Instructions to use afrideva/Walter-StableLM-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/Walter-StableLM-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/Walter-StableLM-3B-GGUF",
	filename="walter-stablelm-3b.fp16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use afrideva/Walter-StableLM-3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/Walter-StableLM-3B-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 afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/Walter-StableLM-3B-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 afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/Walter-StableLM-3B-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 afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/Walter-StableLM-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/Walter-StableLM-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/Walter-StableLM-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/Walter-StableLM-3B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/Walter-StableLM-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/Walter-StableLM-3B-GGUF:Q4_K_M

Ollama
How to use afrideva/Walter-StableLM-3B-GGUF with Ollama:
```
ollama run hf.co/afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/Walter-StableLM-3B-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 afrideva/Walter-StableLM-3B-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 afrideva/Walter-StableLM-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/Walter-StableLM-3B-GGUF to start chatting

Docker Model Runner
How to use afrideva/Walter-StableLM-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/Walter-StableLM-3B-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/Walter-StableLM-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/Walter-StableLM-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Walter-StableLM-3B-GGUF-Q4_K_M

List all available models

lemonade list

KnutJaegersberg/Walter-StableLM-3B-GGUF

Quantized GGUF model files for Walter-StableLM-3B from KnutJaegersberg

Name	Quant method	Size
walter-stablelm-3b.fp16.gguf	fp16	5.59 GB
walter-stablelm-3b.q2_k.gguf	q2_k	1.20 GB
walter-stablelm-3b.q3_k_m.gguf	q3_k_m	1.39 GB
walter-stablelm-3b.q4_k_m.gguf	q4_k_m	1.71 GB
walter-stablelm-3b.q5_k_m.gguf	q5_k_m	1.99 GB
walter-stablelm-3b.q6_k.gguf	q6_k	2.30 GB
walter-stablelm-3b.q8_0.gguf	q8_0	2.97 GB

Original Model Card:

Walter is an unaligned, free thinking AI assistant that has been given time to think about things. It's trained on instruction datasets with open source licenses. It covers a lot of tasks, 2/3 of the samples are from large datasets like flan, but also other datasets. It knows a few tricks, shown by the prompting examples below:

General Prompt Examples:

### Instruction:
Please answer the following question: Process:  - The bat sends out sound waves from their mouth or nose - The sound waves hit an object - Echoes are produced - The echo returns to the bat&#x27;s ears - The bat hears the echo - The bat can figure out where the object is located.  suppose No bats live here happens, how will it affect STRONGER echolocation.  Which of the following is the supposed perturbation?  - directly impacting a step of the process - indirectly impacting a step of the process - not impacting any step of the process Answer: 
### Response:
indirectly impacting a step of the process

### Instruction:
You will be given a text in Russian language which contain different emotion labels from the list - ['joy', ' sadness', 'surprise', 'fear', 'anger']. You need to output the incorrect emotion label, which is irrelevant to the input text. Your answer (i) should contain only one emotion label (ii) should be unambiguous. 
### Input:
То чувство, когда идешь домой после 3-х часовой тренировки и в подъезде пахнет запеченной курицей - зачем вы меня дразните :( 
### Response:
surprise

CoT Prompt Example:

### Instruction:
In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer. PersonX puts ___ on PersonY's car 
### Reasoning:
Since PersonX is putting water on PersonY's car, it could be assumed that the car is on fire. 
### Response:
water

Summarization Example:

### Instruction:
Below is a text. Write a comprehensive, concise and coherent summary. 
### Input:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1).  It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking.  An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly. ==Overview== Embodied bilingual language refers to the role ......
### Response:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1).  It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking.  An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly.

Essay Example:

### Instruction:
Write the original essay for the following summary: A sleeveless dress with a round neck is a great day dress and can be worn for both formal and casual occasions. It has a sweetheart neckline and is made from 100% silk. The dress has a chiffon overlay that covers up the miniskirt and still adds to the class of the dress. 
### Response:
Sleeveless Dress with a Round Neck Essay Casual wear, day dress, more formal dress The garment is a sleeveless dress with a round neck and has a sweetheart neckline. It has sheer detail on the neckline and on the back. These aspects of design make it suitable to be worn for day and evening occasions. Its great detail and chicness make it suitable for more formal events, ....

Downloads last month: 44

GGUF

Model size

3B params

Architecture

stablelm

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/Walter-StableLM-3B-GGUF

Base model

KnutJaegersberg/Walter-StableLM-3B

Quantized

(1)

this model

afrideva
/

Walter-StableLM-3B-GGUF

KnutJaegersberg/Walter-StableLM-3B-GGUF

Original Model Card:

Model tree for afrideva/Walter-StableLM-3B-GGUF

Dataset used to train afrideva/Walter-StableLM-3B-GGUF