Instructions to use OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k with Transformers:

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

pipe = pipeline("text-generation", model="OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k")
model = AutoModelForCausalLM.from_pretrained("OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k

SGLang

How to use OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k 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 "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k" \
    --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": "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k",
		"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 "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k" \
        --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": "OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k with Docker Model Runner:
```
docker model run hf.co/OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k
```

OliverSundaram commited on 16 days ago

Commit

f26771d

verified ·

1 Parent(s): 79bbbbf

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -98,12 +98,12 @@ fine-tuning data volume trades off against both math performance and general cap
 All benchmarks run with [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), each at
 its standard published shot count, compared against the un-tuned base model.
-| Benchmark | Llama-3.2-1B (base) | This model | Change |
-|---|---|---|---|
-| GSM8K | 5.8% | 8.9% | 🟢 +3.1% |
-| ARC-Challenge | 36.9% | 35.8% | 🔴 -1.1% |
-| HellaSwag | 64.2% | 63.6% | 🔴 -0.6% |
-| WinoGrande | 60.8% | 61.4% | 🟢 +0.6% |
 **Speed:** **40.63 tokens/sec**
 (base model: 40.59 tokens/sec)

 All benchmarks run with [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), each at
 its standard published shot count, compared against the un-tuned base model.
+| Benchmark | Llama-3.2-1B (base) | MathCodeInstruct-20k | Change |
+|---|---|----------------------|---|
+| GSM8K | 5.8% | 8.9%                 | 🟢 +3.1% |
+| ARC-Challenge | 36.9% | 35.8%                | 🔴 -1.1% |
+| HellaSwag | 64.2% | 63.6%                | 🔴 -0.6% |
+| WinoGrande | 60.8% | 61.4%                | 🟢 +0.6% |
 **Speed:** **40.63 tokens/sec**
 (base model: 40.59 tokens/sec)