Trendyol-LLM-8B-T1

206

23

8.0B

2 languages

license:apache-2.0

by

Trendyol

Language Model

OTHER

8B params

New

206 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

18GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

8GB+ RAM

Code Examples

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

🚀 Quick-startpythontransformers

import transformers
import torch

model_id = "Trendyol/Trendyol-LLM-8B-T1"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.bfloat16,
        "attn_implementation": "flash_attention_2",
        "device_map": "auto"
    }
)

messages = [
    {"role": "system", "content": "Sen yardımsever bir asistansın."},
    {"role": "user",   "content": "Mona Lisa tablosu hakkında kısa bir özet yazar mısın?"}
]

outputs = pipeline(messages, 
                   return_full_text=False,
                   max_new_tokens=2048
                  )
assistant_response = outputs[0]["generated_text"].strip()
print(assistant_response)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.