Instructions to use mrplexar/PortfolioLLM-RAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrplexar/PortfolioLLM-RAG with Transformers:

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

pipe = pipeline("text-generation", model="mrplexar/PortfolioLLM-RAG")
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("mrplexar/PortfolioLLM-RAG")
model = AutoModelForCausalLM.from_pretrained("mrplexar/PortfolioLLM-RAG", 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 mrplexar/PortfolioLLM-RAG with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mrplexar/PortfolioLLM-RAG

SGLang

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

Docker Model Runner
How to use mrplexar/PortfolioLLM-RAG with Docker Model Runner:
```
docker model run hf.co/mrplexar/PortfolioLLM-RAG
```

mrplexar commited on May 7

Commit

277d113

verified ·

1 Parent(s): 065d05d

Upload 6 files

Browse files

Files changed (6) hide show

README.md +30 -0
chat_template.jinja +6 -0
config.json +40 -0
generation_config.json +7 -0
tokenizer.json +0 -0
tokenizer_config.json +18 -0

README.md ADDED Viewed

	@@ -0,0 +1,30 @@

+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+tags:
+- text-generation-inference
+- transformers
+- smollm2
+- portfolio-agent
+- roleplay
+- gappu
+---
+# 🌌 PortfolioLLM-RAG (GAPPU AI)
+**GAPPU** (Goddess-infused Advanced Portrayal and Presentation Unit) is a specialized fine-tuned model based on **SmolLM2-360M-Instruct**.
+It is designed to serve as a divine and graceful AI assistant for Arpit Ramesan's portfolio.
+## 🌟 Model Details
+- **Architecture**: SmolLM2
+- **Parameters**: 360M
+- **Fine-tuning Technique**: QLoRA (4-bit quantization)
+- **Primary Function**: Portfolio Assistant / Conversational Agent
+- **Personality**: Elegant, Serene, Highly Intelligent
+- **Regional Context**: Thalassery, Kerala, India
+## 🚀 Usage
+This model is intended to be used via the Hugging Face Inference API or integrated into the GAPPU Chat interface.
+## 🛠️ Training
+The model was fine-tuned on a curated dataset of Arpit Ramesan's professional achievements, research publications, and creative works, augmented with a "divine flowery" persona.

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,6 @@

+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.5.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.1"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}