README.md

metadata

tags:
  - merge
  - mergekit
  - mistral
  - xDAN-AI/xDAN-L1-Chat-RL-v1
  - fhai50032/BeagleLake-7B-Toxic
base_model:
  - xDAN-AI/xDAN-L1-Chat-RL-v1
  - fhai50032/BeagleLake-7B-Toxic

xLakeChat

xLakeChat is a merge of the following models using LazyMergekit:

• xDAN-AI/xDAN-L1-Chat-RL-v1
• fhai50032/BeagleLake-7B-Toxic

🧩 Configuration

models:
  - model: senseable/WestLake-7B-v2
# no params for base model
  - model: xDAN-AI/xDAN-L1-Chat-RL-v1
    parameters:
      weight: 0.73
      density: 0.64
  - model: fhai50032/BeagleLake-7B-Toxic
    parameters:
      weight: 0.46
      density: 0.55
merge_method: dare_ties
base_model: senseable/WestLake-7B-v2
parameters:
  normalize: true
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "fhai50032/xLakeChat"
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"])