Instructions to use bartowski/Yi-9B-Coder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Yi-9B-Coder-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Yi-9B-Coder-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Yi-9B-Coder-GGUF", dtype="auto")

llama-cpp-python

How to use bartowski/Yi-9B-Coder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/Yi-9B-Coder-GGUF",
	filename="Yi-9B-Coder-Q2_K.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 bartowski/Yi-9B-Coder-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M

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 bartowski/Yi-9B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M

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 bartowski/Yi-9B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/Yi-9B-Coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/Yi-9B-Coder-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/Yi-9B-Coder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Yi-9B-Coder-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Yi-9B-Coder-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Yi-9B-Coder-GGUF:Q4_K_M

SGLang

How to use bartowski/Yi-9B-Coder-GGUF 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/Yi-9B-Coder-GGUF" \
    --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/Yi-9B-Coder-GGUF",
		"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/Yi-9B-Coder-GGUF" \
        --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/Yi-9B-Coder-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use bartowski/Yi-9B-Coder-GGUF with Ollama:
```
ollama run hf.co/bartowski/Yi-9B-Coder-GGUF:Q4_K_M
```

Unsloth Studio new

How to use bartowski/Yi-9B-Coder-GGUF 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/Yi-9B-Coder-GGUF 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/Yi-9B-Coder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/Yi-9B-Coder-GGUF to start chatting

Docker Model Runner
How to use bartowski/Yi-9B-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Yi-9B-Coder-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/Yi-9B-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/Yi-9B-Coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Yi-9B-Coder-GGUF-Q4_K_M

List all available models

lemonade list

bartowski commited on Mar 13, 2024

Commit

0a34208

verified ·

1 Parent(s): 57f1d03

Llamacpp quants

Browse files

Files changed (14) hide show

.gitattributes +12 -0
README.md +36 -0
Yi-9B-Coder-Q2_K.gguf +3 -0
Yi-9B-Coder-Q3_K_L.gguf +3 -0
Yi-9B-Coder-Q3_K_M.gguf +3 -0
Yi-9B-Coder-Q3_K_S.gguf +3 -0
Yi-9B-Coder-Q4_0.gguf +3 -0
Yi-9B-Coder-Q4_K_M.gguf +3 -0
Yi-9B-Coder-Q4_K_S.gguf +3 -0
Yi-9B-Coder-Q5_0.gguf +3 -0
Yi-9B-Coder-Q5_K_M.gguf +3 -0
Yi-9B-Coder-Q5_K_S.gguf +3 -0
Yi-9B-Coder-Q6_K.gguf +3 -0
Yi-9B-Coder-Q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-9B-Coder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,36 @@

+---
+tags:
+- code
+- llama
+library_name: transformers
+pipeline_tag: text-generation
+license: other
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-9B/blob/main/LICENSE
+quantized_by: bartowski
+---
+## Llamacpp Quantizations of Yi-9B-Coder
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2405">b2405</a> for quantization.
+Original model: https://huggingface.co/TechxGenus/Yi-9B-Coder
+Download a file (not the whole branch) from below:
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Yi-9B-Coder-Q8_0.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q8_0.gguf) | Q8_0 | 9.38GB | Extremely high quality, generally unneeded but max available quant. |
+| [Yi-9B-Coder-Q6_K.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q6_K.gguf) | Q6_K | 7.24GB | Very high quality, near perfect, *recommended*. |
+| [Yi-9B-Coder-Q5_K_M.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q5_K_M.gguf) | Q5_K_M | 6.25GB | High quality, very usable. |
+| [Yi-9B-Coder-Q5_K_S.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q5_K_S.gguf) | Q5_K_S | 6.10GB | High quality, very usable. |
+| [Yi-9B-Coder-Q5_0.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q5_0.gguf) | Q5_0 | 6.10GB | High quality, older format, generally not recommended. |
+| [Yi-9B-Coder-Q4_K_M.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q4_K_M.gguf) | Q4_K_M | 5.32GB | Good quality, similar to 4.25 bpw. |
+| [Yi-9B-Coder-Q4_K_S.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q4_K_S.gguf) | Q4_K_S | 5.07GB | Slightly lower quality with small space savings. |
+| [Yi-9B-Coder-Q4_0.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q4_0.gguf) | Q4_0 | 5.03GB | Decent quality, older format, generally not recommended. |
+| [Yi-9B-Coder-Q3_K_L.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q3_K_L.gguf) | Q3_K_L | 4.69GB | Lower quality but usable, good for low RAM availability. |
+| [Yi-9B-Coder-Q3_K_M.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q3_K_M.gguf) | Q3_K_M | 4.32GB | Even lower quality. |
+| [Yi-9B-Coder-Q3_K_S.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF//main/Yi-9B-Coder-Q3_K_S.gguf) | Q3_K_S | 3.89GB | Low quality, not recommended. |
+| [Yi-9B-Coder-Q2_K.gguf](https://huggingface.co/bartowski/Yi-9B-Coder-GGUF/blob/main/Yi-9B-Coder-Q2_K.gguf) | Q2_K | 3.35GB | Extremely low quality, *not* recommended.
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Yi-9B-Coder-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fdceae26dbdfc611cc2100c2787efa3c06ec22fba8e87fbafdd01c900edddd83
+size 3354324736

Yi-9B-Coder-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:69599fc57d4c28dfef40ba979f7659b7fd42d65dfb8d3499f9b31eed371c5f4a
+size 4690751232

Yi-9B-Coder-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:94707595f2566c67d9f1b6216a0130d304f6d717e4e620136d442e7ab69a5065
+size 4324404992

Yi-9B-Coder-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:718acb38a520cd0fe4802caf1f022cc05cb0ac6e9cb1580588aa2097d7fbc3cf
+size 3899207424

Yi-9B-Coder-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d89dd2addb8177c60229c70ca2939fc1253e093c09e850fe0cc1b4a4ec78ff3
+size 5036994304

Yi-9B-Coder-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1972d66e8506a486dfd0f6fe2e5d4be8c941c648c9685010d10a84ba45e24504
+size 5328957184

Yi-9B-Coder-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9356c6be1bb8a7b36e2298c5a044a940d9cf67af2cd3294f04dbf3695484f0c4
+size 5071859456

Yi-9B-Coder-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:65982931a309d9bb910fa420169008a0aa4908155cfb6b44e35a328881a18f29
+size 6107852544

Yi-9B-Coder-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5c0145d45a2bebb2dd459006c2381839f1bdafe2b1066b714e33b1b308b313
+size 6258257664

Yi-9B-Coder-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b47cd77f9f6b860ed39f68c8d82b837b4b5bb8f9769e83ef193188f58cb8537
+size 6107852544

Yi-9B-Coder-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d2743171804535d3a053e159d5d9cfa24ab08d99e8a7c377498e5e4ca91688
+size 7245639424

Yi-9B-Coder-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:501164323acfc254aded2f829fc77c425885b6ee5678ffe403c3c47e196b9ba7
+size 9383915264