RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Tiny-Vicuna-1B - GGUF

• Model creator: https://huggingface.co/Jiayi-Pan/
• Original model: https://huggingface.co/Jiayi-Pan/Tiny-Vicuna-1B/

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

Original model description:

language: - en license: apache-2.0 model-index: - name: Tiny-Vicuna-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: 33.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-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: 55.92 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-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: 25.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-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: 33.82 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-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: 58.41 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-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: 1.52 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard

Tiny Vicuna 1B

This model is a fine-tuned version of TinyLlama on WizardVicuna Dataset. It should be fully compatible with Vicuna-v1.5 series.

This model is easy to iterate on for early experiments!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	34.76
AI2 Reasoning Challenge (25-Shot)	33.45
HellaSwag (10-Shot)	55.92
MMLU (5-Shot)	25.45
TruthfulQA (0-shot)	33.82
Winogrande (5-shot)	58.41
GSM8k (5-shot)	1.52