Instructions to use mrm8488/santacoder-finetuned-the-stack-swift with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrm8488/santacoder-finetuned-the-stack-swift with Transformers:

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

pipe = pipeline("text-generation", model="mrm8488/santacoder-finetuned-the-stack-swift", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrm8488/santacoder-finetuned-the-stack-swift", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("mrm8488/santacoder-finetuned-the-stack-swift", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrm8488/santacoder-finetuned-the-stack-swift with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrm8488/santacoder-finetuned-the-stack-swift"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrm8488/santacoder-finetuned-the-stack-swift",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrm8488/santacoder-finetuned-the-stack-swift

SGLang

How to use mrm8488/santacoder-finetuned-the-stack-swift 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 "mrm8488/santacoder-finetuned-the-stack-swift" \
    --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": "mrm8488/santacoder-finetuned-the-stack-swift",
		"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 "mrm8488/santacoder-finetuned-the-stack-swift" \
        --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": "mrm8488/santacoder-finetuned-the-stack-swift",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrm8488/santacoder-finetuned-the-stack-swift with Docker Model Runner:
```
docker model run hf.co/mrm8488/santacoder-finetuned-the-stack-swift
```

mrm8488 commited on Feb 9, 2023

Commit

99b9470

1 Parent(s): 5bed5c0

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -3

README.md CHANGED Viewed

@@ -5,12 +5,17 @@ tags:
 model-index:
 - name: santacoder-finetuned-the-stack-swift
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# santacoder-finetuned-the-stack-swift
 This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
 It achieves the following results on the evaluation set:
@@ -18,7 +23,9 @@ It achieves the following results on the evaluation set:
 ## Model description
-More information needed
 ## Intended uses & limitations
@@ -26,7 +33,7 @@ More information needed
 ## Training and evaluation data
-More information needed
 ## Training procedure

 model-index:
 - name: santacoder-finetuned-the-stack-swift
   results: []
+datasets:
+- bigcode/the-stack-dedup
+language:
+- code
+pipeline_tag: text-generation
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# SantaCoder 🎅 fine-tuned on Swift 🍏
 This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
 It achieves the following results on the evaluation set:
 ## Model description
+The [SantaCoder](https://huggingface.co/bigcode/santacoder) models are a series of 1.1B parameter models trained on the Python, Java, and JavaScript subset of [The Stack (v1.1)](https://huggingface.co/datasets/bigcode/the-stack) (which excluded opt-out requests).
+The main model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255).
+In addition, there are several models that were trained on datasets with different filter parameters and with architecture and objective variations.
 ## Intended uses & limitations
 ## Training and evaluation data
+The Stack contains over 6TB of permissively-licensed source code files covering 358 programming languages. The dataset was created as part of the [BigCode Project](https://www.bigcode-project.org/), an open scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs). The Stack serves as a pre-training dataset for Code LLMs, i.e., code-generating AI systems which enable the synthesis of programs from natural language descriptions as well as other from code snippets. **This is the near-deduplicated version with 3TB data.**
 ## Training procedure