ChaoticNeutrals_-_Prima-LelantaclesV4-7b-16k-bf16-gguf/README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Prima-LelantaclesV4-7b-16k-bf16 - GGUF

• Model creator: https://huggingface.co/ChaoticNeutrals/
• Original model: https://huggingface.co/ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16/

Name	Quant method	Size
Prima-LelantaclesV4-7b-16k-bf16.Q2_K.gguf	Q2_K	2.53GB
Prima-LelantaclesV4-7b-16k-bf16.IQ3_XS.gguf	IQ3_XS	2.81GB
Prima-LelantaclesV4-7b-16k-bf16.IQ3_S.gguf	IQ3_S	2.96GB
Prima-LelantaclesV4-7b-16k-bf16.Q3_K_S.gguf	Q3_K_S	2.95GB
Prima-LelantaclesV4-7b-16k-bf16.IQ3_M.gguf	IQ3_M	3.06GB
Prima-LelantaclesV4-7b-16k-bf16.Q3_K.gguf	Q3_K	3.28GB
Prima-LelantaclesV4-7b-16k-bf16.Q3_K_M.gguf	Q3_K_M	3.28GB
Prima-LelantaclesV4-7b-16k-bf16.Q3_K_L.gguf	Q3_K_L	3.56GB
Prima-LelantaclesV4-7b-16k-bf16.IQ4_XS.gguf	IQ4_XS	3.67GB
Prima-LelantaclesV4-7b-16k-bf16.Q4_0.gguf	Q4_0	3.83GB
Prima-LelantaclesV4-7b-16k-bf16.IQ4_NL.gguf	IQ4_NL	3.87GB
Prima-LelantaclesV4-7b-16k-bf16.Q4_K_S.gguf	Q4_K_S	3.86GB
Prima-LelantaclesV4-7b-16k-bf16.Q4_K.gguf	Q4_K	4.07GB
Prima-LelantaclesV4-7b-16k-bf16.Q4_K_M.gguf	Q4_K_M	4.07GB
Prima-LelantaclesV4-7b-16k-bf16.Q4_1.gguf	Q4_1	4.24GB
Prima-LelantaclesV4-7b-16k-bf16.Q5_0.gguf	Q5_0	4.65GB
Prima-LelantaclesV4-7b-16k-bf16.Q5_K_S.gguf	Q5_K_S	4.65GB
Prima-LelantaclesV4-7b-16k-bf16.Q5_K.gguf	Q5_K	4.78GB
Prima-LelantaclesV4-7b-16k-bf16.Q5_K_M.gguf	Q5_K_M	4.78GB
Prima-LelantaclesV4-7b-16k-bf16.Q5_1.gguf	Q5_1	5.07GB
Prima-LelantaclesV4-7b-16k-bf16.Q6_K.gguf	Q6_K	5.53GB
Prima-LelantaclesV4-7b-16k-bf16.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: other library_name: transformers tags:

• mergekit
• merge base_model:
• Test157t/Yarncules-7b-128k
• Test157t/Prima-LelantaclesV3-7b model-index:
• name: Prima-LelantaclesV4-7b-16k-bf16 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: 66.04 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 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: 85.07 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 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: 64.7 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 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: 54.76 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 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: 80.27 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 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: 58.83 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV4-7b-16k-bf16 name: Open LLM Leaderboard

---

Quants Thanks to @Lewdiculous :https://huggingface.co/Lewdiculous/Prima-LelantaclesV4-7b-16k-GGUF

The following models were included in the merge:

• Test157t/Yarncules-7b-128k
• Test157t/Prima-LelantaclesV3-7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Test157t/Yarncules-7b-128k
        layer_range: [0, 32]
      - model: Test157t/Prima-LelantaclesV3-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Prima-LelantaclesV3-7b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.28
AI2 Reasoning Challenge (25-Shot)	66.04
HellaSwag (10-Shot)	85.07
MMLU (5-Shot)	64.70
TruthfulQA (0-shot)	54.76
Winogrande (5-shot)	80.27
GSM8k (5-shot)	58.83