Downloads · 30 days
198
4% of all-time downloads
RichardErkhov/Isotonic_-_smol_llama-4x220M-MoE-gguf
Isotonic_-_smol_llama-4x220M-MoE-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
198
4% of all-time downloads
All-time downloads
4.5K
Public
Repo size
6.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf7.9 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
smol_llama-4x220M-MoE - GGUF
| Name | Quant method | Size |
|---|---|---|
| smol_llama-4x220M-MoE.Q2_K.gguf | Q2_K | 0.22GB |
| smol_llama-4x220M-MoE.IQ3_XS.gguf | IQ3_XS | 0.24GB |
| smol_llama-4x220M-MoE.IQ3_S.gguf | IQ3_S | 0.25GB |
| smol_llama-4x220M-MoE.Q3_K_S.gguf | Q3_K_S | 0.25GB |
| smol_llama-4x220M-MoE.IQ3_M.gguf | IQ3_M | 0.25GB |
| smol_llama-4x220M-MoE.Q3_K.gguf | Q3_K | 0.27GB |
| smol_llama-4x220M-MoE.Q3_K_M.gguf | Q3_K_M | 0.27GB |
| smol_llama-4x220M-MoE.Q3_K_L.gguf | Q3_K_L | 0.29GB |
| smol_llama-4x220M-MoE.IQ4_XS.gguf | IQ4_XS | 0.31GB |
| smol_llama-4x220M-MoE.Q4_0.gguf | Q4_0 | 0.32GB |
| smol_llama-4x220M-MoE.IQ4_NL.gguf | IQ4_NL | 0.32GB |
| smol_llama-4x220M-MoE.Q4_K_S.gguf | Q4_K_S | 0.32GB |
| smol_llama-4x220M-MoE.Q4_K.gguf | Q4_K | 0.34GB |
| smol_llama-4x220M-MoE.Q4_K_M.gguf | Q4_K_M | 0.34GB |
| smol_llama-4x220M-MoE.Q4_1.gguf | Q4_1 | 0.35GB |
| smol_llama-4x220M-MoE.Q5_0.gguf | Q5_0 | 0.39GB |
| smol_llama-4x220M-MoE.Q5_K_S.gguf | Q5_K_S | 0.39GB |
| smol_llama-4x220M-MoE.Q5_K.gguf | Q5_K | 0.4GB |
| smol_llama-4x220M-MoE.Q5_K_M.gguf | Q5_K_M | 0.4GB |
| smol_llama-4x220M-MoE.Q5_1.gguf | Q5_1 | 0.42GB |
| smol_llama-4x220M-MoE.Q6_K.gguf | Q6_K | 0.46GB |
| smol_llama-4x220M-MoE.Q8_0.gguf | Q8_0 | 0.59GB |
license: apache-2.0 tags:
🌟 Buying me coffee is a direct way to show support for this project. <a href="https://www.buymeacoffee.com/isotonic"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
smol_llama-4x220M-MoE is a Mixure of Experts (MoE) made with the following models using LazyMergekit:
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Isotonic/smol_llama-4x220M-MoE"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.bfloat16},
)
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"])
experts:
- source_model: BEE-spoke-data/smol_llama-220M-openhermes
positive_prompts:
- "reasoning"
- "logic"
- "problem-solving"
- "critical thinking"
- "analysis"
- "synthesis"
- "evaluation"
- "decision-making"
- "judgment"
- "insight"
- source_model: BEE-spoke-data/beecoder-220M-python
positive_prompts:
- "program"
- "software"
- "develop"
- "build"
- "create"
- "design"
- "implement"
- "debug"
- "test"
- "code"
- "python"
- "programming"
- "algorithm"
- "function"
- source_model: BEE-spoke-data/zephyr-220m-sft-full
positive_prompts:
- "storytelling"
- "narrative"
- "fiction"
- "creative writing"
- "plot"
- "characters"
- "dialogue"
- "setting"
- "emotion"
- "imagination"
- "scene"
- "story"
- "character"
- source_model: BEE-spoke-data/zephyr-220m-dpo-full
positive_prompts:
- "chat"
- "conversation"
- "dialogue"
- "discuss"
- "ask questions"
- "share thoughts"
- "explore ideas"
- "learn new things"
- "personal assistant"
- "friendly helper"