Instructions to use mekala-2402/final_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mekala-2402/final_model with Transformers:

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

pipe = pipeline("text-generation", model="mekala-2402/final_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mekala-2402/final_model")
model = AutoModelForCausalLM.from_pretrained("mekala-2402/final_model", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use mekala-2402/final_model with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mekala-2402/final_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mekala-2402/final_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": "mekala-2402/final_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mekala-2402/final_model

SGLang

How to use mekala-2402/final_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 "mekala-2402/final_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": "mekala-2402/final_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 "mekala-2402/final_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": "mekala-2402/final_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mekala-2402/final_model with Docker Model Runner:
```
docker model run hf.co/mekala-2402/final_model
```

final_model / README.md

mekala-2402

Upload README.md with huggingface_hub

b842037 verified about 1 year ago

preview code

Raw History Blame Contribute Delete

1.34 kB

---
library_name: transformers
license: apache-2.0
base_model: unsloth/Llama-3.2-3B-Instruct
tags:
- merged
- adapter
- peft
---
# final_model - Merged Model
This model is a merged version of the adapter [mekala-2402/model_long](https://huggingface.co/mekala-2402/model_long) 
with base model [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct).
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
    "mekala-2402/final_model",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("mekala-2402/final_model")
# Generate text
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## Model Details
- **Original adapter**: mekala-2402/model_long
- **Base model**: unsloth/Llama-3.2-3B-Instruct
- **Merged using**: PEFT library
## GGUF Conversion
To convert this merged model to GGUF format, you can use:
1. [llama.cpp convert script](https://github.com/ggerganov/llama.cpp)
2. [Hugging Face GGUF Space](https://huggingface.co/spaces/ggml-org/gguf-my-repo)
## License
This model inherits the license from the base model: unsloth/Llama-3.2-3B-Instruct

	---
	library_name: transformers
	license: apache-2.0
	base_model: unsloth/Llama-3.2-3B-Instruct
	tags:
	- merged
	- adapter
	- peft
	---

	# final_model - Merged Model

	This model is a merged version of the adapter [mekala-2402/model_long](https://huggingface.co/mekala-2402/model_long)
	with base model [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct).

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model = AutoModelForCausalLM.from_pretrained(
	"mekala-2402/final_model",
	torch_dtype=torch.float16,
	device_map="auto"
	)
	tokenizer = AutoTokenizer.from_pretrained("mekala-2402/final_model")

	# Generate text
	inputs = tokenizer("Your prompt here", return_tensors="pt")
	outputs = model.generate(**inputs, max_length=100)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Model Details
	- Original adapter: mekala-2402/model_long
	- Base model: unsloth/Llama-3.2-3B-Instruct
	- Merged using: PEFT library

	## GGUF Conversion
	To convert this merged model to GGUF format, you can use:
	1. [llama.cpp convert script](https://github.com/ggerganov/llama.cpp)
	2. [Hugging Face GGUF Space](https://huggingface.co/spaces/ggml-org/gguf-my-repo)

	## License
	This model inherits the license from the base model: unsloth/Llama-3.2-3B-Instruct