KingNish / CodeMaster-v1-7b

CodeMaster v1 7b

CodeMaster v1 7b is a merge of the following models using LazyMergekit :

• microsoft/wavecoder-ultra-6.7b
• microsoft/wavecoder-ultra-6.7b

🧩 Configuration

slices:
- sources:
  - model: microsoft/wavecoder-ultra-6.7b
    layer_range:
    - 0
    - 32
  - model: microsoft/wavecoder-ultra-6.7b
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: microsoft/wavecoder-ultra-6.7b
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 = "KingNish/CodeMaster-v1-7b"
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=8096, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])