README.md

metadata

base_model:
  - Jebadiah/Aria-coder-7b
  - Jebadiah/Aria-rp-coder-7b
tags:
  - merge
  - mergekit
  - lazymergekit
  - Jebadiah/Aria-coder-7b
  - Jebadiah/Aria-rp-coder-7b

Aria-coder-plus-7b

Aria-coder-plus-7b is a merge of the following models using LazyMergekit:

• Jebadiah/Aria-coder-7b
• Jebadiah/Aria-rp-coder-7b

🧩 Configuration

name: Aria-coder-plus-7b
merge_method: arcee_fusion
base_model: Jebadiah/Aria-coder-7b
models:
  - model: Jebadiah/Aria-coder-7b
    parameters:
      weight: 0.8

  - model: Jebadiah/Aria-rp-coder-7b
    parameters:
      weight: 0.6

dtype: float32
out_dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Jebadiah/Aria-coder-plus-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"])