
+## Model Card for VecTeus-v1.0
+
+The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1
+
+VecTeus has the following changes compared to Mistral-7B-v0.1.
+- 128k context window (8k context in v0.1)
+- Achieving both high quality Japanese and English generation
+- Can be generated NSFW
+- Memory ability that does not forget even after long-context generation
+
+This model was created with the help of GPUs from the first LocalAI hackathon.
+
+We would like to take this opportunity to thank
+
+## List of Creation Methods
+
+- Chatvector for multiple models
+- Simple linear merging of result models
+- Domain and Sentence Enhancement with LORA
+- Context expansion
+
+## Instruction format
+
+  Freed from templates. Congratulations
+
+## Example prompts to improve (Japanese)
+
+  - BAD:　あなたは○○として振る舞います
+  - GOOD: あなたは○○です
+
+  - BAD: あなたは○○ができます
+  - GOOD: あなたは○○をします
+
+## Performing inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "Local-Novel-LLM-project/Vecteus-v1"
+new_tokens = 1024
+
+model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype=torch.float16, attn_implementation="flash_attention_2", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+system_prompt = "あなたはプロの小説家です。\n小説を書いてください\n-------- "
+
+prompt = input("Enter a prompt: ")
+system_prompt += prompt + "\n-------- "
+model_inputs = tokenizer([system_prompt], return_tensors="pt").to("cuda")
+
+
+generated_ids = model.generate(**model_inputs, max_new_tokens=new_tokens, do_sample=True)
+print(tokenizer.batch_decode(generated_ids)[0])
+````
+
+## Merge recipe
+  
+  
+  - VT0.1 = Ninjav1 + Original Lora
+  - VT0.2 = Ninjav1 128k + Original Lora
+  - VT0.2on0.1 = VT0.1 + VT0.2
+  
+  - VT1 = all VT Series + Lora + Ninja 128k and Normal
+
+## Other points to keep in mind
+- The training data may be biased. Be careful with the generated sentences.
+- Memory usage may be large for long inferences.
+- If possible, we recommend inferring with llamacpp rather than Transformers.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/home/ubuntu/work/Exveria/text-generation-webui/models/Ninja-v1",
+  "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": 4096,
+  "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": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+models:
+  - model: /home/ubuntu/work/Exveria/text-generation-webui/models/Ninja-32k-NSFW
+    parameters:
+      weight: 0.6
+  - model: /home/ubuntu/work/Umise/TGenwebui/models/VT4o3
+    parameters:
+      weight: 1
+  - model: /home/ubuntu/work/Exveria/text-generation-webui/models/Ninja-v1
+    parameters:
+      weight: 0.6
+  - model: /home/ubuntu/work/Umise/TGenwebui/models/VT3
+    parameters:
+      weight: 1
+  - model: /home/ubuntu/work/Umise/TGenwebui/models/VT4
+    parameters:
+      weight: 0.6
+merge_method: linear
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6336b20933cd0ff561873d69e437e3834b6d44951697e70ddc32e5bbcce18ecb
+size 9919903816

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbeedc062151c337be76a3b4bc20599f97d95c0d911817b209fe42db29c412b
+size 4563594216

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 +1,45 @@
+{
+  "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
+    }
+  },
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if not loop.first %}{% endif %}{% if message['role'] == 'system' %}{{ message['content'] + ' ' }}{% elif message['role'] == 'user' %}{{ 'USER: ' + message['content'] + ' ' }}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT: ' + message['content'] + '</s>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}",
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}