You can deploy this model and start earning money today!

RichardErkhov/
malhajar_-_Llama-2-13b-chat-tr-gguf

Name: malhajar_-_Llama-2-13b-chat-tr-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-2-13b-chat-tr - GGUF

Model creator: https://huggingface.co/malhajar/
Original model: https://huggingface.co/malhajar/Llama-2-13b-chat-tr/

Name	Quant method	Size
Llama-2-13b-chat-tr.Q2_K.gguf	Q2_K	4.52GB
Llama-2-13b-chat-tr.Q3_K_S.gguf	Q3_K_S	5.27GB
Llama-2-13b-chat-tr.Q3_K.gguf	Q3_K	5.9GB
Llama-2-13b-chat-tr.Q3_K_M.gguf	Q3_K_M	5.9GB
Llama-2-13b-chat-tr.Q3_K_L.gguf	Q3_K_L	6.45GB
Llama-2-13b-chat-tr.IQ4_XS.gguf	IQ4_XS	6.54GB
Llama-2-13b-chat-tr.Q4_0.gguf	Q4_0	6.86GB
Llama-2-13b-chat-tr.IQ4_NL.gguf	IQ4_NL	6.9GB
Llama-2-13b-chat-tr.Q4_K_S.gguf	Q4_K_S	5.54GB
Llama-2-13b-chat-tr.Q4_K.gguf	Q4_K	7.33GB
Llama-2-13b-chat-tr.Q4_K_M.gguf	Q4_K_M	2.53GB
Llama-2-13b-chat-tr.Q4_1.gguf	Q4_1	5.42GB
Llama-2-13b-chat-tr.Q5_0.gguf	Q5_0	8.36GB
Llama-2-13b-chat-tr.Q5_K_S.gguf	Q5_K_S	2.62GB
Llama-2-13b-chat-tr.Q5_K.gguf	Q5_K	1.76GB
Llama-2-13b-chat-tr.Q5_K_M.gguf	Q5_K_M	5.09GB
Llama-2-13b-chat-tr.Q5_1.gguf	Q5_1	8.89GB
Llama-2-13b-chat-tr.Q6_K.gguf	Q6_K	9.95GB
Llama-2-13b-chat-tr.Q8_0.gguf	Q8_0	12.88GB

Original model description:

datasets:

atasoglu/databricks-dolly-15k-tr language:
tr

Model Card for Model ID

malhajar/Llama-2-13b-chat-dolly-tr is a finetuned version of Llama-2-13b-hf using SFT Training. This model can answer information in turkish language as it is finetuned on a turkish dataset specifically databricks-dolly-15k-tr

Model Description

Developed by: Mohamad Alhajar
Language(s) (NLP): Turkish
Finetuned from model: meta-llama/Llama-2-13b-hf

Prompt Template

<s>[INST] <prompt> [/INST]

How to Get Started with the Model

Use the code sample provided in the original post to interact with the model.

python

from transformers import AutoTokenizer,AutoModelForCausalLM
 
model_id = "malhajar/Llama-2-7b-chat-dolly-tr"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "Türkiyenin en büyük şehir nedir?"
# For generating a response
prompt = '''
<s>[INST] {question}  [/INST]
'''
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,repetition_penalty=1.3
        top_p=0.95)
response = tokenizer.decode(output[0])

print(response)

RichardErkhov/malhajar_-_Llama-2-13b-chat-tr-gguf