IceShark-Coder-9b / README.md
powermove72's picture
Upload folder using huggingface_hub
d05c97a verified
metadata
base_model:
  - S-miguel/The-Trinity-Coder-7B
  - powermove72/Shark-1
tags:
  - merge
  - mergekit
  - lazymergekit
  - S-miguel/The-Trinity-Coder-7B
  - powermove72/Shark-1

IceShark-Coder-9b

IceShark-Coder-9b is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
    - model: S-miguel/The-Trinity-Coder-7B
      layer_range: [0, 16]
  - sources:
    - model: powermove72/Shark-1
      layer_range: [8, 32]
merge_method: passthrough
tokenizer_source: union
dtype: float16
    ```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "powermove72/IceShark-Coder-9b"
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"])