Instructions to use Artples/L-MChat-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Artples/L-MChat-Small with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Artples/L-MChat-Small")
model = AutoModelForCausalLM.from_pretrained("Artples/L-MChat-Small")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Artples/L-MChat-Small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Artples/L-MChat-Small

SGLang

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

Docker Model Runner
How to use Artples/L-MChat-Small with Docker Model Runner:
```
docker model run hf.co/Artples/L-MChat-Small
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

L-MChat-Small

This was a test of mine how small merges perform, because there are a lot of 7b merges and higher but not a lot of 2b merges.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: Weyaxi/Einstein-v4-phi2
    layer_range:
    - 0
    - 32
  - model: rhysjones/phi-2-orange-v2
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: rhysjones/phi-2-orange-v2
parameters:
  t:
  - filter: self_attn
    value:
    - 0
    - 0.5
    - 0.3
    - 0.7
    - 1
  - filter: mlp
    value:
    - 1
    - 0.5
    - 0.7
    - 0.3
    - 0
  - value: 0.5
dtype: bfloat16

Usage

Use it with the ChatML format, you can also use the Inference-API for this Model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.14
AI2 Reasoning Challenge (25-Shot)	61.60
HellaSwag (10-Shot)	75.90
MMLU (5-Shot)	57.41
TruthfulQA (0-shot)	49.94
Winogrande (5-shot)	74.98
GSM8k (5-shot)	58.98