Instructions to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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": "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M

SGLang

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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": "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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 "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-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": "QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF 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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF 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 QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen1.5-MoE-A2.7B-Wikihow-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF

This is quantized version of MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow created using llama.cpp

Original Model Card

models/Qwen1.5-MoE-A2.7B-Wikihow

This model is a fine-tuned version of Qwen/Qwen1.5-MoE-A2.7B on the HuggingFaceTB/cosmopedia dataset.

How to use it

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

pipe = pipeline("text-generation", model="MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow")

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

See axolotl config

axolotl version: 0.4.0

base_model: Qwen/Qwen1.5-MoE-A2.7B
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

# hub_model_id: MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow
# hf_use_auth_token: true

chat_template: chatml

datasets:
  - path: HuggingFaceTB/cosmopedia
    name: wikihow
    type:
      system_prompt: ""
      field_instruction: prompt
      field_output: text
      format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
      no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
    
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./models/Qwen1.5-MoE-A2.7B-Wikihow

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

Framework versions

PEFT 0.10.0
Transformers 4.40.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	11.43
IFEval (0-Shot)	29.54
BBH (3-Shot)	15.47
MATH Lvl 5 (4-Shot)	2.87
GPQA (0-shot)	3.36
MuSR (0-shot)	2.01
MMLU-PRO (5-shot)	15.34

Downloads last month: 223

GGUF

Model size

14B params

Architecture

qwen2moe

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/Qwen1.5-MoE-A2.7B-Wikihow-GGUF

Base model

Qwen/Qwen1.5-MoE-A2.7B

Quantized

(8)

this model

QuantFactory
/

Qwen1.5-MoE-A2.7B-Wikihow-GGUF