Instructions to use ankitkushwaha90/tech3space3-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ankitkushwaha90/tech3space3-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="ankitkushwaha90/tech3space3-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ankitkushwaha90/tech3space3-0.6B")
model = AutoModelForCausalLM.from_pretrained("ankitkushwaha90/tech3space3-0.6B")
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]:]))

llama-cpp-python

How to use ankitkushwaha90/tech3space3-0.6B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ankitkushwaha90/tech3space3-0.6B",
	filename="model.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ankitkushwaha90/tech3space3-0.6B 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 ankitkushwaha90/tech3space3-0.6B
# Run inference directly in the terminal:
llama cli -hf ankitkushwaha90/tech3space3-0.6B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ankitkushwaha90/tech3space3-0.6B
# Run inference directly in the terminal:
llama cli -hf ankitkushwaha90/tech3space3-0.6B

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 ankitkushwaha90/tech3space3-0.6B
# Run inference directly in the terminal:
./llama-cli -hf ankitkushwaha90/tech3space3-0.6B

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 ankitkushwaha90/tech3space3-0.6B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ankitkushwaha90/tech3space3-0.6B

Use Docker

docker model run hf.co/ankitkushwaha90/tech3space3-0.6B

LM Studio
Jan

vLLM

How to use ankitkushwaha90/tech3space3-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ankitkushwaha90/tech3space3-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ankitkushwaha90/tech3space3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ankitkushwaha90/tech3space3-0.6B

SGLang

How to use ankitkushwaha90/tech3space3-0.6B 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 "ankitkushwaha90/tech3space3-0.6B" \
    --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": "ankitkushwaha90/tech3space3-0.6B",
		"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 "ankitkushwaha90/tech3space3-0.6B" \
        --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": "ankitkushwaha90/tech3space3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ankitkushwaha90/tech3space3-0.6B with Ollama:
```
ollama run hf.co/ankitkushwaha90/tech3space3-0.6B
```

Unsloth Studio

How to use ankitkushwaha90/tech3space3-0.6B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ankitkushwaha90/tech3space3-0.6B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ankitkushwaha90/tech3space3-0.6B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ankitkushwaha90/tech3space3-0.6B to start chatting

How to use ankitkushwaha90/tech3space3-0.6B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ankitkushwaha90/tech3space3-0.6B

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ankitkushwaha90/tech3space3-0.6B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ankitkushwaha90/tech3space3-0.6B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ankitkushwaha90/tech3space3-0.6B

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 ankitkushwaha90/tech3space3-0.6B

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ankitkushwaha90/tech3space3-0.6B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ankitkushwaha90/tech3space3-0.6B

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 "ankitkushwaha90/tech3space3-0.6B" \
  --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"

Docker Model Runner
How to use ankitkushwaha90/tech3space3-0.6B with Docker Model Runner:
```
docker model run hf.co/ankitkushwaha90/tech3space3-0.6B
```

Lemonade

How to use ankitkushwaha90/tech3space3-0.6B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ankitkushwaha90/tech3space3-0.6B

Run and chat with the model

lemonade run user.tech3space3-0.6B-{{QUANT_TAG}}

List all available models

lemonade list

tech3space3-0.6B / full_fine_tunning_model_SFTTraining..py

ankitkushwaha90

Upload full_fine_tunning_model_SFTTraining..py

de11e8f verified 23 days ago

Raw

History Blame Contribute Delete

3.11 kB

	# train_fft.py

	import os
	import torch

	from datasets import load_dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from trl import SFTTrainer, SFTConfig

	# ============================================================
	# PATHS
	# ============================================================

	MODEL_PATH = "./Qwen3-0.6B"
	DATASET_PATH = "./dataset/train.jsonl"
	OUTPUT_DIR = "./outputs/qwen3_0.6b_fft"

	os.makedirs(OUTPUT_DIR, exist_ok=True)

	# ============================================================
	# DATASET
	# ============================================================

	print("Loading dataset...")
	dataset = load_dataset(
	"json",
	data_files=DATASET_PATH,
	split="train"
	)
	print(f"Dataset size: {len(dataset)}")

	# ============================================================
	# TOKENIZER
	# ============================================================

	print("Loading tokenizer...")
	tokenizer = AutoTokenizer.from_pretrained(
	MODEL_PATH,
	trust_remote_code=True
	)

	# Fix for models that don't have pad_token
	if tokenizer.pad_token is None:
	tokenizer.pad_token = tokenizer.eos_token

	# ============================================================
	# MODEL
	# ============================================================

	print("Loading model...")
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_PATH,
	torch_dtype=torch.bfloat16,
	trust_remote_code=True,
	device_map="auto" # Optional: helps with memory on single GPU
	)

	model.config.use_cache = False

	# ============================================================
	# TRAINING CONFIG
	# ============================================================

	training_args = SFTConfig(
	output_dir=OUTPUT_DIR,
	num_train_epochs=3,
	learning_rate=5e-6,
	per_device_train_batch_size=1,
	gradient_accumulation_steps=16,
	bf16=True,
	logging_steps=10,
	save_strategy="steps",
	save_steps=200,
	save_total_limit=2,
	lr_scheduler_type="cosine",
	warmup_ratio=0.03,
	max_length=512,
	packing=False,
	gradient_checkpointing=True,
	report_to="none",
	# Optional but recommended:
	dataloader_num_workers=2,
	remove_unused_columns=False,
	)

	# ============================================================
	# TRAINER
	# ============================================================

	trainer = SFTTrainer(
	model=model,
	args=training_args,
	train_dataset=dataset,
	processing_class=tokenizer, # Newer TRL uses processing_class
	# tokenizer=tokenizer, # You can use this if processing_class doesn't work
	)

	# ============================================================
	# TRAIN
	# ============================================================

	print("Starting full fine-tuning...")
	trainer.train()

	# ============================================================
	# SAVE MODEL
	# ============================================================

	print("Saving model...")
	trainer.save_model(OUTPUT_DIR)
	tokenizer.save_pretrained(OUTPUT_DIR)

	print("=" * 60)
	print("✅ FULL FINE TUNING COMPLETED")
	print(f"Model saved to: {OUTPUT_DIR}")
	print("=" * 60)