Downloads · 30 days
15
8% of all-time downloads
purrgpt-community/Tiny-Purr-350M-merged
Tiny-Purr-350M-merged is a text generation model from purrgpt-community. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is the full merged version of Tiny-Purr-350M. This model combines the LoRA adapter with the base LiquidAI/LFM2-350M model into a single, standalone model.
Downloads · 30 days
15
8% of all-time downloads
All-time downloads
177
Public
Parameters
354M
1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors709 MB · 99%
From the Hugging Face model README
This is the full merged version of Tiny-Purr-350M. This model combines the LoRA adapter with the base LiquidAI/LFM2-350M model into a single, standalone model.
Note: If you want the lightweight LoRA adapter version instead, see purrgpt-community/Tiny-Purr-350M.
This model is a fine-tuned version of LFM2-350M trained on the Tiny-Purr-2 dataset to generate conversational responses with a casual, friendly, and cat-themed personality.
Key characteristics:
Model Type: Full merged model (ready to use without LoRA adapters)
Training Method: LoRA fine-tuning (now merged into weights)
Max sequence length: 1024 tokens
This model is designed for:
Not recommended for:
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"purrgpt-community/Tiny-Purr-350M-merged",
device_map="auto",
torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("purrgpt-community/Tiny-Purr-350M-merged")
prompt = "<|user|>\nWhat is notable about the ICSE 2002 conference?\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=150,
temperature=0.7,
top_p=0.9,
do_sample=True
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
If you want a system prompt use this:
prompt = "<|system|>\nYou are Tiny-Purr\n<|user|>\nWhat is notable about the ICSE 2002 conference?\n<|assistant|>\n"
<|user|>
What is notable about the ICSE 2002 conference?
<|assistant|>
oh, the 2002 icse conference, you say? sounds like a lot of stuff, user. *purrrr*.
the icse conference was a big deal. they brought together top scientists and
researchers from all over the world to discuss cutting-edge topics in science
and technology. the 2002 one was particularly notable because it focused on
areas like nanotechnology, artificial intelligence, and bioengineering. it
really opened up new avenues for research and collaboration.
did you know they also got a lot of international media coverage? that's
something. it's pretty much like the world's biggest science fair, but with
even more top-tier scientists.
The model expects prompts in the following format:
<|user|>
[Your question or prompt here]
<|assistant|>
The model will then generate a response following the assistant tag.
This model was created by fine-tuning LFM2-350M using LoRA, then merging the adapter weights into the base model.
LoraConfig(
r=16,
lora_alpha=32,
target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM"
)
If you use this model, please cite:
@misc{lfm2-tiny-purr-2024,
title={Tiny-Purr-350M: A Conversational Fine-tune of LFM2},
author={purrgpt-community},
year={2024},
publisher={HuggingFace},
howpublished={\url{https://huggingface.co/purrgpt-community/Tiny-Purr-350M-merged}}
}
@misc{liquid2024lfm,
title={Liquid Foundation Models},
author={Liquid AI Team},
year={2024},
publisher={HuggingFace},
howpublished={\url{https://huggingface.co/LiquidAI/LFM2-350M}}
}
This model is released under the Apache 2.0 license, inheriting from the base LFM2-350M model.
Made with 🐱 and LoRA, now fully merged for your convenience!