Jamba Models not Supported yet

[chintanckg]

NotImplementedError: Unsloth: tiiuae/falcon-mamba-7b not supported yet!
Make an issue to https://github.com/unslothai/unsloth!

Steps to reproduce:

from unsloth import FastLanguageModel
import torch
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.


falcon_mamba = r"tiiuae/falcon-mamba-7b"

model_ootb, tokenizer = FastLanguageModel.from_pretrained(
    
    model_name = falcon_mamba, # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)