Quantization made by Richard Erkhov.

Deacon-1b - GGUF

Model creator: https://huggingface.co/KnutJaegersberg/
Original model: https://huggingface.co/KnutJaegersberg/Deacon-1b/

Name	Quant method	Size
Deacon-1b.Q2_K.gguf	Q2_K	0.4GB
Deacon-1b.IQ3_XS.gguf	IQ3_XS	0.44GB
Deacon-1b.IQ3_S.gguf	IQ3_S	0.47GB
Deacon-1b.Q3_K_S.gguf	Q3_K_S	0.47GB
Deacon-1b.IQ3_M.gguf	IQ3_M	0.48GB
Deacon-1b.Q3_K.gguf	Q3_K	0.51GB
Deacon-1b.Q3_K_M.gguf	Q3_K_M	0.51GB
Deacon-1b.Q3_K_L.gguf	Q3_K_L	0.55GB
Deacon-1b.IQ4_XS.gguf	IQ4_XS	0.57GB
Deacon-1b.Q4_0.gguf	Q4_0	0.59GB
Deacon-1b.IQ4_NL.gguf	IQ4_NL	0.6GB
Deacon-1b.Q4_K_S.gguf	Q4_K_S	0.6GB
Deacon-1b.Q4_K.gguf	Q4_K	0.62GB
Deacon-1b.Q4_K_M.gguf	Q4_K_M	0.62GB
Deacon-1b.Q4_1.gguf	Q4_1	0.65GB
Deacon-1b.Q5_0.gguf	Q5_0	0.71GB
Deacon-1b.Q5_K_S.gguf	Q5_K_S	0.71GB
Deacon-1b.Q5_K.gguf	Q5_K	0.73GB
Deacon-1b.Q5_K_M.gguf	Q5_K_M	0.73GB
Deacon-1b.Q5_1.gguf	Q5_1	0.77GB
Deacon-1b.Q6_K.gguf	Q6_K	0.84GB
Deacon-1b.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: cc-by-nc-4.0 model-index: - name: Deacon-1b 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: 32.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b 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: 58.62 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b 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: 24.89 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b 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: 35.05 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b 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: 59.59 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b 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: 0.68 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b name: Open LLM Leaderboard

Base model is appvoid/palmer-001, fine tuned for 3 epochs with Neftune.

Prompt Example:

### System:

You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.

### Instruction: 

How do you fine tune a large language model? 

### Response:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	35.21
AI2 Reasoning Challenge (25-Shot)	32.42
HellaSwag (10-Shot)	58.62
MMLU (5-Shot)	24.89
TruthfulQA (0-shot)	35.05
Winogrande (5-shot)	59.59
GSM8k (5-shot)	0.68