π«π· Calme-3
Collection
Here you can find all the new Calme-3 models
β’
25 items
β’
Updated
β’
6
This is avery small model, so it might not perform well for some prompts and may be sensitive to hyper parameters. I would appreciate any feedback to see if I can fix any issues in the next iteration. β€οΈ
This model is an advanced iteration of the powerful Qwen/Qwen2.5-3B
, specifically fine-tuned to enhance its capabilities in generic domains.
All GGUF models are available here: MaziyarPanahi/calme-3.1-instruct-3b-GGUF
Leaderboard 2 coming soon!
This model uses ChatML
prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
# Use a pipeline as a high-level helper
from transformers import pipeline
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.1-instruct-3b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.1-instruct-3b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-3b")
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.