Instructions to use tegana/model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tegana/model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "tegana/model")

Transformers

How to use tegana/model with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tegana/model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tegana/model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tegana/model

SGLang

How to use tegana/model 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 "tegana/model" \
    --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": "tegana/model",
		"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 "tegana/model" \
        --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": "tegana/model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tegana/model with Docker Model Runner:
```
docker model run hf.co/tegana/model
```

tegana commited on Mar 10

Commit

8035164

verified ·

1 Parent(s): 0f94d84

Model save

Browse files

Files changed (1) hide show

README.md +70 -0

README.md ADDED Viewed

	@@ -0,0 +1,70 @@

+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: model
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# model
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1739
+## 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
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
+- num_epochs: 3.0
+### Training results
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1464        | 1.1910 | 100  | 0.1870          |
+| 0.0811        | 2.3821 | 200  | 0.1739          |
+### Framework versions
+- PEFT 0.18.1
+- Transformers 5.2.0
+- Pytorch 2.9.0+cu126
+- Datasets 3.2.0
+- Tokenizers 0.22.2