README.md

metadata

tags:
  - llama
  - merge

Healed Llama-3-15B

Llama-3-15B-EtherealMaid-t0.0001

A merge of the following models using a custom NearSwap(t0.0001) algorithm:

• v000000/HaloMaidRP-v1.33-15B-L3
• ZeusLabs/L3-Aethora-15B-V2

With v000000/HaloMaidRP-v1.33-15B-L3 as the base model.

Thanks mradermacher for the quants!

• GGUF
• GGUF imatrix

https://huggingface.co/v000000/L3-15B-EtherealMaid-t0.0001-Q5_K_M-GGUF

#Fixed
def lerp(a, b, t):
    return a * (1 - t) + b * t

def nearswap(v0, v1, t):
    lweight = np.abs(v0 - v1)
    with np.errstate(divide='ignore', invalid='ignore'):
        lweight = np.where(lweight != 0, t / lweight, 1.0)
    lweight = np.nan_to_num(lweight, nan=1.0, posinf=1.0, neginf=1.0)
    np.clip(lweight, a_min=0.0, a_max=1.0, out=lweight)
    return lerp(v0, v1, lweight)

Credit Alchemonaut

Samplers

I found success with:
temperature 0.9-1.2
min_p 0.08
tfs 0.97
smoothing_factor 0.3
smoothing_curve 1.1

Nymeria preset (more coherent):
temp 0.9
top_k 30
top_p 0.75
min_p 0.2
rep_pen 1.1
smooth_factor 0.25
smooth_curve 1

Prompt Template

<|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|>