Instructions to use asjadilahi/danAI-55M-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use asjadilahi/danAI-55M-Reasoning with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf asjadilahi/danAI-55M-Reasoning:Q4_K_M

Use Docker

docker model run hf.co/asjadilahi/danAI-55M-Reasoning:Q4_K_M

LM Studio
Jan

vLLM

How to use asjadilahi/danAI-55M-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asjadilahi/danAI-55M-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asjadilahi/danAI-55M-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/asjadilahi/danAI-55M-Reasoning:Q4_K_M

Ollama
How to use asjadilahi/danAI-55M-Reasoning with Ollama:
```
ollama run hf.co/asjadilahi/danAI-55M-Reasoning:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use asjadilahi/danAI-55M-Reasoning with Docker Model Runner:
```
docker model run hf.co/asjadilahi/danAI-55M-Reasoning:Q4_K_M
```

Lemonade

How to use asjadilahi/danAI-55M-Reasoning with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull asjadilahi/danAI-55M-Reasoning:Q4_K_M

Run and chat with the model

lemonade run user.danAI-55M-Reasoning-Q4_K_M

List all available models

lemonade list

Atomic Chat

danAI-55M-Reasoning / config.json

asjadilahi

Initial release of danAI-55M-Reasoning (54.5M SLM with Native Agentic Tools and <think> CoT)

66287ca verified 2 months ago

Raw History Blame Contribute Delete

660 Bytes

{
  "architectures": [
    "CausalLM"
  ],
  "model_type": "danai",
  "vocab_size": 32768,
  "hidden_size": 512,
  "intermediate_size": 1376,
  "num_hidden_layers": 12,
  "num_attention_heads": 8,
  "num_key_value_heads": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "max_position_embeddings": 2048,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-05,
  "use_cache": true,
  "tie_word_embeddings": true,
  "rope_theta": 10000.0,
  "rope_scaling": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "5.15.0",
  "total_parameters": 54525952,
  "model_name": "danAI-55M-Reasoning",
  "author": "Asjad Ilahi (asjadilahi)",
  "license": "apache-2.0"
}

	{
	"architectures": [
	"CausalLM"
	],
	"model_type": "danai",
	"vocab_size": 32768,
	"hidden_size": 512,
	"intermediate_size": 1376,
	"num_hidden_layers": 12,
	"num_attention_heads": 8,
	"num_key_value_heads": 4,
	"head_dim": 64,
	"hidden_act": "silu",
	"max_position_embeddings": 2048,
	"initializer_range": 0.02,
	"rms_norm_eps": 1e-05,
	"use_cache": true,
	"tie_word_embeddings": true,
	"rope_theta": 10000.0,
	"rope_scaling": null,
	"torch_dtype": "bfloat16",
	"transformers_version": "5.15.0",
	"total_parameters": 54525952,
	"model_name": "danAI-55M-Reasoning",
	"author": "Asjad Ilahi (asjadilahi)",
	"license": "apache-2.0"
	}