from unsloth import FastLanguageModel
import torch


model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "Ashishkr/Gemma-7B-COT-LoRA-1024R",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)



FastLanguageModel.for_inference(model)
inputs = tokenizer(
[
    alpaca_prompt.format(
        "given a number identify if it is an even number, if its even,  square it and add 5 to it. if its odd , get me the square root of the number", # instruction
        "12", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 2048, use_cache = True)
tokenizer.batch_decode(outputs)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for Ashishkr/Gemma-7B-COT-LoRA-1024R

Finetuned
(203)
this model