Instructions to use bartowski/Llama-3-8B-Instruct-Coder-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Llama-3-8B-Instruct-Coder-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Llama-3-8B-Instruct-Coder-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Llama-3-8B-Instruct-Coder-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bartowski/Llama-3-8B-Instruct-Coder-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Llama-3-8B-Instruct-Coder-exl2

SGLang

How to use bartowski/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use bartowski/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-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/Llama-3-8B-Instruct-Coder-exl2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="bartowski/Llama-3-8B-Instruct-Coder-exl2",
    max_seq_length=2048,
)

Docker Model Runner
How to use bartowski/Llama-3-8B-Instruct-Coder-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/Llama-3-8B-Instruct-Coder-exl2
```

bartowski commited on May 4, 2024

Commit

91c8ce9

verified ·

1 Parent(s): b7a5754

measurement.json

Browse files

Files changed (2) hide show

README.md +78 -0
measurement.json +0 -0

README.md ADDED Viewed

	@@ -0,0 +1,78 @@

+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+## Exllama v2 Quantizations of Llama-3-8B-Instruct-Coder
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization.
+<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+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/rombodawg/Codellama-3-8B-Finetuned-Instruct
+## Prompt format
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+## Available sizes
+| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
+| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
+| [8_0](https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2/tree/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](https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2/tree/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](https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2/tree/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](https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2/tree/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](https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2/tree/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:
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-exl2 Llama-3-8B-Instruct-Coder-exl2-6_5
+```
+With huggingface hub (credit to TheBloke for instructions):
+```shell
+pip3 install huggingface-hub
+```
+To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
+Linux:
+```shell
+huggingface-cli download bartowski/Llama-3-8B-Instruct-Coder-exl2 --revision 6_5 --local-dir Llama-3-8B-Instruct-Coder-exl2-6_5 --local-dir-use-symlinks False
+```
+Windows (which apparently doesn't like _ in folders sometimes?):
+```shell
+huggingface-cli download bartowski/Llama-3-8B-Instruct-Coder-exl2 --revision 6_5 --local-dir Llama-3-8B-Instruct-Coder-exl2-6.5 --local-dir-use-symlinks False
+```
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

measurement.json ADDED Viewed

The diff for this file is too large to render. See raw diff