Quantization made by Richard Erkhov.
Aika-7B - GGUF
- Model creator: https://huggingface.co/sethuiyer/
- Original model: https://huggingface.co/sethuiyer/Aika-7B/
| Name | Quant method | Size |
|---|---|---|
| Aika-7B.Q2_K.gguf | Q2_K | 2.53GB |
| Aika-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Aika-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| Aika-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Aika-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| Aika-7B.Q3_K.gguf | Q3_K | 3.28GB |
| Aika-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Aika-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Aika-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Aika-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| Aika-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Aika-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Aika-7B.Q4_K.gguf | Q4_K | 4.07GB |
| Aika-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Aika-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| Aika-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| Aika-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Aika-7B.Q5_K.gguf | Q5_K | 4.78GB |
| Aika-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Aika-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| Aika-7B.Q6_K.gguf | Q6_K | 5.53GB |
| Aika-7B.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
language: - en license: cc library_name: transformers tags: - mergekit - merge datasets: - Anthropic/hh-rlhf base_model: - SanjiWatsuki/Silicon-Maid-7B - Guilherme34/Samantha-v2 - jan-hq/stealth-v1.3 - mitultiwari/mistral-7B-instruct-dpo - senseable/WestLake-7B-v2 model-index: - name: sethuiyer/Aika-7B 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: 65.36 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B 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: 81.49 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B 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: 53.91 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B 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: 51.22 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B 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: 77.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B 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: 25.78 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B name: Open LLM Leaderboard
Aika-7B
Aika is a language model constructed using the DARE TIES merge method using mitultiwari/mistral-7B-instruct-dpo as a base. Aika is designed to interact with users in a way that feels natural and human-like, to solve problems and answer questions with a high degree of accuracy and truthfulness, and to engage in creative and logical tasks with proficiency.
Models Merged
The following models were included in the merge:
The base model is Mistral-7Bv0.1 fine tuned on Anthropic/hh-rlhf.
Why?
- Base model tuned on Anthropic RLHF dataset: Safe AI as a base model, to balance the uncensored model below.
- Silicon-Maid-7B: Boasts excellent multi-turn conversational skills and logical coherence, ensuring smooth interactions.
- Samantha-V2: Offers empathy and human-like responses, equipped with programmed "self-awareness" for a more personalized experience.
- Stealth-V1.3: Known for enhancing performance in merges when integrated as a component, optimizing Aika's functionality.
- WestLake-7B-V2: Sets a high benchmark for emotional intelligence (EQ) and excels in creative writing, enhancing Aika's ability to understand and respond to your needs.
Combine them all
You get Aika - a considerate, personal digital assistant.
Configuration
Please check mergekit_config.yml for the merge config.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 59.25 |
| AI2 Reasoning Challenge (25-Shot) | 65.36 |
| HellaSwag (10-Shot) | 81.49 |
| MMLU (5-Shot) | 53.91 |
| TruthfulQA (0-shot) | 51.22 |
| Winogrande (5-shot) | 77.74 |
| GSM8k (5-shot) | 25.78 |