phillama-prune20

phillama-prune20 is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: raincandy-u/phillama-3.8b-v1
        layer_range: [0, 18]
  - sources:
      - model: raincandy-u/phillama-3.8b-v1
        layer_range: [21, 32]
merge_method: passthrough
dtype: bfloat16

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "aipib/phillama-prune20"
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"])
Downloads last month
84
Safetensors
Model size
3.48B params
Tensor type
BF16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for aipib/phillama-prune20

Finetuned
(2)
this model