AI Observatory / Model Radar Alpindale / alpindale/goliath-120b

Goliath 120B

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...

6,144 Context
1,024 Max output
$3.75 / 1M Prompt price
2023-11-10 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Alpindale Input modalities text
Output modalities text Prompt price $3.75 / 1M
Completion price $7.50 / 1M Request price N/A
Context length 6,144 Max completion tokens 1,024
Supported parameters frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, temperature, top_a, top_k, top_logprobs, top_p
Best for alpindale/goliath-120b

Goliath 120B

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...

03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.