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 the model - [mergek…
Model details →Goliath 120B vs OpenAI: GPT-3.5 Turbo Instruct
OpenAI: GPT-3.5 Turbo Instruct wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
Model details →Side-by-side comparison
| Capability | Goliath 120B | OpenAI: GPT-3.5 Turbo Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 4K | 🏆 Goliath 120B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $1.50 | 🏆 OpenAI: GPT-3.5 Turbo Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $2.00 | 🏆 OpenAI: GPT-3.5 Turbo Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Goliath 120B better than OpenAI: GPT-3.5 Turbo Instruct?
OpenAI: GPT-3.5 Turbo Instruct wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Goliath 120B and OpenAI: GPT-3.5 Turbo Instruct?
Input: $3.75 vs $1.50 per 1M tokens. Output: $7.50 vs $2.00 per 1M tokens.
What context windows do Goliath 120B and OpenAI: GPT-3.5 Turbo Instruct support?
Goliath 120B supports up to 6K tokens. OpenAI: GPT-3.5 Turbo Instruct supports up to 4K tokens.
Do both Goliath 120B and OpenAI: GPT-3.5 Turbo Instruct support tool calling?
Goliath 120B: not advertised. OpenAI: GPT-3.5 Turbo Instruct: not advertised.