RichardErkhov/Josephgflowers_-_Tinyllama-Cinder-1.3B-Reason-Test-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Tinyllama-Cinder-1.3B-Reason-Test - GGUF

• —Model creator: https://huggingface.co/Josephgflowers/
• —Original model: https://huggingface.co/Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test/

Original model description: --- license: mit widget:

• —text: '<|system|>

You are a helpful assistant</s>

<|user|>

Can you explain to me how quantum computing works?</s>

<|assistant|>

' model-index:

• —name: Tinyllama-Cinder-1.3B-Reason-Test results:
• —task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2arc config: ARC-Challenge split: test args: numfew_shot: 25 metrics:
• —type: accnorm value: 34.56 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: numfewshot: 10 metrics:
• —type: accnorm value: 58.24 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: numfewshot: 5 metrics:
• —type: acc value: 25.79 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthfulqa config: multiplechoice split: validation args: numfewshot: 0 metrics:
• —type: mc2 value: 39.93 source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winograndexl split: validation args: numfew_shot: 5 metrics:
• —type: acc value: 63.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: numfewshot: 5 metrics:
• —type: acc value: 4.85 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test name: Open LLM Leaderboard ---

1.3B test of two Cinder models merged layers 1-22 and 18-22, trained on math and step by step reasoning. Model Overview Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration. It is built on the TinyLlama 1.1B parameter model and trained on a unique combination of datasets. Testing on Reason-with-cinder dataset.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here