Instructions to use stabilityai/stablelm-2-zephyr-1_6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/stablelm-2-zephyr-1_6b with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stablelm-2-zephyr-1_6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b")
model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use stabilityai/stablelm-2-zephyr-1_6b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="stabilityai/stablelm-2-zephyr-1_6b",
	filename="stablelm-2-zephyr-1_6b-Q4_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use stabilityai/stablelm-2-zephyr-1_6b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0
# Run inference directly in the terminal:
llama-cli -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0
# Run inference directly in the terminal:
llama-cli -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0

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 stabilityai/stablelm-2-zephyr-1_6b:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0

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 stabilityai/stablelm-2-zephyr-1_6b:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stabilityai/stablelm-2-zephyr-1_6b:Q4_0

Use Docker

docker model run hf.co/stabilityai/stablelm-2-zephyr-1_6b:Q4_0

LM Studio
Jan

vLLM

How to use stabilityai/stablelm-2-zephyr-1_6b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/stablelm-2-zephyr-1_6b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-2-zephyr-1_6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stabilityai/stablelm-2-zephyr-1_6b:Q4_0

SGLang

How to use stabilityai/stablelm-2-zephyr-1_6b 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 "stabilityai/stablelm-2-zephyr-1_6b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-2-zephyr-1_6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "stabilityai/stablelm-2-zephyr-1_6b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-2-zephyr-1_6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use stabilityai/stablelm-2-zephyr-1_6b with Ollama:
```
ollama run hf.co/stabilityai/stablelm-2-zephyr-1_6b:Q4_0
```

Unsloth Studio new

How to use stabilityai/stablelm-2-zephyr-1_6b 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 stabilityai/stablelm-2-zephyr-1_6b 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 stabilityai/stablelm-2-zephyr-1_6b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for stabilityai/stablelm-2-zephyr-1_6b to start chatting

Docker Model Runner
How to use stabilityai/stablelm-2-zephyr-1_6b with Docker Model Runner:
```
docker model run hf.co/stabilityai/stablelm-2-zephyr-1_6b:Q4_0
```

Lemonade

How to use stabilityai/stablelm-2-zephyr-1_6b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stabilityai/stablelm-2-zephyr-1_6b:Q4_0

Run and chat with the model

lemonade run user.stablelm-2-zephyr-1_6b-Q4_0

List all available models

lemonade list

How to finetuning this model?

by LeMoussel - opened Jan 23, 2024

Discussion

LeMoussel

Jan 23, 2024

•

edited Jan 23, 2024

I would like to work on finetuning this model.
It seems that we can do this with axolotl

Which axolotl configuration file to adapt?
Or a second solution of using PEFT LoRA and bitsandbytes (for exemple: fine tune OPT-6.7b)

Any recommendations for me on how to do this?

LeMoussel changed discussion title from How to finetuning this model to How to finetuning this model? Jan 23, 2024

interstellarninja

Jan 24, 2024

hi LeMoussel,

I just finished finetuning the model with the following axolotl config:

base_model: stabilityai/stablelm-2-zephyr-1_6b
base_model_config: stabilityai/stablelm-2-zephyr-1_6b
model_type: StableLMEpochForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: interstellarninja/tool-calls-multiturn
    type: sharegpt.load_multirole
    conversation: zephyr

val_set_size: 0
dataset_prepared_path: last_run_prepared
output_dir: ./stablelm-1_6b-tool-calling-1

sequence_len: 4096
sample_packing: false
eval_sample_packing: false
eval_batch_size: 1

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_on_cpu: true

lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: tool-calling-multiturn-1_6b
wandb_run_id: stablelm-1_6b-tool-calling-1

data_seed: 42
seed: 42

gradient_accumulation_steps: 1
micro_batch_size: 1
warmup_steps: 25
num_epochs: 3
optimizer: adamw_bnb_8bit
learning_rate: 0.00001
lr_scheduler: cosine
weight_decay: 0.02

train_on_inputs: false
group_by_length: true
bf16: true
fp16: false
tf32: true

gradient_checkpointing: true
logging_steps: 1
xformers_attention: false
flash_attention: false

save_strategy: epoch
save_safetensors: true
resume_from_checkpoint: false

hub_model_id: interstellarninja/stablelm-2-zephyr-1_6b-tool-caller

LeMoussel

Jan 24, 2024

Thank you for your help. Very interesting.
I don't find your dataset interstellarninja/tool-calls-multiturn on HuggingFace. Do you have an example dataset for finetuning this model?

g-ronimo

Jan 24, 2024

here's my notebook for finetuning it, no trainer like axolotl though, just HF code
https://github.com/geronimi73/TinyLlama-versus-StableLM2/blob/main/nb_finetune_StableLM2_OA2.ipynb

LeMoussel

Jan 24, 2024

•

edited Jan 24, 2024

Thank you so much !
You use g-ronimo/oasst2_top1_en as dataset.
From what I understand the dataset must be in the form an list of array like this
[ { "content": "Some content user ....", "role": "user" }, { "content": "Some content assistant ...", "role": "assistant" } ]
Do you think it is necessary to have content assistant? Could this be empty?

Rem: I want to create a dataset in French.

g-ronimo

Jan 24, 2024

Do you think it is necessary to have content assistant? Could this be empty?

could you please rephrase, not sure what you mean

LeMoussel

Jan 24, 2024

•

edited Jan 24, 2024

Does dataset may contain only Some content user ....
Eg:

[ { "content": "Some content1 ....", "role": "user" }, { "content": "", "role": "assistant" } ]
[ { "content": "Some content2 ....", "role": "user" }, { "content": "", "role": "assistant" } ]
.....

israellaguan

Jun 4, 2024

I think the idea was to create at least a question and an answer, if you remove the assistant object, you remove the answer.

If your use case is to expose to "user questions" you can do it but I think it can make the model to answer questions with "", which I think is not desirable. My suggestion is that you explain more your use case or to create synthetic answers with a more capable model or even humans.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment