Akicou/foreigner-Test

Serpent-02-Tiny

Serpent-02-Tiny is a merge of the following models using LazyMergekit:

• uukuguy/speechless-code-mistral-orca-7b-v1.0

🧩 Configuration

slices:
  - sources:
      - model: uukuguy/speechless-code-mistral-orca-7b-v1.0
        layer_range: [0, 32]
  - sources:
      - model: decapoda-research/Adrastea-7b-v1.0
        layer_range: [0, 32]
merge_method: slerp
base_model: LatitudeGames/Muse-12B
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.5, 0.7, 0.8, 0.9]
    - filter: mlp
      value: [0.8, 0.7, 0.5, 0.3, 0.2]
    - value: 0.5
allow_crimes: true
force_architecture: true
merge_moe: true          # enable merging for mixture-of-experts
moe_strategy: average    # collapse experts into dense FFN
dtype: bfloat16
copy_tokenizer: true

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Akicou/Serpent-02-Tiny"
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"])