Instructions to use andrijdavid/LMCocktail-10.7B-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andrijdavid/LMCocktail-10.7B-v1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="andrijdavid/LMCocktail-10.7B-v1-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andrijdavid/LMCocktail-10.7B-v1-GGUF")
model = AutoModelForCausalLM.from_pretrained("andrijdavid/LMCocktail-10.7B-v1-GGUF", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use andrijdavid/LMCocktail-10.7B-v1-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 andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andrijdavid/LMCocktail-10.7B-v1-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 andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use andrijdavid/LMCocktail-10.7B-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andrijdavid/LMCocktail-10.7B-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andrijdavid/LMCocktail-10.7B-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M

SGLang

How to use andrijdavid/LMCocktail-10.7B-v1-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 "andrijdavid/LMCocktail-10.7B-v1-GGUF" \
    --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": "andrijdavid/LMCocktail-10.7B-v1-GGUF",
		"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 "andrijdavid/LMCocktail-10.7B-v1-GGUF" \
        --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": "andrijdavid/LMCocktail-10.7B-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use andrijdavid/LMCocktail-10.7B-v1-GGUF with Ollama:
```
ollama run hf.co/andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use andrijdavid/LMCocktail-10.7B-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M
```

Lemonade

How to use andrijdavid/LMCocktail-10.7B-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull andrijdavid/LMCocktail-10.7B-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LMCocktail-10.7B-v1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

LMCocktail-10.7B-v1-GGUF / alpaca_eval /chatgpt_fn_--SOLAR-10-7B-LMCocktail /leaderboard.csv

andrijdavid

Upload folder using huggingface_hub

7c669f0 almost 3 years ago

Raw History Blame Contribute Delete

1.15 kB

,win_rate,standard_error,n_wins,n_wins_base,n_draws,n_total,mode,avg_length
gpt4,73.7888198757764,1.5359801545073597,588,205,12,805,minimal,1365
SOLAR-10.7B-LMCocktail,73.44527363184079,1.5572150363643398,590,213,1,804,community,1203
claude,70.37267080745342,1.599519507147828,562,234,9,805,minimal,1082
chatgpt,66.08695652173913,1.6626479994330317,529,270,6,805,minimal,811
wizardlm-13b,65.15527950310559,1.670034107787565,520,276,9,805,minimal,985
vicuna-13b,64.09937888198758,1.6895185863153146,515,288,2,805,minimal,1037
guanaco-65b,62.36024844720497,1.7086348811605765,502,303,0,805,minimal,1249
oasst-rlhf-llama-33b,62.0496894409938,1.7080028976103514,498,304,3,805,minimal,1079
alpaca-farm-ppo-human,60.24844720496895,1.7169496733548772,481,316,8,805,minimal,803
falcon-40b-instruct,56.52173913043478,1.7438750520312944,453,348,4,805,minimal,662
phi-2-alpaca-gpt4-dpo,55.59701492537313,1.7533719245384989,447,357,0,804,community,4532
text_davinci_003,50.0,0.0,0,0,805,805,minimal,307
alpaca-7b,45.21739130434783,1.7375846781579476,356,433,16,805,minimal,396
text_davinci_001,28.07453416149068,1.5602183426587484,216,569,20,805,minimal,296

	,win_rate,standard_error,n_wins,n_wins_base,n_draws,n_total,mode,avg_length
	gpt4,73.7888198757764,1.5359801545073597,588,205,12,805,minimal,1365
	SOLAR-10.7B-LMCocktail,73.44527363184079,1.5572150363643398,590,213,1,804,community,1203
	claude,70.37267080745342,1.599519507147828,562,234,9,805,minimal,1082
	chatgpt,66.08695652173913,1.6626479994330317,529,270,6,805,minimal,811
	wizardlm-13b,65.15527950310559,1.670034107787565,520,276,9,805,minimal,985
	vicuna-13b,64.09937888198758,1.6895185863153146,515,288,2,805,minimal,1037
	guanaco-65b,62.36024844720497,1.7086348811605765,502,303,0,805,minimal,1249
	oasst-rlhf-llama-33b,62.0496894409938,1.7080028976103514,498,304,3,805,minimal,1079
	alpaca-farm-ppo-human,60.24844720496895,1.7169496733548772,481,316,8,805,minimal,803
	falcon-40b-instruct,56.52173913043478,1.7438750520312944,453,348,4,805,minimal,662
	phi-2-alpaca-gpt4-dpo,55.59701492537313,1.7533719245384989,447,357,0,804,community,4532
	text_davinci_003,50.0,0.0,0,0,805,805,minimal,307
	alpaca-7b,45.21739130434783,1.7375846781579476,356,433,16,805,minimal,396
	text_davinci_001,28.07453416149068,1.5602183426587484,216,569,20,805,minimal,296