Instructions to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/CodeLlama-7b-Instruct-hf")
model = PeftModel.from_pretrained(base_model, "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st")

Transformers

How to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st with Transformers:

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

pipe = pipeline("text-generation", model="j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st

SGLang

How to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st 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 "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st with Docker Model Runner:
```
docker model run hf.co/j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st
```

SFT-CodeLlama-7B-Instruct_128_v1.1st

This model is a fine-tuned version of meta-llama/CodeLlama-7b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4774

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: 0.0001
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.8478	0.3049	50	0.8231
0.641	0.6098	100	0.7294
0.6417	0.9146	150	0.6423
0.5366	1.2195	200	0.5949
0.454	1.5244	250	0.5547
0.4829	1.8293	300	0.5252
0.3738	2.1341	350	0.5223
0.317	2.4390	400	0.4940
0.2744	2.7439	450	0.4794
0.2723	3.0488	500	0.4771
0.2536	3.3537	550	0.4898
0.1833	3.6585	600	0.4930
0.2219	3.9634	650	0.4826

Framework versions

PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1

Downloads last month: -

Model tree for j05hr3d/SFT-CodeLlama-7B-Instruct_128_v1.1st

Base model

meta-llama/CodeLlama-7b-Instruct-hf

Adapter

(35)

this model