Quantization made by Richard Erkhov.
DareBeagel-2x7B - GGUF
- Model creator: https://huggingface.co/shadowml/
- Original model: https://huggingface.co/shadowml/DareBeagel-2x7B/
| Name | Quant method | Size |
|---|---|---|
| DareBeagel-2x7B.Q2_K.gguf | Q2_K | 4.43GB |
| DareBeagel-2x7B.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| DareBeagel-2x7B.IQ3_S.gguf | IQ3_S | 5.22GB |
| DareBeagel-2x7B.Q3_K_S.gguf | Q3_K_S | 5.2GB |
| DareBeagel-2x7B.IQ3_M.gguf | IQ3_M | 3.28GB |
| DareBeagel-2x7B.Q3_K.gguf | Q3_K | 5.78GB |
| DareBeagel-2x7B.Q3_K_M.gguf | Q3_K_M | 5.78GB |
| DareBeagel-2x7B.Q3_K_L.gguf | Q3_K_L | 6.27GB |
| DareBeagel-2x7B.IQ4_XS.gguf | IQ4_XS | 2.32GB |
| DareBeagel-2x7B.Q4_0.gguf | Q4_0 | 6.78GB |
| DareBeagel-2x7B.IQ4_NL.gguf | IQ4_NL | 6.85GB |
| DareBeagel-2x7B.Q4_K_S.gguf | Q4_K_S | 6.84GB |
| DareBeagel-2x7B.Q4_K.gguf | Q4_K | 7.25GB |
| DareBeagel-2x7B.Q4_K_M.gguf | Q4_K_M | 7.25GB |
| DareBeagel-2x7B.Q4_1.gguf | Q4_1 | 7.52GB |
| DareBeagel-2x7B.Q5_0.gguf | Q5_0 | 8.26GB |
| DareBeagel-2x7B.Q5_K_S.gguf | Q5_K_S | 8.26GB |
| DareBeagel-2x7B.Q5_K.gguf | Q5_K | 8.51GB |
| DareBeagel-2x7B.Q5_K_M.gguf | Q5_K_M | 8.51GB |
| DareBeagel-2x7B.Q5_1.gguf | Q5_1 | 9.01GB |
| DareBeagel-2x7B.Q6_K.gguf | Q6_K | 9.84GB |
| DareBeagel-2x7B.Q8_0.gguf | Q8_0 | 12.75GB |
Original model description:
license: apache-2.0 tags: - moe - merge - mergekit - lazymergekit - mlabonne/NeuralBeagle14-7B - mlabonne/NeuralDaredevil-7B model-index: - name: DareBeagel-2x7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 72.01 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 88.12 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.51 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 69.09 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 82.72 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 70.51 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B name: Open LLM Leaderboard
Beyonder-2x7B-v2
Beyonder-2x7B-v2 is a Mixure of Experts (MoE) made with the following models using LazyMergekit:
🧩 Configuration
base_model: mlabonne/NeuralBeagle14-7B
gate_mode: random
experts:
- source_model: mlabonne/NeuralBeagle14-7B
positive_prompts: [""]
- source_model: mlabonne/NeuralDaredevil-7B
positive_prompts: [""]
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "shadowml/Beyonder-2x7B-v2"
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"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.49 |
| AI2 Reasoning Challenge (25-Shot) | 72.01 |
| HellaSwag (10-Shot) | 88.12 |
| MMLU (5-Shot) | 64.51 |
| TruthfulQA (0-shot) | 69.09 |
| Winogrande (5-shot) | 82.72 |
| GSM8k (5-shot) | 70.51 |