Instructions to use rudrashah/RLM-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rudrashah/RLM-mini with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rudrashah/RLM-mini")
model = AutoModelForCausalLM.from_pretrained("rudrashah/RLM-mini")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rudrashah/RLM-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rudrashah/RLM-mini

SGLang

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

Docker Model Runner
How to use rudrashah/RLM-mini with Docker Model Runner:
```
docker model run hf.co/rudrashah/RLM-mini
```

RLM-mini

RLM-mini is a 7.2 Billion parameter model,RLM-mini is designed to provide a robust and versatile natural language processing (NLP) capability, leveraging the strengths of two foundational models. By combining models from different sources, RLM-mini aims to inherit diverse linguistic features and training data nuances, resulting in improved performance across a wide range of NLP tasks. This includes more robust understanding and generation capabilities, especially in handling nuanced and context-heavy queries. The fine-tuning process integrates the best practices and optimizations from both parent models. This ensures that RLM-mini not only maintains high accuracy but also delivers responses more efficiently.

It is base model and requires Fine tuning.

Two Merged Models

Usage

Direct Model

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rudrashah/RLM-mini")
model = AutoModelForCausalLM.from_pretrained("rudrashah/RLM-mini")

input_token = tokenizer("How to make Pav Bhaji?", return_tensors="pt")
output = model.generate(**input_token, max_length=250)
output = tokenizer.decode(output[0])

Using Pipeline

from transformers import AutoTokenizer
import transformers
import torch

model = "rudrashah/RLM-mini"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

BF16