Instructions to use Neel003/IRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neel003/IRA with Transformers:

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

pipe = pipeline("text-generation", model="Neel003/IRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neel003/IRA")
model = AutoModelForCausalLM.from_pretrained("Neel003/IRA")
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 Neel003/IRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neel003/IRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neel003/IRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neel003/IRA

SGLang

How to use Neel003/IRA 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 "Neel003/IRA" \
    --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": "Neel003/IRA",
		"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 "Neel003/IRA" \
        --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": "Neel003/IRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neel003/IRA with Docker Model Runner:
```
docker model run hf.co/Neel003/IRA
```

Neel003 commited on Feb 2

Commit

10be81f

verified ·

1 Parent(s): 75353f9

Update README.md

Browse files

Files changed (1) hide show

README.md +33 -1

README.md CHANGED Viewed

@@ -6,4 +6,36 @@ tags:
 - reasoning
 - custom-finetune
 - moe
----

 - reasoning
 - custom-finetune
 - moe
+license: apache-2.0
+base_model:
+- mistralai/Mixtral-8x7B-v0.1
+library_name: transformers
+---
+# IRA (Integrated Reasoning Architecture)
+**IRA** is a proprietary, custom fine-tuned model developed by **Neel003**. It is an advanced Integrated Reasoning Architecture optimized for high-precision logic, complex reasoning, and advanced synthesis tasks.
+## Model Highlights
+- **Developer:** Neel003
+- **Model Name:** IRA
+- **Parameters:** 47B
+- **Architecture:** Mixture-of-Experts (MoE)
+- **Format:** Safetensors (19 Shards)
+## Technical Usage
+IRA is compatible with the `transformers` library. For high-performance inference, loading with 4-bit quantization is recommended.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+model_id = "Neel003/IRA"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_4bit=True
+)