Instructions to use KrisMinchev/train-bioR-concat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KrisMinchev/train-bioR-concat with Transformers:

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

pipe = pipeline("text-generation", model="KrisMinchev/train-bioR-concat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KrisMinchev/train-bioR-concat")
model = AutoModelForCausalLM.from_pretrained("KrisMinchev/train-bioR-concat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KrisMinchev/train-bioR-concat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KrisMinchev/train-bioR-concat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KrisMinchev/train-bioR-concat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KrisMinchev/train-bioR-concat

SGLang

How to use KrisMinchev/train-bioR-concat 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 "KrisMinchev/train-bioR-concat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KrisMinchev/train-bioR-concat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "KrisMinchev/train-bioR-concat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KrisMinchev/train-bioR-concat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KrisMinchev/train-bioR-concat with Docker Model Runner:
```
docker model run hf.co/KrisMinchev/train-bioR-concat
```

train-bioR-concat

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.6559

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: 0.001
train_batch_size: 24
eval_batch_size: 24
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 96
total_eval_batch_size: 96
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
training_steps: 41803
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2076	0.0239	1000	1.8223
1.2901	0.0478	2000	1.8245
1.1528	0.0718	3000	1.8674
1.0056	0.0957	4000	1.9692
0.8399	0.1196	5000	2.0165
0.7892	0.1435	6000	1.9441
0.7658	0.1674	7000	1.8904
0.7284	0.1914	8000	1.8260
0.7217	0.2153	9000	1.8162
0.7122	0.2392	10000	1.7559
0.7055	0.2631	11000	1.7974
0.6943	0.2871	12000	1.7621
0.6942	0.3110	13000	1.7651
0.6868	0.3349	14000	1.7228
0.6817	0.3588	15000	1.7558
0.6911	0.3827	16000	1.7466
0.6889	0.4067	17000	1.7291
0.6798	0.4306	18000	1.6921
0.675	0.4545	19000	1.7139
0.6779	0.4784	20000	1.6933
0.6851	0.5023	21000	1.7136
0.675	0.5263	22000	1.6874
0.6747	0.5502	23000	1.6950
0.6724	0.5741	24000	1.6884
0.6631	0.5980	25000	1.6873
0.6671	0.6220	26000	1.6983
0.6645	0.6459	27000	1.6729
0.658	0.6698	28000	1.6809
0.6605	0.6937	29000	1.6656
0.6599	0.7176	30000	1.6704
0.6591	0.7416	31000	1.6679
0.6664	0.7655	32000	1.6555
0.6608	0.7894	33000	1.6487
0.6609	0.8133	34000	1.6522
0.6553	0.8372	35000	1.6502
0.6527	0.8612	36000	1.6568
0.6648	0.8851	37000	1.6587
0.6515	0.9090	38000	1.6471
0.65	0.9329	39000	1.6461
0.65	0.9568	40000	1.6499
0.6533	0.9808	41000	1.6559

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 2

Safetensors

Model size

0.4B params

Tensor type

F32