Phitor
Phitor is a merge of the following models using LazyMergekit:
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
- Venkman42/Phiter
𧩠Configuration
dtype: float16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 4]
model: Venkman42/Phiter
- sources:
- layer_range: [2, 6]
model: Venkman42/Phiter
- sources:
- layer_range: [4, 8]
model: Venkman42/Phiter
- sources:
- layer_range: [6, 10]
model: Venkman42/Phiter
- sources:
- layer_range: [8, 12]
model: Venkman42/Phiter
- sources:
- layer_range: [10, 14]
model: Venkman42/Phiter
- sources:
- layer_range: [12, 16]
model: Venkman42/Phiter
- sources:
- layer_range: [14, 18]
model: Venkman42/Phiter
- sources:
- layer_range: [16, 20]
model: Venkman42/Phiter
- sources:
- layer_range: [18, 22]
model: Venkman42/Phiter
- sources:
- layer_range: [20, 24]
model: Venkman42/Phiter
- sources:
- layer_range: [22, 26]
model: Venkman42/Phiter
- sources:
- layer_range: [24, 28]
model: Venkman42/Phiter
- sources:
- layer_range: [26, 30]
model: Venkman42/Phiter
- sources:
- layer_range: [28, 32]
model: Venkman42/Phiter
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Venkman42/Phitor"
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
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Venkman42/Phitor
Base model
Venkman42/Phiter