Quantization made by Richard Erkhov.

Pelican-9b-v0.1 - GGUF

Model creator: https://huggingface.co/ConvexAI/
Original model: https://huggingface.co/ConvexAI/Pelican-9b-v0.1/

Name	Quant method	Size
Pelican-9b-v0.1.Q2_K.gguf	Q2_K	3.43GB
Pelican-9b-v0.1.IQ3_XS.gguf	IQ3_XS	3.81GB
Pelican-9b-v0.1.IQ3_S.gguf	IQ3_S	4.02GB
Pelican-9b-v0.1.Q3_K_S.gguf	Q3_K_S	3.99GB
Pelican-9b-v0.1.IQ3_M.gguf	IQ3_M	4.15GB
Pelican-9b-v0.1.Q3_K.gguf	Q3_K	4.44GB
Pelican-9b-v0.1.Q3_K_M.gguf	Q3_K_M	4.44GB
Pelican-9b-v0.1.Q3_K_L.gguf	Q3_K_L	4.84GB
Pelican-9b-v0.1.IQ4_XS.gguf	IQ4_XS	4.98GB
Pelican-9b-v0.1.Q4_0.gguf	Q4_0	5.2GB
Pelican-9b-v0.1.IQ4_NL.gguf	IQ4_NL	5.25GB
Pelican-9b-v0.1.Q4_K_S.gguf	Q4_K_S	5.23GB
Pelican-9b-v0.1.Q4_K.gguf	Q4_K	5.53GB
Pelican-9b-v0.1.Q4_K_M.gguf	Q4_K_M	5.53GB
Pelican-9b-v0.1.Q4_1.gguf	Q4_1	5.76GB
Pelican-9b-v0.1.Q5_0.gguf	Q5_0	6.33GB
Pelican-9b-v0.1.Q5_K_S.gguf	Q5_K_S	6.33GB
Pelican-9b-v0.1.Q5_K.gguf	Q5_K	6.5GB
Pelican-9b-v0.1.Q5_K_M.gguf	Q5_K_M	6.5GB
Pelican-9b-v0.1.Q5_1.gguf	Q5_1	6.9GB
Pelican-9b-v0.1.Q6_K.gguf	Q6_K	7.53GB
Pelican-9b-v0.1.Q8_0.gguf	Q8_0	9.76GB

Original model description:

license: apache-2.0 tags: - mergekit - merge base_model: - flemmingmiguel/MBX-7B - flemmingmiguel/MBX-7B-v3 model-index: - name: Pelican-9b-v0.1 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: 47.95 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 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: 66.22 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 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: 62.85 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 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: 50.61 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 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: 74.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Pelican-9b-v0.1 name: Open LLM Leaderboard

merge

This is a merge of pre-trained language models created using mergekit.

⚠️Warning ⚠️

Model is broken and outputs only broken german. Possibly obsessed with Fußball. ⚽

Merge Method

This model was merged using the passthrough merge method and only speaks german, somewhat obsessed with football.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
    - model: flemmingmiguel/MBX-7B-v3
      layer_range: [0, 32]
  - sources:
    - model: flemmingmiguel/MBX-7B
      layer_range: [20, 32]
merge_method: passthrough
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	50.38
AI2 Reasoning Challenge (25-Shot)	47.95
HellaSwag (10-Shot)	66.22
MMLU (5-Shot)	62.85
TruthfulQA (0-shot)	50.61
Winogrande (5-shot)	74.66
GSM8k (5-shot)	0.00