Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) PowerMoE-3b - GGUF - Model creator: https://huggingface.co/ibm/ - Original model: https://huggingface.co/ibm/PowerMoE-3b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [PowerMoE-3b.Q2_K.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q2_K.gguf) | Q2_K | 1.18GB | | [PowerMoE-3b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.IQ3_XS.gguf) | IQ3_XS | 1.32GB | | [PowerMoE-3b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.IQ3_S.gguf) | IQ3_S | 1.39GB | | [PowerMoE-3b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q3_K_S.gguf) | Q3_K_S | 1.39GB | | [PowerMoE-3b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.IQ3_M.gguf) | IQ3_M | 1.41GB | | [PowerMoE-3b.Q3_K.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q3_K.gguf) | Q3_K | 1.53GB | | [PowerMoE-3b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q3_K_M.gguf) | Q3_K_M | 1.53GB | | [PowerMoE-3b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q3_K_L.gguf) | Q3_K_L | 1.65GB | | [PowerMoE-3b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.IQ4_XS.gguf) | IQ4_XS | 1.72GB | | [PowerMoE-3b.Q4_0.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q4_0.gguf) | Q4_0 | 1.79GB | | [PowerMoE-3b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.IQ4_NL.gguf) | IQ4_NL | 1.81GB | | [PowerMoE-3b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q4_K_S.gguf) | Q4_K_S | 1.81GB | | [PowerMoE-3b.Q4_K.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q4_K.gguf) | Q4_K | 1.92GB | | [PowerMoE-3b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q4_K_M.gguf) | Q4_K_M | 1.92GB | | [PowerMoE-3b.Q4_1.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q4_1.gguf) | Q4_1 | 1.99GB | | [PowerMoE-3b.Q5_0.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q5_0.gguf) | Q5_0 | 2.18GB | | [PowerMoE-3b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q5_K_S.gguf) | Q5_K_S | 2.18GB | | [PowerMoE-3b.Q5_K.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q5_K.gguf) | Q5_K | 2.24GB | | [PowerMoE-3b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q5_K_M.gguf) | Q5_K_M | 2.24GB | | [PowerMoE-3b.Q5_1.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q5_1.gguf) | Q5_1 | 2.37GB | | [PowerMoE-3b.Q6_K.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q6_K.gguf) | Q6_K | 2.59GB | | [PowerMoE-3b.Q8_0.gguf](https://huggingface.co/RichardErkhov/ibm_-_PowerMoE-3b-gguf/blob/main/PowerMoE-3b.Q8_0.gguf) | Q8_0 | 3.35GB | Original model description: --- pipeline_tag: text-generation inference: false license: apache-2.0 library_name: transformers model-index: - name: ibm/PowerMoE-3b results: - task: type: text-generation dataset: type: lm-eval-harness name: ARC metrics: - name: accuracy-norm type: accuracy-norm value: 58.1 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: BoolQ metrics: - name: accuracy type: accuracy value: 65.0 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: Hellaswag metrics: - name: accuracy-norm type: accuracy-norm value: 71.5 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: OpenBookQA metrics: - name: accuracy-norm type: accuracy-norm value: 41.0 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: PIQA metrics: - name: accuracy-norm type: accuracy-norm value: 79.1 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: Winogrande metrics: - name: accuracy-norm type: accuracy-norm value: 65.0 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: MMLU (5 shot) metrics: - name: accuracy type: accuracy value: 42.8 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: GSM8k (5 shot) metrics: - name: accuracy type: accuracy value: 25.9 verified: false - task: type: text-generation dataset: type: lm-eval-harness name: math (4 shot) metrics: - name: accuracy type: accuracy value: 14.8 verified: false - task: type: text-generation dataset: type: bigcode-eval name: humaneval metrics: - name: pass@1 type: pass@1 value: 20.1 verified: false - task: type: text-generation dataset: type: bigcode-eval name: MBPP metrics: - name: pass@1 type: pass@1 value: 32.4 verified: false --- ## Model Summary PowerMoE-3B is a 3B sparse Mixture-of-Experts (sMoE) language model trained with the Power learning rate scheduler. It sparsely activates 800M parameters for each token. It is trained on a mix of open-source and proprietary datasets. PowerMoE-3B has shown promising results compared to other dense models with 2x activate parameters across various benchmarks, including natural language multi-choices, code generation, and math reasoning. Paper: https://arxiv.org/abs/2408.13359 ## Usage Note: Requires installing HF transformers from source. ### Generation This is a simple example of how to use **PowerMoE-3b** model. ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # or "cpu" model_path = "ibm/PowerMoE-3b" tokenizer = AutoTokenizer.from_pretrained(model_path) # drop device_map if running on CPU model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) model.eval() # change input text as desired prompt = "Write a code to find the maximum value in a list of numbers." # tokenize the text input_tokens = tokenizer(prompt, return_tensors="pt") # transfer tokenized inputs to the device for i in input_tokens: input_tokens[i] = input_tokens[i].to(device) # generate output tokens output = model.generate(**input_tokens, max_new_tokens=100) # decode output tokens into text output = tokenizer.batch_decode(output) # loop over the batch to print, in this example the batch size is 1 for i in output: print(i) ``` Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.