Phind-CodeLlama-34B-v2-Codefuse-CodeLlama-34B-dare-ties
Phind-CodeLlama-34B-v2-Codefuse-CodeLlama-34B-dare-ties is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: Phind/Phind-CodeLlama-34B-v2
parameters:
density: 0.5
weight: 0.6
# No parameters necessary for base model
- model: codefuse-ai/CodeFuse-CodeLlama-34B
parameters:
density: 0.5
weight: 0.4
merge_method: dare_ties
base_model: Phind/Phind-CodeLlama-34B-v2
parameters:
int8_mask: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/Phind-CodeLlama-34B-v2-Codefuse-CodeLlama-34B-dare-ties"
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"])