Instructions to use alphahg/CodeLlama-7b-hf-rust-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alphahg/CodeLlama-7b-hf-rust-finetune with Transformers:

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

pipe = pipeline("text-generation", model="alphahg/CodeLlama-7b-hf-rust-finetune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alphahg/CodeLlama-7b-hf-rust-finetune")
model = AutoModelForCausalLM.from_pretrained("alphahg/CodeLlama-7b-hf-rust-finetune")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alphahg/CodeLlama-7b-hf-rust-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alphahg/CodeLlama-7b-hf-rust-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alphahg/CodeLlama-7b-hf-rust-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alphahg/CodeLlama-7b-hf-rust-finetune

SGLang

How to use alphahg/CodeLlama-7b-hf-rust-finetune 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 "alphahg/CodeLlama-7b-hf-rust-finetune" \
    --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": "alphahg/CodeLlama-7b-hf-rust-finetune",
		"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 "alphahg/CodeLlama-7b-hf-rust-finetune" \
        --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": "alphahg/CodeLlama-7b-hf-rust-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alphahg/CodeLlama-7b-hf-rust-finetune with Docker Model Runner:
```
docker model run hf.co/alphahg/CodeLlama-7b-hf-rust-finetune
```

llama2-7b-rust-finetune

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on the-stack-rust-clean dataset. It achieves the following results on the evaluation set:

Loss: 0.5347

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: 2.5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0	100	0.5443
No log	0.01	200	0.5385
No log	0.01	300	0.5362
No log	0.01	400	0.5351
0.5389	0.02	500	0.5347

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1

Downloads last month: 25

Model tree for alphahg/CodeLlama-7b-hf-rust-finetune

Base model

codellama/CodeLlama-7b-hf

Finetuned

(78)

this model