Instructions to use second-state/Yi-1.5-34B-Chat-16K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/Yi-1.5-34B-Chat-16K-GGUF",
	filename="Yi-1.5-34B-Chat-16K-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Yi-1.5-34B-Chat-16K-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 second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Yi-1.5-34B-Chat-16K-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 second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Yi-1.5-34B-Chat-16K-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Yi-1.5-34B-Chat-16K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M

Ollama
How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with Ollama:
```
ollama run hf.co/second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
```

Unsloth Studio

How to use second-state/Yi-1.5-34B-Chat-16K-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 second-state/Yi-1.5-34B-Chat-16K-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 second-state/Yi-1.5-34B-Chat-16K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/Yi-1.5-34B-Chat-16K-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Yi-1.5-34B-Chat-16K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Yi-1.5-34B-Chat-16K-GGUF-Q4_K_M

List all available models

lemonade list

Yi-1.5-34B-Chat-16K-GGUF / README.md

apepkuss79

Update README.md

383b00d verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

4.88 kB

	---
	base_model: 01-ai/Yi-1.5-34B-Chat-16K
	inference: false
	license: other
	license_link: LICENSE
	license_name: yi-license
	model_creator: 01-ai
	model_name: Yi-1.5-34B-Chat-16
	model_type: yi
	pipeline_tag: text-generation
	quantized_by: Second State Inc.
	---

	<!-- header start -->
	<!-- 200823 -->
	<div style="width: auto; margin-left: auto; margin-right: auto">
	<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
	</div>
	<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
	<!-- header end -->

	# Yi-1.5-34B-Chat-16K-GGUF

	## Original Model

	[01-ai/Yi-1.5-34B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K)

	## Run with LlamaEdge

	- LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) and above

	- Prompt template

	- Prompt type: `chatml`

	- Prompt string

	```text
	<\|im_start\|>system
	{system_message}<\|im_end\|>
	<\|im_start\|>user
	{prompt}<\|im_end\|>
	<\|im_start\|>assistant
	```

	- Reverse prompt: `<\|im_end\|>`

	- Context size: `16384`

	- Run as LlamaEdge service

	```bash
	wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
	llama-api-server.wasm \
	--prompt-template chatml \
	--reverse-prompt "<\|im_end\|>" \
	--ctx-size 16384 \
	--model-name Yi-1.5-34B-Chat-16K
	```

	- Run as LlamaEdge command app

	```bash
	wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
	llama-chat.wasm \
	--prompt-template chatml \
	--reverse-prompt "<\|im_end\|>" \
	--ctx-size 16384
	```

	## Quantized GGUF Models

	\| Name \| Quant method \| Bits \| Size \| Use case \|
	\| ---- \| ---- \| ---- \| ---- \| ----- \|
	\| [Yi-1.5-34B-Chat-16K-Q2_K.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q2_K.gguf) \| Q2_K \| 2 \|12.8 GB\| smallest, significant quality loss - not recommended for most purposes \|
	\| [Yi-1.5-34B-Chat-16K-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_L.gguf) \| Q3_K_L \| 3 \| 18.1 GB\| small, substantial quality loss \|
	\| [Yi-1.5-34B-Chat-16K-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_M.gguf) \| Q3_K_M \| 3 \| 16.7 GB\| very small, high quality loss \|
	\| [Yi-1.5-34B-Chat-16K-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_S.gguf) \| Q3_K_S \| 3 \| 15 GB\| very small, high quality loss \|
	\| [Yi-1.5-34B-Chat-16K-Q4_0.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_0.gguf) \| Q4_0 \| 4 \| 19.5 GB\| legacy; small, very high quality loss - prefer using Q3_K_M \|
	\| [Yi-1.5-34B-Chat-16K-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_M.gguf) \| Q4_K_M \| 4 \| 20.7 GB\| medium, balanced quality - recommended \|
	\| [Yi-1.5-34B-Chat-16K-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_S.gguf) \| Q4_K_S \| 4 \| 19.6 GB\| small, greater quality loss \|
	\| [Yi-1.5-34B-Chat-16K-Q5_0.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_0.gguf) \| Q5_0 \| 5 \| 23.7 GB\| legacy; medium, balanced quality - prefer using Q4_K_M \|
	\| [Yi-1.5-34B-Chat-16K-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_M.gguf) \| Q5_K_M \| 5 \| 24.3 GB\| large, very low quality loss - recommended \|
	\| [Yi-1.5-34B-Chat-16K-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_S.gguf) \| Q5_K_S \| 5 \| 23.7 GB\| large, low quality loss - recommended \|
	\| [Yi-1.5-34B-Chat-16K-Q6_K.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q6_K.gguf) \| Q6_K \| 6 \| 28.2 GB\| very large, extremely low quality loss \|
	\| [Yi-1.5-34B-Chat-16K-Q8_0.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q8_0.gguf) \| Q8_0 \| 8 \| 36.5 GB\| very large, extremely low quality loss - not recommended \|
	\| [Yi-1.5-34B-Chat-16K-f16-00001-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00001-of-00003.gguf) \| f16 \| 16 \| 32.2 GB\| \|
	\| [Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf) \| f16 \| 16 \| 32.1 GB\| \|
	\| [Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf) \| f16 \| 16 \| 4.48 GB\| \|

	Quantized with llama.cpp b3135