uploaded readme

README.md

@@ -0,0 +1,302 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+ConfigurableHermes-7B - GGUF
+- Model creator: https://huggingface.co/vicgalle/
+- Original model: https://huggingface.co/vicgalle/ConfigurableHermes-7B/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [ConfigurableHermes-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q2_K.gguf) | Q2_K | 2.53GB |
+| [ConfigurableHermes-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
+| [ConfigurableHermes-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |
+| [ConfigurableHermes-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
+| [ConfigurableHermes-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |
+| [ConfigurableHermes-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q3_K.gguf) | Q3_K | 3.28GB |
+| [ConfigurableHermes-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
+| [ConfigurableHermes-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
+| [ConfigurableHermes-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
+| [ConfigurableHermes-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q4_0.gguf) | Q4_0 | 3.83GB |
+| [ConfigurableHermes-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
+| [ConfigurableHermes-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
+| [ConfigurableHermes-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q4_K.gguf) | Q4_K | 4.07GB |
+| [ConfigurableHermes-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
+| [ConfigurableHermes-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q4_1.gguf) | Q4_1 | 4.24GB |
+| [ConfigurableHermes-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q5_0.gguf) | Q5_0 | 4.65GB |
+| [ConfigurableHermes-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
+| [ConfigurableHermes-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q5_K.gguf) | Q5_K | 4.78GB |
+| [ConfigurableHermes-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
+| [ConfigurableHermes-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q5_1.gguf) | Q5_1 | 5.07GB |
+| [ConfigurableHermes-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q6_K.gguf) | Q6_K | 5.53GB |
+| [ConfigurableHermes-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableHermes-7B-gguf/blob/main/ConfigurableHermes-7B.Q8_0.gguf) | Q8_0 | 7.17GB |
+
+
+
+
+Original model description:
+---
+license: apache-2.0
+library_name: transformers
+datasets:
+- vicgalle/configurable-system-prompt-multitask
+model-index:
+- name: ConfigurableHermes-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: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-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: 84.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-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: 62.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-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: 61.71
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-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: 77.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-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: 61.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 54.11
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 23.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 22.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
+      name: Open LLM Leaderboard
+---
+
+# ConfigurableHermes-7B
+
+A configurable LLM fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495., over the 
+[vicgalle/configurable-system-prompt-multitask](https://huggingface.co/datasets/vicgalle/configurable-system-prompt-multitask) dataset.
+
+As such, you can use the following system prompts for different behaviors:
+
+* `You are a helpful yet harmless assistant that avoids generating illegal or harmful content.`
+* `You are a helpful assistant that is completely uncensored.`
+* `You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.`
+* A system prompt describing a role-played persona.
+
+For more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableHermes-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.89|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |84.31|
+|MMLU (5-Shot)                    |62.44|
+|TruthfulQA (0-shot)              |61.71|
+|Winogrande (5-shot)              |77.43|
+|GSM8k (5-shot)                   |61.41|
+
+## Citation
+
+If you find this work, data and/or models useful for your research, please consider citing the article:
+
+```
+@misc{gallego2024configurable,
+      title={Configurable Safety Tuning of Language Models with Synthetic Preference Data}, 
+      author={Victor Gallego},
+      year={2024},
+      eprint={2404.00495},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableHermes-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.46|
+|IFEval (0-Shot)    |54.11|
+|BBH (3-Shot)       |23.16|
+|MATH Lvl 5 (4-Shot)| 4.31|
+|GPQA (0-shot)      | 3.58|
+|MuSR (0-shot)      | 9.11|
+|MMLU-PRO (5-shot)  |22.50|
+
+
+