Instructions to use bartowski/speechless-zephyr-code-functionary-7b-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/speechless-zephyr-code-functionary-7b-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/speechless-zephyr-code-functionary-7b-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/speechless-zephyr-code-functionary-7b-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bartowski/speechless-zephyr-code-functionary-7b-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/speechless-zephyr-code-functionary-7b-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/speechless-zephyr-code-functionary-7b-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/speechless-zephyr-code-functionary-7b-exl2

SGLang

How to use bartowski/speechless-zephyr-code-functionary-7b-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/speechless-zephyr-code-functionary-7b-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/speechless-zephyr-code-functionary-7b-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/speechless-zephyr-code-functionary-7b-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/speechless-zephyr-code-functionary-7b-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bartowski/speechless-zephyr-code-functionary-7b-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/speechless-zephyr-code-functionary-7b-exl2
```

speechless-zephyr-code-functionary-7b-exl2 / README.md

bartowski

measurement.json

b83e90f verified over 2 years ago

preview code

raw

history blame contribute delete

3.08 kB

	---
	language:
	- en
	library_name: transformers
	pipeline_tag: text-generation
	license: apache-2.0
	quantized_by: bartowski
	---

	## Exllama v2 Quantizations of speechless-zephyr-code-functionary-7b

	Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> 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/uukuguy/speechless-zephyr-code-functionary-7b

	\| Branch \| Bits \| lm_head bits \| Size \| Description \|
	\| ----- \| ---- \| ------- \| ------ \| ------------ \|
	\| [8_0](https://huggingface.co/Bartowski/speechless-zephyr-code-functionary-7b-exl2/tree/8_0) \| 8.0 \| 8.0 \| 9.8 GB \| Maximum quality that ExLlamaV2 can produce, near unquantized performance. \|
	\| [6_5](https://huggingface.co/Bartowski/speechless-zephyr-code-functionary-7b-exl2/tree/6_5) \| 6.5 \| 8.0 \| 8.6 GB \| Very similar to 8.0, good tradeoff of size vs performance, recommended. \|
	\| [5_0](https://huggingface.co/Bartowski/speechless-zephyr-code-functionary-7b-exl2/tree/5_0) \| 5.0 \| 6.0 \| 7.4 GB \| Slightly lower quality vs 6.5, but usable on 8GB cards. \|
	\| [4_25](https://huggingface.co/Bartowski/speechless-zephyr-code-functionary-7b-exl2/tree/4_25) \| 4.25 \| 6.0 \| 6.7 GB \| GPTQ equivalent bits per weight, slightly higher quality. \|
	\| [3_5](https://huggingface.co/Bartowski/speechless-zephyr-code-functionary-7b-exl2/tree/3_5) \| 3.5 \| 6.0 \| 6.1 GB \| Lower quality, only use if you have to. \|

	All VRAM requirements estimated from 16k context. For 32k context add ~2 GB.

	## Download instructions

	With git:

	```shell
	git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/speechless-zephyr-code-functionary-7b-exl2 speechless-zephyr-code-functionary-7b-exl2-6_5
	```

	With huggingface hub (credit to TheBloke for instructions):

	```shell
	pip3 install huggingface-hub
	```

	To download the `main` (only useful if you only care about measurement.json) branch to a folder called `speechless-zephyr-code-functionary-7b-exl2`:

	```shell
	mkdir speechless-zephyr-code-functionary-7b-exl2
	huggingface-cli download bartowski/speechless-zephyr-code-functionary-7b-exl2 --local-dir speechless-zephyr-code-functionary-7b-exl2 --local-dir-use-symlinks False
	```

	To download from a different branch, add the `--revision` parameter:

	Linux:

	```shell
	mkdir speechless-zephyr-code-functionary-7b-exl2-6_5
	huggingface-cli download bartowski/speechless-zephyr-code-functionary-7b-exl2 --revision 6_5 --local-dir speechless-zephyr-code-functionary-7b-exl2-6_5 --local-dir-use-symlinks False
	```

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

	```shell
	mkdir speechless-zephyr-code-functionary-7b-exl2-6.5
	huggingface-cli download bartowski/speechless-zephyr-code-functionary-7b-exl2 --revision 6_5 --local-dir speechless-zephyr-code-functionary-7b-exl2-6.5 --local-dir-use-symlinks False
	```