metadata
base_model:
- appvoid/arco-2
tags:
- merge
- mergekit
- lazymergekit
- appvoid/arco-2
acheron-c
acheron-c is a merge of the following models using LazyMergekit:
🧩 Configuration
merge_method: ties
base_model: h2oai/h2o-danube3-500m-base
dtype: float16
# ------------------ TIES Parameters ------------------
parameters:
normalize: true
int8_mask: true
models:
- model: appvoid/arco-2
parameters:
density: 0.5 # Keep 50% of arco's largest deltas
weight: 1.0 # Full weighting of arco's delta
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "bfuzzy1/acheron-c"
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"])