Instructions to use patricksaxton/peft-starcoder-lora-a100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patricksaxton/peft-starcoder-lora-a100 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-1b")
model = PeftModel.from_pretrained(base_model, "patricksaxton/peft-starcoder-lora-a100")

Transformers

How to use patricksaxton/peft-starcoder-lora-a100 with Transformers:

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

pipe = pipeline("text-generation", model="patricksaxton/peft-starcoder-lora-a100")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("patricksaxton/peft-starcoder-lora-a100", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use patricksaxton/peft-starcoder-lora-a100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patricksaxton/peft-starcoder-lora-a100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patricksaxton/peft-starcoder-lora-a100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/patricksaxton/peft-starcoder-lora-a100

SGLang

How to use patricksaxton/peft-starcoder-lora-a100 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 "patricksaxton/peft-starcoder-lora-a100" \
    --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": "patricksaxton/peft-starcoder-lora-a100",
		"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 "patricksaxton/peft-starcoder-lora-a100" \
        --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": "patricksaxton/peft-starcoder-lora-a100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use patricksaxton/peft-starcoder-lora-a100 with Docker Model Runner:
```
docker model run hf.co/patricksaxton/peft-starcoder-lora-a100
```

peft-starcoder-lora-a100 / README.md

patricksaxton

End of training

bb62a5a verified 10 months ago

preview code

Raw History Blame Contribute Delete

2.53 kB

---
library_name: peft
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- base_model:adapter:bigcode/starcoderbase-1b
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: peft-starcoder-lora-a100
  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. -->

# peft-starcoder-lora-a100

This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3521

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.1602        | 0.05  | 100  | 3.3944          |
| 4.9152        | 0.1   | 200  | 3.3911          |
| 4.864         | 0.15  | 300  | 3.3850          |
| 5.0538        | 0.2   | 400  | 3.3808          |
| 5.0474        | 0.25  | 500  | 3.3748          |
| 5.7174        | 0.3   | 600  | 3.3669          |
| 4.8981        | 0.35  | 700  | 3.3714          |
| 5.3039        | 0.4   | 800  | 3.3702          |
| 5.5544        | 0.45  | 900  | 3.3721          |
| 5.4907        | 0.5   | 1000 | 3.3747          |
| 2.8972        | 0.55  | 1100 | 3.3880          |
| 4.6895        | 0.6   | 1200 | 3.3689          |
| 4.4027        | 0.65  | 1300 | 3.3708          |
| 5.6217        | 0.7   | 1400 | 3.3690          |
| 5.0912        | 0.75  | 1500 | 3.3651          |
| 5.3595        | 0.8   | 1600 | 3.3628          |
| 4.3603        | 0.85  | 1700 | 3.3541          |
| 4.7773        | 0.9   | 1800 | 3.3548          |
| 3.3149        | 0.95  | 1900 | 3.3524          |
| 4.9032        | 1.0   | 2000 | 3.3521          |


### Framework versions

- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1

	---
	library_name: peft
	license: bigcode-openrail-m
	base_model: bigcode/starcoderbase-1b
	tags:
	- base_model:adapter:bigcode/starcoderbase-1b
	- lora
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: peft-starcoder-lora-a100
	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. -->

	# peft-starcoder-lora-a100

	This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 3.3521

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.0005
	- train_batch_size: 12
	- eval_batch_size: 12
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 30
	- training_steps: 2000

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 5.1602 \| 0.05 \| 100 \| 3.3944 \|
	\| 4.9152 \| 0.1 \| 200 \| 3.3911 \|
	\| 4.864 \| 0.15 \| 300 \| 3.3850 \|
	\| 5.0538 \| 0.2 \| 400 \| 3.3808 \|
	\| 5.0474 \| 0.25 \| 500 \| 3.3748 \|
	\| 5.7174 \| 0.3 \| 600 \| 3.3669 \|
	\| 4.8981 \| 0.35 \| 700 \| 3.3714 \|
	\| 5.3039 \| 0.4 \| 800 \| 3.3702 \|
	\| 5.5544 \| 0.45 \| 900 \| 3.3721 \|
	\| 5.4907 \| 0.5 \| 1000 \| 3.3747 \|
	\| 2.8972 \| 0.55 \| 1100 \| 3.3880 \|
	\| 4.6895 \| 0.6 \| 1200 \| 3.3689 \|
	\| 4.4027 \| 0.65 \| 1300 \| 3.3708 \|
	\| 5.6217 \| 0.7 \| 1400 \| 3.3690 \|
	\| 5.0912 \| 0.75 \| 1500 \| 3.3651 \|
	\| 5.3595 \| 0.8 \| 1600 \| 3.3628 \|
	\| 4.3603 \| 0.85 \| 1700 \| 3.3541 \|
	\| 4.7773 \| 0.9 \| 1800 \| 3.3548 \|
	\| 3.3149 \| 0.95 \| 1900 \| 3.3524 \|
	\| 4.9032 \| 1.0 \| 2000 \| 3.3521 \|


	### Framework versions

	- PEFT 0.18.0
	- Transformers 4.57.3
	- Pytorch 2.9.0+cu126
	- Datasets 4.0.0
	- Tokenizers 0.22.1