Thanks to @s3nh for the great quantization notebook code.

Original model card

Buy @s3nh a coffee if you like this project ;)

Description

GGUF Format model files for This project.

GGUF Specs

GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:

Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. mmap compatibility: models can be loaded using mmap for fast loading and saving. Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for inference or for identifying the model.

Original model card

試製-暮光-7B

試製-暮光-7B　是用LazyMergekit融合以下模型生成的：

這是一個實驗模型，目的是爲了檢驗套用在不同語言上的高品質模型調教是否能夠轉移（此模型爲英文到中文）。

shizhi-twilight-7B

shizhi-twilight-7B is a merge of the following models using LazyMergekit:

This is an experiment product on checking whether high quality fine-tuning on one language (English) could be transferred to another language (Mandarin) leveraging Slerp merge method.

🧩 Configuration

slices:
  - sources:
      - model: MediaTek-Research/Breeze-7B-Instruct-v0_1
        layer_range: [0, 32]
      - model: argilla/CapybaraHermes-2.5-Mistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "lipcut/shizhi-twilight-7B"
messages = [{"role": "user", "content": "什麼是大型語言模型?"}]

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"])