LayOnGGUF / llama3-stheno

Stheno-v3.2-Zeta I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.

8B

1 Pull Updated 2 days ago

... /
params
ad5080070371 · 144B
{ "min_p": 0.075, "repeat_penalty": 1.1, "stop": [ "\\n\\n{{User}}", "<|eot_id|>", "<|end_of_text|>" ], "temperature": 1.12, "top_k": 50 }