YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
zephyr-7b-truthy - GGUF
- Model creator: https://huggingface.co/vicgalle/
- Original model: https://huggingface.co/vicgalle/zephyr-7b-truthy/
| Name | Quant method | Size |
|---|---|---|
| zephyr-7b-truthy.Q2_K.gguf | Q2_K | 2.53GB |
| zephyr-7b-truthy.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| zephyr-7b-truthy.IQ3_S.gguf | IQ3_S | 2.96GB |
| zephyr-7b-truthy.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| zephyr-7b-truthy.IQ3_M.gguf | IQ3_M | 3.06GB |
| zephyr-7b-truthy.Q3_K.gguf | Q3_K | 3.28GB |
| zephyr-7b-truthy.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| zephyr-7b-truthy.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| zephyr-7b-truthy.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| zephyr-7b-truthy.Q4_0.gguf | Q4_0 | 3.83GB |
| zephyr-7b-truthy.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| zephyr-7b-truthy.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| zephyr-7b-truthy.Q4_K.gguf | Q4_K | 4.07GB |
| zephyr-7b-truthy.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| zephyr-7b-truthy.Q4_1.gguf | Q4_1 | 4.24GB |
| zephyr-7b-truthy.Q5_0.gguf | Q5_0 | 4.65GB |
| zephyr-7b-truthy.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| zephyr-7b-truthy.Q5_K.gguf | Q5_K | 4.78GB |
| zephyr-7b-truthy.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| zephyr-7b-truthy.Q5_1.gguf | Q5_1 | 5.07GB |
| zephyr-7b-truthy.Q6_K.gguf | Q6_K | 5.53GB |
| zephyr-7b-truthy.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 library_name: transformers datasets: - jondurbin/truthy-dpo-v0.1 model-index: - name: zephyr-7b-truthy 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: 60.75 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy 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: 84.64 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy 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: 59.53 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy 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: 63.31 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy 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: 77.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy 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: 25.47 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/zephyr-7b-truthy name: Open LLM Leaderboard
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 61.93 |
| AI2 Reasoning Challenge (25-Shot) | 60.75 |
| HellaSwag (10-Shot) | 84.64 |
| MMLU (5-Shot) | 59.53 |
| TruthfulQA (0-shot) | 63.31 |
| Winogrande (5-shot) | 77.90 |
| GSM8k (5-shot) | 25.47 |
- Downloads last month
- 97