YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Boundary-Solar-Chat-2x10.7B-MoE - GGUF
- Model creator: https://huggingface.co/NotAiLOL/
- Original model: https://huggingface.co/NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE/
Original model description:
license: apache-2.0 tags: - moe - merge - mergekit - NousResearch/Nous-Hermes-2-SOLAR-10.7B - upstage/SOLAR-10.7B-Instruct-v1.0 - llama - Llama base_model: - NousResearch/Nous-Hermes-2-SOLAR-10.7B - upstage/SOLAR-10.7B-Instruct-v1.0
Boundary-Solar-Chat-2x10.7B-MoE
Boundary-Solar-Chat-2x10.7B-MoE is a Mixture of Experts (MoE) made with the following models:
𧩠Configuration
base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
dtype: float16
gate_mode: cheap_embed
experts:
- source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
positive_prompts: ["You are a helpful general assistant."]
- source_model: upstage/SOLAR-10.7B-Instruct-v1.0
positive_prompts: ["You are assistant for question and answering."]
π» Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE"
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"])
- Downloads last month
- 125