Instructions to use MedGm/Llama-Locali-Qwen2.5-Coder-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MedGm/Llama-Locali-Qwen2.5-Coder-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="MedGm/Llama-Locali-Qwen2.5-Coder-1.5B")
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("MedGm/Llama-Locali-Qwen2.5-Coder-1.5B")
model = AutoModelForCausalLM.from_pretrained("MedGm/Llama-Locali-Qwen2.5-Coder-1.5B", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MedGm/Llama-Locali-Qwen2.5-Coder-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MedGm/Llama-Locali-Qwen2.5-Coder-1.5B

SGLang

How to use MedGm/Llama-Locali-Qwen2.5-Coder-1.5B 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 "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B" \
    --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": "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B",
		"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 "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B" \
        --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": "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MedGm/Llama-Locali-Qwen2.5-Coder-1.5B with Docker Model Runner:
```
docker model run hf.co/MedGm/Llama-Locali-Qwen2.5-Coder-1.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-Locali-Qwen2.5-Coder-1.5B

Llama-Locali-Qwen2.5-Coder-1.5B-QLoRA merged into Qwen2.5-Coder-1.5B-Instruct (revision 2e1fd39), saved in FP16. Training details, results and limitations are on that page. The name prefix is explained there too (Llama 3.1 licence).

The adapter was evaluated served on the FP16 base, so merging into the full-precision base reproduces the evaluated model. I checked the merge on three chat prompts:

base + unmerged adapter vs merged model, FP32: largest logit difference 7e-5
FP16 copy vs FP32: same next token at every position

The merge script is training/merge_adapter.py in the project repository.

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("MedGm/Llama-Locali-Qwen2.5-Coder-1.5B")
model = AutoModelForCausalLM.from_pretrained("MedGm/Llama-Locali-Qwen2.5-Coder-1.5B", torch_dtype="auto")

or vllm serve MedGm/Llama-Locali-Qwen2.5-Coder-1.5B.

Built with Llama. Apache-2.0, with the Llama 3.1 Community License naming and attribution terms applying because of the training data.

Downloads last month: 718

Safetensors

Model size

2B params

Tensor type

F16

Model tree for MedGm/Llama-Locali-Qwen2.5-Coder-1.5B

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Finetuned

(230)

this model

Quantizations

1 model

MedGm
/

Llama-Locali-Qwen2.5-Coder-1.5B

Llama-Locali-Qwen2.5-Coder-1.5B

Model tree for MedGm/Llama-Locali-Qwen2.5-Coder-1.5B

Dataset used to train MedGm/Llama-Locali-Qwen2.5-Coder-1.5B