Instructions to use Jebadiah/Aria-coder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jebadiah/Aria-coder-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Jebadiah/Aria-coder-7b",
	filename="Aria-coder-7b-F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Jebadiah/Aria-coder-7b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jebadiah/Aria-coder-7b:F16
# Run inference directly in the terminal:
llama-cli -hf Jebadiah/Aria-coder-7b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jebadiah/Aria-coder-7b:F16
# Run inference directly in the terminal:
llama-cli -hf Jebadiah/Aria-coder-7b:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Jebadiah/Aria-coder-7b:F16
# Run inference directly in the terminal:
./llama-cli -hf Jebadiah/Aria-coder-7b:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Jebadiah/Aria-coder-7b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jebadiah/Aria-coder-7b:F16

Use Docker

docker model run hf.co/Jebadiah/Aria-coder-7b:F16

LM Studio
Jan
Ollama
How to use Jebadiah/Aria-coder-7b with Ollama:
```
ollama run hf.co/Jebadiah/Aria-coder-7b:F16
```

Unsloth Studio new

How to use Jebadiah/Aria-coder-7b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jebadiah/Aria-coder-7b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jebadiah/Aria-coder-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jebadiah/Aria-coder-7b to start chatting

Docker Model Runner
How to use Jebadiah/Aria-coder-7b with Docker Model Runner:
```
docker model run hf.co/Jebadiah/Aria-coder-7b:F16
```

Lemonade

How to use Jebadiah/Aria-coder-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jebadiah/Aria-coder-7b:F16

Run and chat with the model

lemonade run user.Aria-coder-7b-F16

List all available models

lemonade list

Aria-coder-7b

Aria-coder-7b is a merge of the following models using LazyMergekit:

🧩 Configuration

name: Aria-coder-7b
merge_method: sce
parameters:
  select_topk: 0.666
  normalize: true
dtype: float32
out_dtype: bfloat16
base_model: Jebadiah/Aria-ruby-v3
tokenizer:
  source: union
  special_tokens: keep_all
  priority: none
  add_padding_token: true
  force_fast_tokenizer: true  # Can help with compatibility
  resolve_conflicts: append_ids  # Append IDs to conflicting tokens to make them unique
models:
  - model: xingyaoww/CodeActAgent-Mistral-7b-v0.1
  - model: Badgids/Gonzo-Code-7B
  - model: Jebadiah/Aria-ruby-v3
  - model: flammenai/flammen31-mistral-7B
  - model: fhai50032/SamChat

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Jebadiah/Aria-coder-7b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 27

Safetensors

Model size

7B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Jebadiah/Aria-coder-7b

Finetunes

1 model

Merges

1 model

Quantizations

2 models