Instructions to use rvind2508/CodeLlama-7b-hf_FIM_200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rvind2508/CodeLlama-7b-hf_FIM_200 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/CodeLlama-7b-hf")
model = PeftModel.from_pretrained(base_model, "rvind2508/CodeLlama-7b-hf_FIM_200")

Transformers

How to use rvind2508/CodeLlama-7b-hf_FIM_200 with Transformers:

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

pipe = pipeline("text-generation", model="rvind2508/CodeLlama-7b-hf_FIM_200")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rvind2508/CodeLlama-7b-hf_FIM_200", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rvind2508/CodeLlama-7b-hf_FIM_200 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rvind2508/CodeLlama-7b-hf_FIM_200"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rvind2508/CodeLlama-7b-hf_FIM_200",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rvind2508/CodeLlama-7b-hf_FIM_200

SGLang

How to use rvind2508/CodeLlama-7b-hf_FIM_200 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 "rvind2508/CodeLlama-7b-hf_FIM_200" \
    --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": "rvind2508/CodeLlama-7b-hf_FIM_200",
		"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 "rvind2508/CodeLlama-7b-hf_FIM_200" \
        --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": "rvind2508/CodeLlama-7b-hf_FIM_200",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rvind2508/CodeLlama-7b-hf_FIM_200 with Docker Model Runner:
```
docker model run hf.co/rvind2508/CodeLlama-7b-hf_FIM_200
```

CodeLlama-7b-hf_FIM_200

This model is a fine-tuned version of meta-llama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7774

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: 0.0002
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 64
optimizer: Use adamw_torch 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: 0.05
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.6036	0.5	100	1.5000
0.4254	1.0	200	1.7774

Framework versions

PEFT 0.18.1
Transformers 5.3.0
Pytorch 2.5.1+cu121
Datasets 4.7.0
Tokenizers 0.22.2

Downloads last month: -

Model tree for rvind2508/CodeLlama-7b-hf_FIM_200

Base model

meta-llama/CodeLlama-7b-hf

Adapter

(20)

this model