Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks · HackerPapers discussions

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks — mentioned by airgapstopgap

Wed, 19 Jul 2023 02:18:40 GMT

> But there's no little numeric model embedded inside the language model that would tell it how many dollars, or be able to compare dollars against dollars This logic applies to any function an LLM may perform, therefore it cannot perform any function, which is absurd. Indeed there functionally are little circuits inside LLMs; its pretraining amounts to formation of those circuits. [1] LLaMA tokenizer parses integers as individual tokens and allows the model to see that "$105,000" is [$][1][0][5][,][0][0][0], which makes it more than capable of learning arithmetic for the general case, and…

Paper and discussion history. A mention is not an endorsement.

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks — mentioned by anon373839

Mon, 19 Jun 2023 04:46:26 GMT

1. Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks https://huggingface.co/papers/2305.14201 2. Gorilla: Large Language Model Connected with Massive APIs https://arxiv.org/abs/2305.15334

Paper and discussion history. A mention is not an endorsement.

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks — mentioned by anon373839

Tue, 06 Jun 2023 23:05:59 GMT

> a base for fine-tuning a task specific model Yes. The 7B size can perform very well when tuned on a specific menu of tasks: 1. Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks https://huggingface.co/papers/2305.14201 2. Gorilla: Large Language Model Connected with Massive APIs https://arxiv.org/abs/2305.15334

Paper and discussion history. A mention is not an endorsement.

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks — mentioned by anon373839

Thu, 01 Jun 2023 08:30:25 GMT

Sure, here are two: 1. Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks https://huggingface.co/papers/2305.14201 2. Gorilla: Large Language Model Connected with Massive APIs https://arxiv.org/abs/2305.15334 Consider also these 2 papers supporting the feasibility of fine-tuning: 3. LIMA: Less Is More for Alignment [showing that a very small number of high quality examples is sufficient to align a base model] https://arxiv.org/abs/2305.11206 4. QLoRA: Efficient Finetuning of Quantized LLMs [showing that LLMs can now be fine-tuned quickly on consumer-grade GPUs]…

Paper and discussion history. A mention is not an endorsement.

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks — HN submission

Wed, 24 May 2023 18:01:54 GMT

Goat: Fine-Tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.