Instructions to use Emreyz03/fubbs-tr-rn-r2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Emreyz03/fubbs-tr-rn-r2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("RefinedNeuro/RN_TR_R2")
model = PeftModel.from_pretrained(base_model, "Emreyz03/fubbs-tr-rn-r2")

Transformers

How to use Emreyz03/fubbs-tr-rn-r2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Emreyz03/fubbs-tr-rn-r2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Emreyz03/fubbs-tr-rn-r2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Emreyz03/fubbs-tr-rn-r2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Emreyz03/fubbs-tr-rn-r2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Emreyz03/fubbs-tr-rn-r2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Emreyz03/fubbs-tr-rn-r2

SGLang

How to use Emreyz03/fubbs-tr-rn-r2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Emreyz03/fubbs-tr-rn-r2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Emreyz03/fubbs-tr-rn-r2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Emreyz03/fubbs-tr-rn-r2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Emreyz03/fubbs-tr-rn-r2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Emreyz03/fubbs-tr-rn-r2 with Docker Model Runner:
```
docker model run hf.co/Emreyz03/fubbs-tr-rn-r2
```

fubbs-tr-rn-r2

This model is a fine-tuned version of RefinedNeuro/RN_TR_R2 on the None dataset. It achieves the following results on the evaluation set:

Loss: nan

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 50
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Epoch	Step	Validation Loss
0.0521	100	nan
0.1043	200	nan
0.1564	300	nan
0.2086	400	nan
0.2607	500	nan
0.3128	600	nan
0.3650	700	nan
0.4171	800	nan
0.4692	900	nan
0.5214	1000	nan

Framework versions

PEFT 0.17.0
Transformers 4.55.0
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 5

Model tree for Emreyz03/fubbs-tr-rn-r2

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1

Finetuned

ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1

Finetuned

RefinedNeuro/RN_TR_R2

Adapter

(1)

this model