初始化项目，由ModelHub XC社区提供模型

Model: ikarius/Meta-Llama-3.1-8B-Instruct-Abliterated-NF4
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 +1,83 @@
+---
+license: llama3.1
+language:
+- en
+base_model:
+- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- llama3.1
+- abliteration
+- quantized
+- nf4
+- bitsandbytes
+- 4-bit
+---
+
+📜 Model Description
+
+This model is a 4-bit NormalFloat (NF4) quantized version of the Meta-Llama-3.1-8B-Instruct-Abliterated, fine-tuned by mlabonne.
+
+The quantization process significantly reduces the memory footprint (VRAM usage) and improves inference speed, making it highly accessible for deployment on consumer-grade GPUs and limited-resource hardware, while maintaining high performance due to the nature of the NF4 method.
+🔗 Original Model Source
+
+    Original Model Name: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
+
+    Original Base Model: Llama 3.1 8B Instruct
+
+    Original Description: A version of Llama 3.1 8B Instruct that has undergone "Abliteration" (further fine-tuning) to enhance its capabilities and alignment.
+
+⚙️ Quantization Details
+
+    Quantization Technique: NF4 (NormalFloat 4-bit)
+
+    Library Used: Typically implemented using bitsandbytes via the Hugging Face transformers library.
+
+    Purpose: To enable loading and running the model in 4-bit precision, drastically cutting down VRAM requirements.
+
+🛠️ How to Use the Model (4-bit Loading)
+
+This model is intended to be used with the Hugging Face transformers library and bitsandbytes for 4-bit loading.
+💻 Installation
+
+To utilize the 4-bit configuration, you must have the necessary libraries installed:
+```Bash
+pip install torch transformers accelerate bitsandbytes
+```
+
+# Python Usage Example
+
+```Python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "ikarius/Meta-Llama-3.1-8B-Instruct-Abliterated-NF4"
+
+# 1. Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
+
+# 2. Run Inference using the Instruct template
+messages = [
+    {"role": "system", "content": "You are a helpful and friendly AI assistant."},
+    {"role": "user", "content": "What is the main benefit of 4-bit NF4 quantization?"}
+]
+
+# Apply the Llama 3.1 chat template
+input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    temperature=0.7,
+    do_sample=True,
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```

chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b24bd1c7f913fdf6a6039adf4390c3ae3d53e74980247cf6dfcc977eea58a0
+size 4652072866

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8005050c5e27c8232d9ce04f03631ce67bcc362c80fc57079bda23b498695c20
+size 1050673280

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}