Instructions to use Hariharan05/Qwen3-1.7B-Distill-Claude with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-1.7b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Hariharan05/Qwen3-1.7B-Distill-Claude")

Transformers

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Transformers:

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

pipe = pipeline("text-generation", model="Hariharan05/Qwen3-1.7B-Distill-Claude")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hariharan05/Qwen3-1.7B-Distill-Claude")
model = AutoModelForCausalLM.from_pretrained("Hariharan05/Qwen3-1.7B-Distill-Claude", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Hariharan05/Qwen3-1.7B-Distill-Claude",
	filename="Qwen3-1.5B-Distill-Claudeq4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Hariharan05/Qwen3-1.7B-Distill-Claude 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 Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hariharan05/Qwen3-1.7B-Distill-Claude: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 Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hariharan05/Qwen3-1.7B-Distill-Claude: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 Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

Use Docker

docker model run hf.co/Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

LM Studio
Jan

vLLM

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hariharan05/Qwen3-1.7B-Distill-Claude"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hariharan05/Qwen3-1.7B-Distill-Claude",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

SGLang

How to use Hariharan05/Qwen3-1.7B-Distill-Claude 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 "Hariharan05/Qwen3-1.7B-Distill-Claude" \
    --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": "Hariharan05/Qwen3-1.7B-Distill-Claude",
		"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 "Hariharan05/Qwen3-1.7B-Distill-Claude" \
        --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": "Hariharan05/Qwen3-1.7B-Distill-Claude",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Ollama:
```
ollama run hf.co/Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
```

Unsloth Studio

How to use Hariharan05/Qwen3-1.7B-Distill-Claude 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 Hariharan05/Qwen3-1.7B-Distill-Claude 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 Hariharan05/Qwen3-1.7B-Distill-Claude to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Hariharan05/Qwen3-1.7B-Distill-Claude to start chatting

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

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": "Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hariharan05/Qwen3-1.7B-Distill-Claude: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 Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hariharan05/Qwen3-1.7B-Distill-Claude: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 "Hariharan05/Qwen3-1.7B-Distill-Claude: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"

Docker Model Runner
How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Docker Model Runner:
```
docker model run hf.co/Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M
```

Lemonade

How to use Hariharan05/Qwen3-1.7B-Distill-Claude with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hariharan05/Qwen3-1.7B-Distill-Claude:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-1.7B-Distill-Claude-Q4_K_M

List all available models

lemonade list

Qwen3-1.7B-Distill-Claude

This is a fine-tuned version of the Qwen/Qwen3-1.7B model, trained to follow instructions and generate high-quality responses using a distilled Claude-Alpaca dataset.

This model was trained using EasyFineTuner and Unsloth for 2x faster training and optimized memory usage. It is provided in lightweight GGUF formats (q4_k_m and q5_k_m) for seamless local inference.

📊 Model Details

Base Model: Qwen/Qwen3-1.7B
Architecture: Causal LM
Parameters: 1.7 Billion
Trainable Parameters: 17,432,576 (LoRA)
Format: GGUF & LoRA Adapters

📚 Dataset Information

The model was trained on a high-quality blend of 30,000 instruction-following examples:

Norquinal/WizardLM_alpaca_claude_evol_instruct_70k (25,000 examples)
AlSamCur123/Alpaca (5,000 examples)

Dataset Statistics:

Total Training Examples: 28,500
Total Validation Examples: 1,500
Average Sequence Length: 139 tokens
Max Sequence Length Used: 1024 tokens

⚙️ Training Configuration

The model was fine-tuned using Low-Rank Adaptation (LoRA) with the following hyperparameters:

Epochs: 1
Learning Rate: 2.0e-04
Batch Size: 4
Gradient Accumulation Steps: 4 (Total Effective Batch Size: 32)
LoRA Rank (r): 16
LoRA Alpha: 64
Warmup Steps: 100
Weight Decay: 0.01
Optimizer: AdamW

Performance:

Final Training Loss: 1.1782
Training Time: ~3.3 hours on a single Tesla T4 GPU

💻 Usage (Local Inference)

You can run this model locally using Ollama or llama.cpp.

Using Ollama

Create a Modelfile with the following content:

FROM ./Qwen3-1.5B-Distill-Claudeq4_k_m.gguf
TEMPLATE \"\"\"<|im_start|>system
You are a helpful AI assistant trained to assist with coding questions, explain technical concepts, and engage in friendly conversation. Be concise but thorough in your explanations.<|im_start|>user
{{ .Prompt }}<|im_start|>assistant
\"\"\"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.18.1
TRL: 0.23.0
Transformers: 4.56.2
Pytorch: 2.10.0+cu128
Datasets: 4.3.0
Tokenizers: 0.22.2

Downloads last month: 53

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Hariharan05/Qwen3-1.7B-Distill-Claude

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(563)

this model

Hariharan05
/

Qwen3-1.7B-Distill-Claude

Qwen3-1.7B-Distill-Claude

📊 Model Details

📚 Dataset Information

⚙️ Training Configuration

💻 Usage (Local Inference)

Using Ollama

Quick start

Training procedure

Framework versions

Model tree for Hariharan05/Qwen3-1.7B-Distill-Claude

Datasets used to train Hariharan05/Qwen3-1.7B-Distill-Claude