初始化项目，由ModelHub XC社区提供模型

Model: CultriX/NeuralTrixlaser-bf16
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 +1,78 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- bardsai/jaskier-7b-dpo-v3.3
+- Kquant03/NeuralTrix-7B-dpo-laser
+- CultriX/NeuralTrix-v4-bf16
+- CultriX/NeuralTrix-V2
+base_model:
+- bardsai/jaskier-7b-dpo-v3.3
+- Kquant03/NeuralTrix-7B-dpo-laser
+- CultriX/NeuralTrix-v4-bf16
+- CultriX/NeuralTrix-V2
+license: apache-2.0
+---
+
+# NeuralTrixlaser-bf16
+
+NeuralTrixlaser-bf16 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [bardsai/jaskier-7b-dpo-v3.3](https://huggingface.co/bardsai/jaskier-7b-dpo-v3.3)
+* [Kquant03/NeuralTrix-7B-dpo-laser](https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-laser)
+* [CultriX/NeuralTrix-v4-bf16](https://huggingface.co/CultriX/NeuralTrix-v4-bf16)
+* [CultriX/NeuralTrix-V2](https://huggingface.co/CultriX/NeuralTrix-V2)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: eren23/dpo-binarized-NeuralTrix-7B
+    # no parameters necessary for base model
+  - model: bardsai/jaskier-7b-dpo-v3.3
+    parameters:
+      density: 0.65
+      weight: 0.4
+  - model: Kquant03/NeuralTrix-7B-dpo-laser
+    parameters:
+      density: 0.6
+      weight: 0.35
+  - model: CultriX/NeuralTrix-v4-bf16
+    parameters:
+      density: 0.55
+      weight: 0.15
+  - model: CultriX/NeuralTrix-V2
+    parameters:
+      density: 0.55
+      weight: 0.15
+merge_method: dare_ties
+base_model: eren23/dpo-binarized-NeuralTrix-7B
+parameters:
+  int8_mask: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "CultriX/"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "eren23/dpo-binarized-NeuralTrix-7B",
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,25 @@
+
+models:
+  - model: eren23/dpo-binarized-NeuralTrix-7B
+    # no parameters necessary for base model
+  - model: bardsai/jaskier-7b-dpo-v3.3
+    parameters:
+      density: 0.65
+      weight: 0.4
+  - model: Kquant03/NeuralTrix-7B-dpo-laser
+    parameters:
+      density: 0.6
+      weight: 0.35
+  - model: CultriX/NeuralTrix-v4-bf16
+    parameters:
+      density: 0.55
+      weight: 0.15
+  - model: CultriX/NeuralTrix-V2
+    parameters:
+      density: 0.55
+      weight: 0.15
+merge_method: dare_ties
+base_model: eren23/dpo-binarized-NeuralTrix-7B
+parameters:
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830a1048584a24a8ee3c41a7346fc69ccda0ad3d0d43e657428bc070818a6fd2
+size 9942981696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9ea805f149afe9412e94d38e63f480ad5ffc46ac3b7709702e4ce835c8ab63
+size 4540516344

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 +1,40 @@
+{
+  "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": [],
+  "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
+}