Instructions to use aipib/llmjp-dareties with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aipib/llmjp-dareties with Transformers:

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

pipe = pipeline("text-generation", model="aipib/llmjp-dareties")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aipib/llmjp-dareties")
model = AutoModelForCausalLM.from_pretrained("aipib/llmjp-dareties", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use aipib/llmjp-dareties 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 aipib/llmjp-dareties:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aipib/llmjp-dareties:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aipib/llmjp-dareties:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aipib/llmjp-dareties: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 aipib/llmjp-dareties:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf aipib/llmjp-dareties: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 aipib/llmjp-dareties:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aipib/llmjp-dareties:Q4_K_M

Use Docker

docker model run hf.co/aipib/llmjp-dareties:Q4_K_M

LM Studio
Jan

vLLM

How to use aipib/llmjp-dareties with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/aipib/llmjp-dareties:Q4_K_M

SGLang

How to use aipib/llmjp-dareties 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 "aipib/llmjp-dareties" \
    --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": "aipib/llmjp-dareties",
		"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 "aipib/llmjp-dareties" \
        --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": "aipib/llmjp-dareties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use aipib/llmjp-dareties with Ollama:
```
ollama run hf.co/aipib/llmjp-dareties:Q4_K_M
```

Unsloth Studio

How to use aipib/llmjp-dareties 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 aipib/llmjp-dareties 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 aipib/llmjp-dareties to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aipib/llmjp-dareties to start chatting

Docker Model Runner
How to use aipib/llmjp-dareties with Docker Model Runner:
```
docker model run hf.co/aipib/llmjp-dareties:Q4_K_M
```

Lemonade

How to use aipib/llmjp-dareties with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aipib/llmjp-dareties:Q4_K_M

Run and chat with the model

lemonade run user.llmjp-dareties-Q4_K_M

List all available models

lemonade list

Atomic Chat

aipib commited on Jun 21, 2024

Commit

23cec42

verified ·

1 Parent(s): 4904b9f

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -25

README.md CHANGED Viewed

@@ -16,31 +16,6 @@ llmjp-dareties is a merge of the following models using [LazyMergekit](https://c
 * [kcoopermiller/llm-jp-1.3b-v1.0-aya](https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya)
 * [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
-## 🧩 Configuration
-```yaml
-slices:
-- sources:
-  - layer_range: [0, 24]
-    model: kcoopermiller/llm-jp-1.3b-v1.0-aya
-    parameters:
-      density: [1, 0.7, 0.1]
-      weight: 1.0
-  - layer_range: [0, 24]
-    model: llm-jp/llm-jp-1.3b-v1.0
-    parameters:
-      density: 0.33
-      weight:
-        - filter: mlp
-          value: 0.5
-        - value: 0
-merge_method: dare_ties
-base_model: llm-jp/llm-jp-1.3b-v1.0
-parameters:
-  normalize: true
-  int8_mask: true
-dtype: bfloat16
-```
 ## 💻 Usage

 * [kcoopermiller/llm-jp-1.3b-v1.0-aya](https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya)
 * [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
 ## 💻 Usage