Instructions to use bartowski/Replete-Coder-Llama3-8B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Replete-Coder-Llama3-8B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Replete-Coder-Llama3-8B-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Replete-Coder-Llama3-8B-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bartowski/Replete-Coder-Llama3-8B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Replete-Coder-Llama3-8B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Replete-Coder-Llama3-8B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Replete-Coder-Llama3-8B-exl2

SGLang

How to use bartowski/Replete-Coder-Llama3-8B-exl2 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 "bartowski/Replete-Coder-Llama3-8B-exl2" \
    --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": "bartowski/Replete-Coder-Llama3-8B-exl2",
		"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 "bartowski/Replete-Coder-Llama3-8B-exl2" \
        --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": "bartowski/Replete-Coder-Llama3-8B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use bartowski/Replete-Coder-Llama3-8B-exl2 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 bartowski/Replete-Coder-Llama3-8B-exl2 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 bartowski/Replete-Coder-Llama3-8B-exl2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/Replete-Coder-Llama3-8B-exl2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="bartowski/Replete-Coder-Llama3-8B-exl2",
    max_seq_length=2048,
)

Docker Model Runner
How to use bartowski/Replete-Coder-Llama3-8B-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/Replete-Coder-Llama3-8B-exl2
```

Exllama v2 Quantizations of Replete-Coder-Llama3-8B

Using turboderp's ExLlamaV2 v0.1.6 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B

Prompt format

### System:
{}

### Instruction:
{}

### Response:
{}

Available sizes

Branch	Bits	lm_head bits	VRAM (4k)	VRAM (8K)	VRAM (16k)	VRAM (32k)	Description
8_0	8.0	8.0	10.1 GB	10.5 GB	11.5 GB	13.6 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	8.9 GB	9.3 GB	10.3 GB	12.4 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	7.7 GB	8.1 GB	9.1 GB	11.2 GB	Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25	4.25	6.0	7.0 GB	7.4 GB	8.4 GB	10.5 GB	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	6.0	6.4 GB	6.8 GB	7.8 GB	9.9 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Replete-Coder-Llama3-8B-exl2 Replete-Coder-Llama3-8B-exl2-6_5

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:

Linux:

huggingface-cli download bartowski/Replete-Coder-Llama3-8B-exl2 --revision 6_5 --local-dir Replete-Coder-Llama3-8B-exl2-6_5

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download bartowski/Replete-Coder-Llama3-8B-exl2 --revision 6_5 --local-dir Replete-Coder-Llama3-8B-exl2-6.5

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month: -; Downloads are not tracked for this model. How to track

Datasets used to train bartowski/Replete-Coder-Llama3-8B-exl2

Evaluation results

pass@1 on HumanEval
self-reported
normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard
multiple_choice_accuracy on TruthfulQA (0-shot)
validation set Open LLM Leaderboard
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard