Instructions to use SanatanSinghVishen/sift-1b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use SanatanSinghVishen/sift-1b-gguf with PEFT:
```
Task type is invalid.
```

How to use SanatanSinghVishen/sift-1b-gguf with Transformers:

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

pipe = pipeline("text-generation", model="SanatanSinghVishen/sift-1b-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SanatanSinghVishen/sift-1b-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SanatanSinghVishen/sift-1b-gguf 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 SanatanSinghVishen/sift-1b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SanatanSinghVishen/sift-1b-gguf: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 SanatanSinghVishen/sift-1b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SanatanSinghVishen/sift-1b-gguf: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 SanatanSinghVishen/sift-1b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Use Docker

docker model run hf.co/SanatanSinghVishen/sift-1b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use SanatanSinghVishen/sift-1b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SanatanSinghVishen/sift-1b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SanatanSinghVishen/sift-1b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SanatanSinghVishen/sift-1b-gguf:Q4_K_M

SGLang

How to use SanatanSinghVishen/sift-1b-gguf 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 "SanatanSinghVishen/sift-1b-gguf" \
    --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": "SanatanSinghVishen/sift-1b-gguf",
		"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 "SanatanSinghVishen/sift-1b-gguf" \
        --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": "SanatanSinghVishen/sift-1b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SanatanSinghVishen/sift-1b-gguf with Ollama:
```
ollama run hf.co/SanatanSinghVishen/sift-1b-gguf:Q4_K_M
```
Unsloth Desktop

How to use SanatanSinghVishen/sift-1b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SanatanSinghVishen/sift-1b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SanatanSinghVishen/sift-1b-gguf with Docker Model Runner:
```
docker model run hf.co/SanatanSinghVishen/sift-1b-gguf:Q4_K_M
```

Lemonade

How to use SanatanSinghVishen/sift-1b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sift-1b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SanatanSinghVishen/sift-1b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SanatanSinghVishen/sift-1b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SanatanSinghVishen/sift-1b-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "SanatanSinghVishen/sift-1b-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Sift-1B: Deterministic Function Calling & Intent Routing SLM

Sift-1B is a hyper-specialized 1.5B-parameter Small Language Model (SLM) engineered specifically to sift structured JSON parameters out of unstructured user prompts and shift routing workloads away from expensive cloud LLMs.

Trained via a two-stage Supervised Fine-Tuning (SFT) + Direct Preference Optimization (DPO) pipeline on top of Qwen/Qwen2.5-1.5B-Instruct, Sift-1B strips away all conversational fluff ("Sure! Here is your JSON:") and outputs strict, machine-readable JSON on the very first attempt.

Developed & Designed by: Sanatan Singh
Base Architecture: Qwen/Qwen2.5-1.5B-Instruct
Model Type: Causal Language Model + QLoRA Adapter + GGUF Quantization (q4_k_m)
License: MIT
GitHub Repository: SanatanSinghVishen/Sift-1B
GGUF Quantized: SanatanSinghVishen/sift-1b-gguf
DPO Golden Adapter: SanatanSinghVishen/sift-1b-dpo
SFT Adapter: SanatanSinghVishen/sift-1b-sft

📊 Comprehensive Benchmark Results

Evaluated across 50 holdout test cases containing UNSEEN function schemas (not present in training) comparing Base Qwen vs. SFT vs. DPO (Golden Release Checkpoint-750):

Evaluation Metric	Base Model (Qwen2.5-1.5B)	Sift-1B (SFT)	🏆 Sift-1B (DPO Golden)	Delta vs Base
Tool Selection Accuracy	70.0%	98.0%	100.0% ✅	+30.0%
Parameter Extraction Accuracy	34.0%	80.0%	88.0% ✅	+54.0%
JSON Parse / Validity Rate	96.0%	98.0%	100.0% ✅	+4.0%
Zero Markdown / Fluff Rate	76.0%	100.0%	100.0% ✅	+24.0%
Zero Hallucination Rate	100.0%	100.0%	100.0% ✅	0% Hallucinations
Average Latency (TTFT)	2,277 ms	1,734 ms	1,714 ms ⚡	25% Faster

⚙️ Technical Specifications & GGUF Metadata

GGUF Architecture Parameters

Quantization Format: q4_k_m (4-bit medium K-quantization)
GGUF File Size: 940.4 MB (0.94 GB)
Context Length (n_ctx): 32,768 tokens
Embedding Dimensions (n_embd): 1,536
Feed-Forward Network Dimension (n_ff): 8,960
Attention Heads (n_head): 12
Key-Value Heads (n_head_kv): 2 (Grouped-Query Attention / GQA)
RMS Norm Epsilon: 1e-6
RoPE Theta Base (rope_theta): 1,000,000.0
Vocabulary Size: 151,936 tokens (ChatML format)

Training Hyperparameters

Stage 1: Supervised Fine-Tuning (SFT)

Dataset: 10,000 ChatML multi-turn function calling samples derived from Salesforce/xlam-60k
Quantization: QLoRA 4-bit NF4 (load_in_4bit=True)
LoRA Rank ($r$): 16 | LoRA Alpha ($\alpha$): 32 | Dropout: 0
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Batch Size: 1 per device | Gradient Accumulation: 8 (Effective batch size = 8)
Learning Rate: 2.0e-4 (Cosine schedule, warmup_ratio=0.05)
Epochs: 2 (2,500 total steps) | Optimizer: adamw_8bit

Stage 2: Direct Preference Optimization (DPO)

Dataset: Synthetically mutated preference pairs ($y_w$ = clean JSON, $y_l$ = markdown fluff/hallucinations)
DPO Temperature ($\beta$): 0.1 | Loss Type: sigmoid
Learning Rate: 5.0e-6 (Cosine schedule, warmup_ratio=0.1)
Epochs: 1 (2,500 total steps, golden checkpoint at step 750)

🚀 Quick Start Code Examples

1. Ollama (Local CLI & Server)

# Run directly from Hugging Face Hub:
ollama run hf.co/SanatanSinghVishen/sift-1b-gguf

Downloads last month: 134

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for SanatanSinghVishen/sift-1b-gguf

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(1384)

this model