Instructions to use afrideva/stablelm-3b-4e1t-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/stablelm-3b-4e1t-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="afrideva/stablelm-3b-4e1t-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("afrideva/stablelm-3b-4e1t-GGUF", dtype="auto")

llama-cpp-python

How to use afrideva/stablelm-3b-4e1t-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/stablelm-3b-4e1t-GGUF",
	filename="stablelm-3b-4e1t.q2_k.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/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/stablelm-3b-4e1t-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M

SGLang

How to use afrideva/stablelm-3b-4e1t-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 "afrideva/stablelm-3b-4e1t-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": "afrideva/stablelm-3b-4e1t-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 "afrideva/stablelm-3b-4e1t-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": "afrideva/stablelm-3b-4e1t-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use afrideva/stablelm-3b-4e1t-GGUF with Ollama:
```
ollama run hf.co/afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/stablelm-3b-4e1t-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/stablelm-3b-4e1t-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/stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF to start chatting

Docker Model Runner
How to use afrideva/stablelm-3b-4e1t-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/stablelm-3b-4e1t-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/stablelm-3b-4e1t-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.stablelm-3b-4e1t-GGUF-Q4_K_M

List all available models

lemonade list

stabilityai/stablelm-3b-4e1t-GGUF

Quantized GGUF model files for stablelm-3b-4e1t from stabilityai

** StableLM support currently requires using this llama.cpp fork by Galunid. Quantized and tested with the stablelm-support branch, commit a00bb06 **

StableLM support pull request: https://github.com/ggerganov/llama.cpp/pull/3586

Name	Quant method	Size
stablelm-3b-4e1t.q2_k.gguf	q2_k	1.20 GB
stablelm-3b-4e1t.q3_k_m.gguf	q3_k_m	1.39 GB
stablelm-3b-4e1t.q4_k_m.gguf	q4_k_m	1.71 GB
stablelm-3b-4e1t.q5_k_m.gguf	q5_k_m	1.99 GB
stablelm-3b-4e1t.q6_k.gguf	q6_k	2.30 GB
stablelm-3b-4e1t.q8_0.gguf	q8_0	2.97 GB

Original Model Card:

`StableLM-3B-4E1T`

Model Description

StableLM-3B-4E1T is a 3 billion parameter decoder-only language model pre-trained on 1 trillion tokens of diverse English and code datasets for 4 epochs.

Usage

Get started generating text with StableLM-3B-4E1T by using the following code snippet:

from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
model = AutoModelForCausalLM.from_pretrained(
  "stabilityai/stablelm-3b-4e1t",
  trust_remote_code=True,
  torch_dtype="auto",
)
model.cuda()
inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to("cuda")
tokens = model.generate(
  **inputs,
  max_new_tokens=64,
  temperature=0.75,
  top_p=0.95,
  do_sample=True,
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))

Model Details

Developed by: Stability AI
Model type: StableLM-3B-4E1T models are auto-regressive language models based on the transformer decoder architecture.
Language(s): English
Library: GPT-NeoX
License: Model checkpoints are licensed under the Creative Commons license (CC BY-SA-4.0). Under this license, you must give credit to Stability AI, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the Stability AI endorses you or your use.
Contact: For questions and comments about the model, please email lm@stability.ai

Model Architecture

The model is a decoder-only transformer similar to the LLaMA (Touvron et al., 2023) architecture with the following modifications:

Parameters	Hidden Size	Layers	Heads	Sequence Length
2,795,443,200	2560	32	32	4096

Position Embeddings: Rotary Position Embeddings (Su et al., 2021) applied to the first 25% of head embedding dimensions for improved throughput following Black et al. (2022).
Normalization: LayerNorm (Ba et al., 2016) with learned bias terms as opposed to RMSNorm (Zhang & Sennrich, 2019).
Tokenizer: GPT-NeoX (Black et al., 2022).

Training

For complete dataset and training details, please see the StableLM-3B-4E1T Technical Report.

Training Dataset

The dataset is comprised of a filtered mixture of open-source large-scale datasets available on the HuggingFace Hub: Falcon RefinedWeb extract (Penedo et al., 2023), RedPajama-Data (Together Computer., 2023) and The Pile (Gao et al., 2020) both without the Books3 subset, and StarCoder (Li et al., 2023).

Given the large amount of web data, we recommend fine-tuning the base StableLM-3B-4E1T for your downstream tasks.

Training Procedure

The model is pre-trained on the aforementioned datasets in bfloat16 precision, optimized with AdamW, and trained using the NeoX tokenizer with a vocabulary size of 50,257. We outline the complete hyperparameters choices in the project's GitHub repository - config.

Training Infrastructure

Hardware: StableLM-3B-4E1T was trained on the Stability AI cluster across 256 NVIDIA A100 40GB GPUs (AWS P4d instances). Training began on August 23, 2023, and took approximately 30 days to complete.
Software: We use a fork of gpt-neox (EleutherAI, 2021), train under 2D parallelism (Data and Tensor Parallel) with ZeRO-1 (Rajbhandari et al., 2019), and rely on flash-attention as well as SwiGLU and Rotary Embedding kernels from FlashAttention-2 (Dao et al., 2023)

Use and Limitations

Intended Use

The model is intended to be used as a foundational base model for application-specific fine-tuning. Developers must evaluate and fine-tune the model for safe performance in downstream applications.

Limitations and Bias

As a base model, this model may exhibit unreliable, unsafe, or other undesirable behaviors that must be corrected through evaluation and fine-tuning prior to deployment. The pre-training dataset may have contained offensive or inappropriate content, even after applying data cleansing filters, which can be reflected in the model-generated text. We recommend that users exercise caution when using these models in production systems. Do not use the models if they are unsuitable for your application, or for any applications that may cause deliberate or unintentional harm to others.

How to Cite

@misc{StableLM-3B-4E1T,
      url={[https://huggingface.co/stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t)},
      title={StableLM 3B 4E1T},
      author={Tow, Jonathan and Bellagente, Marco and Mahan, Dakota and Riquelme, Carlos}
}

Downloads last month: 2,106

GGUF

Model size

3B params

Architecture

stablelm

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for afrideva/stablelm-3b-4e1t-GGUF

Base model

stabilityai/stablelm-3b-4e1t

Quantized

(7)

this model

Datasets used to train afrideva/stablelm-3b-4e1t-GGUF

Papers for afrideva/stablelm-3b-4e1t-GGUF