This model was converted to GGUF format from v000000/L3-Umbral-Storm-8B-t0.0001 using llama.cpp Refer to the original model card for more details on the model.

Llama-3-Umbral-Storm-8B (8K) (GGUF)

RP model, "L3-Umbral-Mind-v2.0" as a base, nearswapped with one of the smartest L3.1 models "Storm".

Warning: Based on Mopey-Mule so it should be negative, don't use this model for any truthful information or advice.

merge

This is a merge of pre-trained language models.

Merge Details

This model is on the Llama-3 arch with Llama-3.1 merged in, so it has 8k context length. But could possibly be extended slightly with RoPE due to the L3.1 layers.

Merge Method

This model was merged using the NEARSWAP t0.0001 merge algorithm.

Models Merged

The following models were included in the merge:

Base Model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
akjindal53244/Llama-3.1-Storm-8B

Configuration

yaml

slices:
  - sources:
      - model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: nearswap
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
parameters:
  t:
    - value: 0.0001
dtype: bfloat16

Prompt Template:

bash

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>