Instructions to use de-coder/UlizaLlama_Q4_K_M-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use de-coder/UlizaLlama_Q4_K_M-gguf with Transformers:

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

pipe = pipeline("text-generation", model="de-coder/UlizaLlama_Q4_K_M-gguf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("de-coder/UlizaLlama_Q4_K_M-gguf")
model = AutoModelForCausalLM.from_pretrained("de-coder/UlizaLlama_Q4_K_M-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use de-coder/UlizaLlama_Q4_K_M-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 de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf de-coder/UlizaLlama_Q4_K_M-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 de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf de-coder/UlizaLlama_Q4_K_M-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 de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf de-coder/UlizaLlama_Q4_K_M-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 de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M

Use Docker

docker model run hf.co/de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use de-coder/UlizaLlama_Q4_K_M-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "de-coder/UlizaLlama_Q4_K_M-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "de-coder/UlizaLlama_Q4_K_M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M

SGLang

How to use de-coder/UlizaLlama_Q4_K_M-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 "de-coder/UlizaLlama_Q4_K_M-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": "de-coder/UlizaLlama_Q4_K_M-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 "de-coder/UlizaLlama_Q4_K_M-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": "de-coder/UlizaLlama_Q4_K_M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use de-coder/UlizaLlama_Q4_K_M-gguf with Ollama:
```
ollama run hf.co/de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use de-coder/UlizaLlama_Q4_K_M-gguf with Docker Model Runner:
```
docker model run hf.co/de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M
```

Lemonade

How to use de-coder/UlizaLlama_Q4_K_M-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull de-coder/UlizaLlama_Q4_K_M-gguf:Q4_K_M

Run and chat with the model

lemonade run user.UlizaLlama_Q4_K_M-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

UlizaLlama_Q4_K_M-gguf / config.json

de-coder

Create config.json

640f687 verified over 2 years ago

Raw

History Blame Contribute Delete

1.62 kB

	{
	"_name_or_path": "de-coder/UlizaLlama_Q4_K_M-gguf",
	"architectures": ["LlamaForCausalLM"],
	"model_type": "llama",
	"torch_dtype": "float16",
	"transformers_version": "4.34.0",

	"vocab_size": 20000,
	"hidden_size": 4096,
	"intermediate_size": 11008,
	"num_hidden_layers": 32,
	"num_attention_heads": 32,
	"num_key_value_heads": 32,
	"hidden_act": "silu",
	"max_position_embeddings": 4096,
	"initializer_range": 0.02,
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000.0,
	"rope_scaling": null,
	"attention_bias": false,
	"use_cache": true,
	"tie_word_embeddings": false,

	"bos_token_id": 1,
	"eos_token_id": 2,
	"pad_token_id": 0,
	"unk_token_id": 0,

	"quantization": {
	"method": "GGUF",
	"bits": 4,
	"variant": "q4_0",
	"block_size": 32,
	"group_size": 32,
	"tensors": {
	"query": "Q4_0",
	"key": "Q4_0",
	"value": "Q4_0",
	"output": "Q4_0",
	"intermediate": "Q4_0",
	"gate": "Q4_0",
	"embedding": "Q4_0",
	"norm": "F16"
	},
	"scales_dtype": "fp16"
	},

	"tokenizer": {
	"type": "BPE",
	"vocab_file": "ulizallama-tokenizer.json",
	"merges_file": "ulizallama-merges.txt"
	},

	"generation": {
	"temperature": 0.7,
	"top_p": 0.95,
	"top_k": 40,
	"repetition_penalty": 1.1,
	"max_new_tokens": 512
	},

	"base_model": {
	"name": "Jacaranda/kiswallama-pretrained",
	"type": "Llama2 Continual Pretraining"
	},
	"quantization_process": {
	"library": "llama.cpp",
	"version": "1.0.0",
	"command": "llama.cpp quantize ulizallama-7b.gguf ulizallama-7b-gguf-q4_0.bin q4_0"
	}
	}