metadata
license: apache-2.0
tags:
- moe
- merge
- mergekit
- lazymergekit
- cognitivecomputations/dolphin-2_6-phi-2
- lxuechen/phi-2-dpo
- Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
- mrm8488/phi-2-coder
phixtral-4x2.8
phixtral-2x2.8 is a Mixure of Experts (MoE) made with the following models using a custom version of mergekit:
- cognitivecomputations/dolphin-2_6-phi-2
- lxuechen/phi-2-dpo
- Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
- mrm8488/phi-2-coder
🧩 Configuration
base_model: cognitivecomputations/dolphin-2_6-phi-2
gate_mode: cheap_embed
experts:
- source_model: cognitivecomputations/dolphin-2_6-phi-2
positive_prompts: [""]
- source_model: lxuechen/phi-2-dpo
positive_prompts: [""]
- source_model: Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
positive_prompts: [""]
- source_model: mrm8488/phi-2-coder
positive_prompts: [""]
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/phixtral-4x2.8"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])