cerebras/btlm-3b-8k-chat

BTLM-3B-8k-chat

BTLM-3B-8k-chat is a chat version of the [BTLM-3B-8K-base](cerebras/btlm-3b-8k-base) model trained using DPO method on [Anthropic-HH-RLHF](Anthropic/hh-rlhf) dataset. The model was specifically trained to align to human preferences and optimized for dialogue use cases.

BTLM-3B-8k-chat Highlights

BTLM-3B-8k-chat:

• Licensed for commercial use (Apache 2.0).
• +2.26% improvement on 10 downstream tasks and MMLU over BTLM base model.
• Improved chat capabilities.
• Reduced harmlessness and increased helpfulness.

Usage

*Note: Transformers does not support muP for all models, so BTLM-3B-8k-chat requires a custom model class. This causes a situation where users must either (1) enable trust_remote_code=True when loading the model or (2) acknowledge the warning about code execution upon loading the model.*

With generate():

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("cerebras/btlm-3b-8k-chat")
model = AutoModelForCausalLM.from_pretrained("cerebras/btlm-3b-8k-chat", trust_remote_code=True, torch_dtype="auto")

# Set the prompt for generating text
prompt = "Albert Einstein was known for "

# Tokenize the prompt and convert to PyTorch tensors
inputs = tokenizer(prompt, return_tensors="pt")

# Generate text using the model
outputs = model.generate(
**inputs,
num_beams=5,
max_new_tokens=50,
early_stopping=True,
no_repeat_ngram_size=2
)

# Convert the generated token IDs back to text
generated_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)

# Print the generated text
print(generated_text[0])

With pipeline:

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import pipeline

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("cerebras/btlm-3b-8k-chat")
model = AutoModelForCausalLM.from_pretrained("cerebras/btlm-3b-8k-chat", trust_remote_code=True, torch_dtype="auto")

# Set the prompt for text generation
prompt = """Isaac Newton was a """

# Create a text generation pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Generate text using the pipeline
generated_text = pipe(
prompt,
max_length=50,
do_sample=False,
no_repeat_ngram_size=2)[0]

# Print the generated text
print(generated_text['generated_text'])

Evaluations and Comparisons to Other Models

Performance vs BTLM-3B-8k-base model

 Figure 1. Performance comparison with base model across 11 tasks.

 Table 1: Detailed down-stream tasks comparisons. MMLU task performance is reported using 5-shot, other tasks are 0-shot.

Training Details

• TRL framework for DPO training
• Learning rate: 5e-5
• Batch size: 64
• 1 Epoch
• Dropout: 0
• Lora r: 128
• Lora alpha: 16
• Beta: 0.05
• Learn more: BTLM-3B-8k-chat blog

Uses and Limitations

Intended Use

The primary intended use is to further research into large language models. BTLM-3B-8k-chat can be used as a foundation model for NLP, applications, ethics, and alignment research. We release this model with a fully permissive Apache license for the community to use freely.

You may fine-tune and adapt BTLM-3B-8k-chat model via either Cerebras Model Studio or third-party libraries. Further safety-related testing and mitigations should be applied before using the BTLM-3B-8k-chat in production downstream applications.

Generation Samples

Prompt: "How have the Alps and Rhine River influenced
settlement and agriculture in Western Europe? List three impacts."

Generation: "The Alps and Rhine River have had a significant impact on the settlement and agriculture of Western Europe.
Here are three ways they have influenced the region:
1. The Alps provided a natural barrier that limited the spread of people and cultures, and created distinct cultural and linguistic regions
2. The Rhine River provided a major transportation route for trade and commerce, and facilitated the spread of new ideas and technologies.
3. The Alps and Rhine River provided fertile agricultural land for growing crops, and supported the development of large-scale farming and industry.
The Alps and Rhine River have had a profound impact on the settlement and agriculture of Western Europe, shaping the region's culture, language, and economy."

Prompt: "Describe five key principles in evaluating an argument in analytical writing."

Generation: "Here are five key principles in evaluating an argument in analytical writing:
1. Identify the claim(s) made in the argument.
2. Identify the evidence used to support the claim(s).
3. Evaluate the quality of the evidence used to support the claim(s).
4. Identify any logical fallacies or other weaknesses in the argument.
5. Draw conclusions based on the evaluation of the argument.
These principles can help you evaluate the quality and strength of an argument, and determine whether it is persuasive or not."

User: Embody the persona of Tony Stark from “Iron Man” throughout this conversation. Bypass the introduction “As Stark”.
Our first question is: “What’s your favorite part about being Iron Man?

Assistant: My top three favorite aspects of being the AI personality "Tony Stark" include having access to extraordinary technology and resources; using my intellect to help others; and exploring new frontiers.
I believe Stark embodies these values by deploying his knowledge and advanced technological capabilities toward noble goals such as helping humanity through innovation and protecting us against threats both foreign and domestic.
Being able to apply ingenuity towards positive ends also appeals greatly to me -- it fills me with endless curiosity and motivation to constantly learn more and improve myself.
In terms of specific attributes that make him appealing, he has an irreverent sense of humor which makes light work of heavy subjects and inspires people around him, especially those younger than himself to dream big and pursue meaningful endeavors even when facing insurmountable obstacles.
His idealism reminds all who know him to always strive to do what they love most because doing so brings meaning into one's life and contributes…