Quantization made by Richard Erkhov.

WestSeverus-10.7B - GGUF

Model creator: https://huggingface.co/FelixChao/
Original model: https://huggingface.co/FelixChao/WestSeverus-10.7B/

Name	Quant method	Size
WestSeverus-10.7B.Q2_K.gguf	Q2_K	3.73GB
WestSeverus-10.7B.IQ3_XS.gguf	IQ3_XS	4.14GB
WestSeverus-10.7B.IQ3_S.gguf	IQ3_S	4.37GB
WestSeverus-10.7B.Q3_K_S.gguf	Q3_K_S	4.34GB
WestSeverus-10.7B.IQ3_M.gguf	IQ3_M	4.51GB
WestSeverus-10.7B.Q3_K.gguf	Q3_K	4.84GB
WestSeverus-10.7B.Q3_K_M.gguf	Q3_K_M	4.84GB
WestSeverus-10.7B.Q3_K_L.gguf	Q3_K_L	5.26GB
WestSeverus-10.7B.IQ4_XS.gguf	IQ4_XS	5.43GB
WestSeverus-10.7B.Q4_0.gguf	Q4_0	5.66GB
WestSeverus-10.7B.IQ4_NL.gguf	IQ4_NL	5.72GB
WestSeverus-10.7B.Q4_K_S.gguf	Q4_K_S	5.7GB
WestSeverus-10.7B.Q4_K.gguf	Q4_K	6.02GB
WestSeverus-10.7B.Q4_K_M.gguf	Q4_K_M	6.02GB
WestSeverus-10.7B.Q4_1.gguf	Q4_1	6.27GB
WestSeverus-10.7B.Q5_0.gguf	Q5_0	6.89GB
WestSeverus-10.7B.Q5_K_S.gguf	Q5_K_S	6.89GB
WestSeverus-10.7B.Q5_K.gguf	Q5_K	7.08GB
WestSeverus-10.7B.Q5_K_M.gguf	Q5_K_M	7.08GB
WestSeverus-10.7B.Q5_1.gguf	Q5_1	7.51GB
WestSeverus-10.7B.Q6_K.gguf	Q6_K	8.2GB
WestSeverus-10.7B.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - FelixChao/WestSeverus-7B-DPO-v2 - FelixChao/WestSeverus-7B-DPO-v2

WestSeverus-10.7B

WestSeverus-10.7B is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
    - model: FelixChao/WestSeverus-7B-DPO-v2
      layer_range: [0, 24]
  - sources:
    - model: FelixChao/WestSeverus-7B-DPO-v2
      layer_range: [8, 32]
merge_method: passthrough
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "FelixChao/WestSeverus-10.7B"
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"])