RichardErkhov/TomGrc_-_FusionNet_linear-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

FusionNet_linear - GGUF

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

Name	Quant method	Size
FusionNet_linear.Q2_K.gguf	Q2_K	3.73GB
FusionNet_linear.IQ3_XS.gguf	IQ3_XS	4.14GB
FusionNet_linear.IQ3_S.gguf	IQ3_S	4.37GB
FusionNet_linear.Q3_K_S.gguf	Q3_K_S	4.34GB
FusionNet_linear.IQ3_M.gguf	IQ3_M	4.51GB
FusionNet_linear.Q3_K.gguf	Q3_K	4.84GB
FusionNet_linear.Q3_K_M.gguf	Q3_K_M	4.84GB
FusionNet_linear.Q3_K_L.gguf	Q3_K_L	5.26GB
FusionNet_linear.IQ4_XS.gguf	IQ4_XS	5.43GB
FusionNet_linear.Q4_0.gguf	Q4_0	5.66GB
FusionNet_linear.IQ4_NL.gguf	IQ4_NL	5.72GB
FusionNet_linear.Q4_K_S.gguf	Q4_K_S	5.7GB
FusionNet_linear.Q4_K.gguf	Q4_K	6.02GB
FusionNet_linear.Q4_K_M.gguf	Q4_K_M	6.02GB
FusionNet_linear.Q4_1.gguf	Q4_1	6.27GB
FusionNet_linear.Q5_0.gguf	Q5_0	6.89GB
FusionNet_linear.Q5_K_S.gguf	Q5_K_S	5.89GB
FusionNet_linear.Q5_K.gguf	Q5_K	7.08GB
FusionNet_linear.Q5_K_M.gguf	Q5_K_M	7.08GB
FusionNet_linear.Q5_1.gguf	Q5_1	7.51GB
FusionNet_linear.Q6_K.gguf	Q6_K	8.2GB
FusionNet_linear.Q8_0.gguf	Q8_0	10.62GB

Original model description:

language: - en license: mit tags: - merge pipeline_tag: text-generation model-index: - name: FusionNet_linear 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_linear 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: 88.44 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_linear 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: 66.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_linear 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: 71.94 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_linear 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_linear 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: 65.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_linear name: Open LLM Leaderboard

FusionNet_linear

Fine-tuned model on English language using linear Fusion method.

Model description

This is an experiment with the linear Fusion method of FusionNet. This model 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.	74.43
AI2 Reasoning Challenge (25-Shot)	71.25
HellaSwag (10-Shot)	88.44
MMLU (5-Shot)	66.35
TruthfulQA (0-shot)	71.94
Winogrande (5-shot)	83.27
GSM8k (5-shot)	65.35