metadata

library_name: transformers
license: apache-2.0

WestLake-7B-v2-laser-truthy-dpo

Process

Trained cognitivecomputations/WestLake-7B-v2-laser on jondurbin/truthy-dpo-v0.1
Completed 2 epochs
2e-5 learning rate

Code Example

from transformers import AutoTokenizer
import transformers
import torch

model = "macadeliccc/WestLake-7B-v2-laser-truthy-dpo"
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"])

Evaluations

Evaluated the GGUF for usability reasons. EQ-Bench uses Ooba for inference.

----Benchmark Complete----
2024-01-31 14:38:14
Time taken: 18.9 mins
Prompt Format: ChatML
Model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo-GGUF
Score (v2): 75.15
Parseable: 171.0
---------------
Batch completed
Time taken: 19.0 mins
---------------

GGUF

GGUF versions are available here