Downloads · 30 days
27
52% of all-time downloads
phi_35_ttt_pd_merge_linear
ihughes15234/phi_35_ttt_pd_merge_linear
phi_35_ttt_pd_merge_linear is a machine learning model from ihughes15234. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
phi35tttpdmergelinear is a merge of the following models using LazyMergekit: ihughes15234/phi35tictactoedpo5epochv7 ihughes15234/phi35pddpo10epoch1200
All-time downloads
52
Public
Parameters
3.8B
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024
- SHA
- d9556b42
Base models
Model card
From the Hugging Face model README
phi_35_ttt_pd_merge_linear
phi_35_ttt_pd_merge_linear is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: ihughes15234/phi35_tictactoe_dpo5epoch_v7
parameters:
weight: 0.5
- model: ihughes15234/phi35_pd_dpo10epoch_1200
parameters:
weight: 0.5
merge_method: linear
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ihughes15234/phi_35_ttt_pd_merge_linear"
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"])
- Type
- llama
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024