You can deploy this model and start earning money today!

RichardErkhov/
malhajar_-_Qwen1.5-7B-turkish-gguf

Name: malhajar_-_Qwen1.5-7B-turkish-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen1.5-7B-turkish - GGUF

Model creator: https://huggingface.co/malhajar/
Original model: https://huggingface.co/malhajar/Qwen1.5-7B-turkish/

Name	Quant method	Size
Qwen1.5-7B-turkish.Q2_K.gguf	Q2_K	2.89GB
Qwen1.5-7B-turkish.IQ3_XS.gguf	IQ3_XS	3.18GB
Qwen1.5-7B-turkish.IQ3_S.gguf	IQ3_S	3.32GB
Qwen1.5-7B-turkish.Q3_K_S.gguf	Q3_K_S	3.32GB
Qwen1.5-7B-turkish.IQ3_M.gguf	IQ3_M	3.48GB
Qwen1.5-7B-turkish.Q3_K.gguf	Q3_K	3.65GB
Qwen1.5-7B-turkish.Q3_K_M.gguf	Q3_K_M	3.65GB
Qwen1.5-7B-turkish.Q3_K_L.gguf	Q3_K_L	3.93GB
Qwen1.5-7B-turkish.IQ4_XS.gguf	IQ4_XS	4.02GB
Qwen1.5-7B-turkish.Q4_0.gguf	Q4_0	4.2GB
Qwen1.5-7B-turkish.IQ4_NL.gguf	IQ4_NL	4.22GB
Qwen1.5-7B-turkish.Q4_K_S.gguf	Q4_K_S	4.23GB
Qwen1.5-7B-turkish.Q4_K.gguf	Q4_K	4.44GB
Qwen1.5-7B-turkish.Q4_K_M.gguf	Q4_K_M	4.44GB
Qwen1.5-7B-turkish.Q4_1.gguf	Q4_1	4.62GB
Qwen1.5-7B-turkish.Q5_0.gguf	Q5_0	5.03GB
Qwen1.5-7B-turkish.Q5_K_S.gguf	Q5_K_S	5.03GB
Qwen1.5-7B-turkish.Q5_K.gguf	Q5_K	5.15GB
Qwen1.5-7B-turkish.Q5_K_M.gguf	Q5_K_M	5.15GB
Qwen1.5-7B-turkish.Q5_1.gguf	Q5_1	5.44GB
Qwen1.5-7B-turkish.Q6_K.gguf	Q6_K	5.91GB
Qwen1.5-7B-turkish.Q8_0.gguf	Q8_0	7.65GB

Original model description:

license: apache-2.0 datasets:

malhajar/alpaca-gpt4-tr language:
tr
en

Model Card for Model ID

malhajar/Mistral-7B-Instruct-v0.2-turkish is a finetuned version of Qwen1.5-7B using SFT Training and Freeze method. This model can answer information in a chat format as it is finetuned specifically on instructions specifically alpaca-gpt4-tr

Model Description

Developed by: Mohamad Alhajar
Language(s) (NLP): Turkish
Finetuned from model: Qwen1.5-7B

Prompt Template

### Instruction:

<prompt> (without the <>)

### Response:

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/Qwen1.5-7B-turkish"
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 = '''
### Instruction:  {question} ### Response:
'''
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,trust_remote_code=True,)
response = tokenizer.decode(output[0])

print(response)

RichardErkhov/malhajar_-_Qwen1.5-7B-turkish-gguf