Instructions to use uukuguy/speechless-sparsetral-mistral-16x7b-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uukuguy/speechless-sparsetral-mistral-16x7b-MoE with Transformers:

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

pipe = pipeline("text-generation", model="uukuguy/speechless-sparsetral-mistral-16x7b-MoE", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("uukuguy/speechless-sparsetral-mistral-16x7b-MoE", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use uukuguy/speechless-sparsetral-mistral-16x7b-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uukuguy/speechless-sparsetral-mistral-16x7b-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uukuguy/speechless-sparsetral-mistral-16x7b-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/uukuguy/speechless-sparsetral-mistral-16x7b-MoE

SGLang

How to use uukuguy/speechless-sparsetral-mistral-16x7b-MoE 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 "uukuguy/speechless-sparsetral-mistral-16x7b-MoE" \
    --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": "uukuguy/speechless-sparsetral-mistral-16x7b-MoE",
		"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 "uukuguy/speechless-sparsetral-mistral-16x7b-MoE" \
        --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": "uukuguy/speechless-sparsetral-mistral-16x7b-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use uukuguy/speechless-sparsetral-mistral-16x7b-MoE with Docker Model Runner:
```
docker model run hf.co/uukuguy/speechless-sparsetral-mistral-16x7b-MoE
```

speechless-sparsetral-16x7b-MoE

speechless-sparsetral-16x7b-MoE is the MoE upgraded version of speechless-code-mistral-7b-v1.0. The MoE fine-tuning adopts Parameter-Efficient Sparsity Crafting (PESC), which is an efficient fine-tuning architecture that uses LoRA modules as expert models, similar to the concept of multi-loras. The model size is approximately 10B.

Specifically, Mistral-7B-0.1 is used as the base model, with 16 experts and 4 expert outputs selected for inference. The fine-tuning dataset includes codefuse-ai/Evol-Instruction-66k to enhance the model's code generation ability. The specific datasets are as follows:

jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
garage-bAInd/Open-Platypus: 100%, 24,926 samples.
WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
Spider: 8,659 samples
codefuse-ai/Evol-Instruction-66k: 100%, 66,862 samples

Alpaca Prompt Format

### Instruction:
<instruction>
### Response:

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name_or_path="uukuguy/speechless-sparsetral-16x7b-MoE"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=True).eval()

system = ""Below is an instruction that describes a task.\nWrite a response that appropriately completes the request.\n\n""
prompt = f"{system}\n\n### Instruction:\n{instruction}\n\n### Response:"

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))

Downloads last month: 16

Safetensors

Model size

9B params

Tensor type

BF16

Datasets used to train uukuguy/speechless-sparsetral-mistral-16x7b-MoE

Paper for uukuguy/speechless-sparsetral-mistral-16x7b-MoE

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Paper • 2401.02731 • Published Jan 5, 2024 • 3

Evaluation results

pass@1 on HumanEval
self-reported