Instructions to use jaydeepb/llama-3.2-1b-code-run2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaydeepb/llama-3.2-1b-code-run2 with Transformers:

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

pipe = pipeline("text-generation", model="jaydeepb/llama-3.2-1b-code-run2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jaydeepb/llama-3.2-1b-code-run2")
model = AutoModelForCausalLM.from_pretrained("jaydeepb/llama-3.2-1b-code-run2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jaydeepb/llama-3.2-1b-code-run2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaydeepb/llama-3.2-1b-code-run2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaydeepb/llama-3.2-1b-code-run2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jaydeepb/llama-3.2-1b-code-run2

SGLang

How to use jaydeepb/llama-3.2-1b-code-run2 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 "jaydeepb/llama-3.2-1b-code-run2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaydeepb/llama-3.2-1b-code-run2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "jaydeepb/llama-3.2-1b-code-run2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaydeepb/llama-3.2-1b-code-run2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jaydeepb/llama-3.2-1b-code-run2 with Docker Model Runner:
```
docker model run hf.co/jaydeepb/llama-3.2-1b-code-run2
```

jaydeepb commited on 9 days ago

Commit

9080f67

verified ·

1 Parent(s): b821b44

Update model card: Run 2 + classifier/prediction note

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -7,12 +7,14 @@ tags:
 - research-artifact
 ---
-# llama-3.2-1b fine-tuned on The Stack (code)
 Research artifact from *Predicting Memorization Before Fine-Tuning Language Models*.
-This is `meta-llama/Llama-3.2-1B` fine-tuned for one epoch on a 1M-sequence sample of **The Stack (code)**, used to
-study and predict verbatim memorization of fine-tuning data.
 > **Note.** This model was fine-tuned to study memorization and can reproduce portions of its
 > fine-tuning data verbatim. It is released as a research artifact for reproducibility.

 - research-artifact
 ---
+# llama-3.2-1b fine-tuned on The Stack (code) (Run 2)
 Research artifact from *Predicting Memorization Before Fine-Tuning Language Models*.
+This is `meta-llama/Llama-3.2-1B` fine-tuned for one epoch on a 1M-sequence sample of **The Stack (code)** — the held-out
+"Run 2" fine-tuning run used for evaluation in the paper. The trained classifiers in that work
+**predict which sequences this fine-tuned model memorizes** from pre-fine-tuning (base-model)
+features; i.e., the verbatim memorization of training data in this model is what those classifiers forecast.
 > **Note.** This model was fine-tuned to study memorization and can reproduce portions of its
 > fine-tuning data verbatim. It is released as a research artifact for reproducibility.