Instructions to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Transformers:

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

pipe = pipeline("text-generation", model="Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2")
model = AutoModelForCausalLM.from_pretrained("Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2")
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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2",
	filename="unsloth.F16.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2: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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2: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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

Use Docker

docker model run hf.co/Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

LM Studio
Jan

vLLM

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

SGLang

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 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 "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2" \
    --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": "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2",
		"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 "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2" \
        --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": "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Ollama:
```
ollama run hf.co/Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
```

Unsloth Studio

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 to start chatting

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2: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": "Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2: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 Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Docker Model Runner:
```
docker model run hf.co/Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M
```

Lemonade

How to use Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Qurtana/Qwen-2.5-0.5B-MathInstruct.rev.2:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-2.5-0.5B-MathInstruct.rev.2-Q4_K_M

List all available models

lemonade list

Qurtana commited on Oct 29, 2024

Commit

841a361

verified ·

1 Parent(s): ba26448

Trained with Unsloth

Browse files

Files changed (4) hide show

README.md +1 -0
config.json +31 -0
generation_config.json +15 -0
pytorch_model.bin +3 -0

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ tags:
 - unsloth
 - qwen2
 - trl
 ---
 # Uploaded  model

 - unsloth
 - qwen2
 - trl
+- sft
 ---
 # Uploaded  model

config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "_name_or_path": "unsloth/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151665,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0.dev0",
+  "unsloth_version": "2024.10.7",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.47.0.dev0"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71ab8f5e46e61a45f1eedd0eefae818fad66c55cf2cb8909e9386679c5d388c0
+size 1260432534