RichardErkhov/TomGrc_-_FusionNet-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

FusionNet - GGUF

• Model creator: https://huggingface.co/TomGrc/
• Original model: https://huggingface.co/TomGrc/FusionNet/

Name	Quant method	Size
FusionNet.Q2_K.gguf	Q2_K	3.73GB
FusionNet.IQ3_XS.gguf	IQ3_XS	4.14GB
FusionNet.IQ3_S.gguf	IQ3_S	4.37GB
FusionNet.Q3_K_S.gguf	Q3_K_S	4.34GB
FusionNet.IQ3_M.gguf	IQ3_M	4.51GB
FusionNet.Q3_K.gguf	Q3_K	4.84GB
FusionNet.Q3_K_M.gguf	Q3_K_M	4.84GB
FusionNet.Q3_K_L.gguf	Q3_K_L	5.26GB
FusionNet.IQ4_XS.gguf	IQ4_XS	5.43GB
FusionNet.Q4_0.gguf	Q4_0	5.66GB
FusionNet.IQ4_NL.gguf	IQ4_NL	5.72GB
FusionNet.Q4_K_S.gguf	Q4_K_S	5.7GB
FusionNet.Q4_K.gguf	Q4_K	6.02GB
FusionNet.Q4_K_M.gguf	Q4_K_M	6.02GB
FusionNet.Q4_1.gguf	Q4_1	6.27GB
FusionNet.Q5_0.gguf	Q5_0	6.89GB
FusionNet.Q5_K_S.gguf	Q5_K_S	6.89GB
FusionNet.Q5_K.gguf	Q5_K	7.08GB
FusionNet.Q5_K_M.gguf	Q5_K_M	7.08GB
FusionNet.Q5_1.gguf	Q5_1	7.51GB
FusionNet.Q6_K.gguf	Q6_K	8.2GB
FusionNet.Q8_0.gguf	Q8_0	10.62GB

Original model description:

language: - en license: mit tags: - merge pipeline_tag: text-generation model-index: - name: FusionNet 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: 71.25 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet 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: 88.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet 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: 66.36 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet 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: 71.95 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet 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: 83.27 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet 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: 65.05 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet name: Open LLM Leaderboard

FusionNet

Fine-tuned model on English language using Fusion method.

Model description

The FusionNet is a model to experiment with the "Fusion" method, which could significantly increase the performance of the original model. The FusionNet has 10.7B parameters, and this model is fine-tuned. Enjoy!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.38
AI2 Reasoning Challenge (25-Shot)	71.25
HellaSwag (10-Shot)	88.42
MMLU (5-Shot)	66.36
TruthfulQA (0-shot)	71.95
Winogrande (5-shot)	83.27
GSM8k (5-shot)	65.05