You can deploy this model and start earning money today!

RichardErkhov/
atasoglu_-_gemma-2-2b-tr-gguf

Name: atasoglu_-_gemma-2-2b-tr-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2-2b-tr - GGUF

Model creator: https://huggingface.co/atasoglu/
Original model: https://huggingface.co/atasoglu/gemma-2-2b-tr/

Name	Quant method	Size
gemma-2-2b-tr.Q2_K.gguf	Q2_K	1.15GB
gemma-2-2b-tr.IQ3_XS.gguf	IQ3_XS	1.22GB
gemma-2-2b-tr.IQ3_S.gguf	IQ3_S	1.27GB
gemma-2-2b-tr.Q3_K_S.gguf	Q3_K_S	1.27GB
gemma-2-2b-tr.IQ3_M.gguf	IQ3_M	1.3GB
gemma-2-2b-tr.Q3_K.gguf	Q3_K	1.36GB
gemma-2-2b-tr.Q3_K_M.gguf	Q3_K_M	1.36GB
gemma-2-2b-tr.Q3_K_L.gguf	Q3_K_L	1.44GB
gemma-2-2b-tr.IQ4_XS.gguf	IQ4_XS	1.47GB
gemma-2-2b-tr.Q4_0.gguf	Q4_0	1.52GB
gemma-2-2b-tr.IQ4_NL.gguf	IQ4_NL	1.53GB
gemma-2-2b-tr.Q4_K_S.gguf	Q4_K_S	1.53GB
gemma-2-2b-tr.Q4_K.gguf	Q4_K	1.59GB
gemma-2-2b-tr.Q4_K_M.gguf	Q4_K_M	1.59GB
gemma-2-2b-tr.Q4_1.gguf	Q4_1	1.64GB
gemma-2-2b-tr.Q5_0.gguf	Q5_0	1.75GB
gemma-2-2b-tr.Q5_K_S.gguf	Q5_K_S	1.75GB
gemma-2-2b-tr.Q5_K.gguf	Q5_K	1.79GB
gemma-2-2b-tr.Q5_K_M.gguf	Q5_K_M	1.79GB
gemma-2-2b-tr.Q5_1.gguf	Q5_1	1.87GB
gemma-2-2b-tr.Q6_K.gguf	Q6_K	2.0GB
gemma-2-2b-tr.Q8_0.gguf	Q8_0	2.59GB

Original model description:

base_model: unsloth/gemma-2-2b-bnb-4bit datasets:

myzens/alpaca-turkish-combined language:
en
tr license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
gemma2
trl

Uploaded model

Developed by: atasoglu
License: apache-2.0
Finetuned from model : unsloth/gemma-2-2b-bnb-4bit

This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Usage

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.

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "atasoglu/gemma-2-2b-tr",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)

FastLanguageModel.for_inference(model) # Enable native 2x faster inference

alpaca_prompt = """Aşağıda verilen talimat ve giriş ifadelerine uygun bir cevap yaz.

### Talimat:
Aşağıdaki programlama dillerinden hangisi yapay zeka çalışmak için daha uygundur?
Sebebini açıkla.

### Giriş:
Python, C++, Java, Rust

### Cevap:
"""
inputs = tokenizer(alpaca_prompt, return_tensors="pt").to("cuda")
outputs = model.generate(
    **inputs,
    max_new_tokens=128,
    do_sample=True,
    temperature=0.2,
    repetition_penalty=1.15,
    top_k=20,
    top_p=0.7,
)

generated_tokens = outputs[:, inputs.input_ids.shape[1]:]
response = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(response)
# Output: ['C++ veya Python en iyi seçenektir çünkü bu iki dilde çok sayıda yapay zeka araçları vardır. Bu araçlar, veri analizi, öğrenme algoritmaları ve karar verme süreçlerini kolaylaştırır. Ayrıca, her ikisinin de güçlü bir kütüphanesi olması da önemlidir.']

RichardErkhov/atasoglu_-_gemma-2-2b-tr-gguf

Original model description:

Uploaded model

Usage

RichardErkhov/
atasoglu_-_gemma-2-2b-tr-gguf