You can deploy this model and start earning money today!

RichardErkhov/
v000000_-_L3.1-Storniitova-8B-gguf

Name: v000000_-_L3.1-Storniitova-8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3.1-Storniitova-8B - GGUF

Model creator: https://huggingface.co/v000000/
Original model: https://huggingface.co/v000000/L3.1-Storniitova-8B/

Name	Quant method	Size
L3.1-Storniitova-8B.Q2_K.gguf	Q2_K	2.96GB
L3.1-Storniitova-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
L3.1-Storniitova-8B.IQ3_S.gguf	IQ3_S	3.43GB
L3.1-Storniitova-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
L3.1-Storniitova-8B.IQ3_M.gguf	IQ3_M	3.52GB
L3.1-Storniitova-8B.Q3_K.gguf	Q3_K	3.74GB
L3.1-Storniitova-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
L3.1-Storniitova-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
L3.1-Storniitova-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
L3.1-Storniitova-8B.Q4_0.gguf	Q4_0	4.34GB
L3.1-Storniitova-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
L3.1-Storniitova-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
L3.1-Storniitova-8B.Q4_K.gguf	Q4_K	4.58GB
L3.1-Storniitova-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
L3.1-Storniitova-8B.Q4_1.gguf	Q4_1	4.78GB
L3.1-Storniitova-8B.Q5_0.gguf	Q5_0	5.21GB
L3.1-Storniitova-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
L3.1-Storniitova-8B.Q5_K.gguf	Q5_K	5.34GB
L3.1-Storniitova-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
L3.1-Storniitova-8B.Q5_1.gguf	Q5_1	5.65GB
L3.1-Storniitova-8B.Q6_K.gguf	Q6_K	6.14GB
L3.1-Storniitova-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers tags:

mergekit
merge
llama base_model:
v000000/L3.1-8B-RP-Test-003-Task_Arithmetic
v000000/L3.1-Niitorm-8B-t0.0001
Sao10K/L3.1-8B-Niitama-v1.1
arcee-ai/Llama-3.1-SuperNova-Lite
akjindal53244/Llama-3.1-Storm-8B
arcee-ai/Llama-Spark
v000000/L3.1-8B-RP-Test-002-Task_Arithmetic
grimjim/Llama-3-Instruct-abliteration-LoRA-8B model-index:
name: L3.1-Storniitova-8B results:
- task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
  - type: inst_level_strict_acc and prompt_level_strict_acc value: 78.17 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
  - type: acc_norm value: 30.81 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
  - type: exact_match value: 13.29 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
  - type: acc_norm value: 5.26 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
  - type: acc_norm value: 9.96 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 30.84 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=v000000/L3.1-Storniitova-8B name: Open LLM Leaderboard

Llama-3.1-Storniitova-8B

Storniitova-8B is a RP/Instruct model built on the foundation of Llama-3.1-SuperNova-Lite, which is distilled from the 405B parameter variant of Llama-3.1

By only changing the vector tasks, I attempt to retain the full 405B distillation while learning roleplaying capabilties.

(GGUF) mradermacher quants:

(GGUF) QuantFactory quants:

GGUFs

merge

This is a merge of pre-trained language models created using mergekit and other proprietary tools.

Merge Details

Merge Method

This model was merged using the SLERP, Task_Arithmetic and NEARSWAP merge method.

Models Merged

The following models were included in the merge:

Recipe

The following YAML configuration was used to produce this model:

yaml

#Step1 - Add smarts to Niitama with alchemonaut's algorithm.

slices:
  - sources:
      - model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: nearswap
base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
  t:
    - value: 0.0001
dtype: bfloat16
out_type: float16

#Step 2 - Learn vectors onto Supernova 0.4(Niitorm)

models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 1.0
  - model: v000000/L3.1-Niitorm-8B-t0.0001
    parameters:
      weight: 0.4
merge_method: task_arithmetic
base_model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
    normalize: false
dtype: float16

#Step 3 - Fully learn vectors onto Supernova 1.25(Niitorm)

models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 0.0
  - model: v000000/L3.1-Niitorm-8B-t0.0001
    parameters:
      weight: 1.25
merge_method: task_arithmetic
base_model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
    normalize: false
dtype: float16

#Step 4 - Merge checkpoints and keep output/input Supernova heavy
#Merge with a triangular slerp from sophosympatheia.

models:
  - model: v000000/L3.1-8B-RP-Test-003-Task_Arithmetic
merge_method: slerp
base_model: v000000/L3.1-8B-RP-Test-002-Task_Arithmetic+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
# This model needed some abliteration^
parameters:
  t:
    - value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0]
dtype: float16

SLERP distribution used to smoothly blend the mostly Supernova base with the roleplay vectors:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.06
IFEval (0-Shot)	78.17
BBH (3-Shot)	30.81
MATH Lvl 5 (4-Shot)	13.29
GPQA (0-shot)	5.26
MuSR (0-shot)	9.96
MMLU-PRO (5-shot)	30.84

RichardErkhov/v000000_-_L3.1-Storniitova-8B-gguf