Openrouter doesn't require the user to set up a proxy, this does! I'm not following, would someone care to explain? But a hosted proxy seems best because it can have integrated automated tests and update, without me having to update my code...

New activity in dphn/dolphin-2.5-mixtral-8x7b over 1 year ago

Adding `safetensors` variant of this model

#23 opened almost 2 years ago by

fseiler275

New activity in Efficient-ML/LLaMA-3-8B-SmoothQuant-4bit-4bit over 1 year ago

Why is this exactly the same size as the 8-bit one?

#1 opened over 1 year ago by

dagelf

New activity in CohereLabs/c4ai-command over 1 year ago

Question

#2 opened over 1 year ago by

mrfakename

New activity in SinclairSchneider/dbrx-instruct-quantization-fixed over 1 year ago

Some error when running

#1 opened over 1 year ago by

Williams07

reacted to philschmid's post with 🔥 over 1 year ago

Post

8504

New state-of-the-art open LLM! 🚀 Databricks just released DBRX, a 132B MoE trained on 12T tokens. Claiming to surpass OpenAI GPT-3.5 and is competitive with Google Gemini 1.0 Pro. 🤯

TL;DR
🧮 132B MoE with 16 experts with 4 active in generation
🪟 32 000 context window
📈 Outperforms open LLMs on common benchmarks, including MMLU
🚀 Up to 2x faster inference than Llama 2 70B
💻 Trained on 12T tokens
🔡 Uses the GPT-4 tokenizer
📜 Custom License, commercially useable

Collection: databricks/dbrx-6601c0852a0cdd3c59f71962
Demo: https://huggingface.co/spaces/databricks/dbrx-instruct

Kudos to the Team at Databricks and MosaicML for this strong release in the open community! 🤗

4 replies

reacted to akhaliq's post with ❤️ almost 2 years ago

Post

Chain-of-Thought Reasoning Without Prompting

paper page: Chain-of-Thought Reasoning Without Prompting (2402.10200)

In enhancing the reasoning capabilities of large language models (LLMs), prior research primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of-thought (CoT) prompting. These methods, while effective, often involve manually intensive prompt engineering. Our study takes a novel approach by asking: Can LLMs reason effectively without prompting? Our findings reveal that, intriguingly, CoT reasoning paths can be elicited from pre-trained LLMs by simply altering the decoding process. Rather than conventional greedy decoding, we investigate the top-k alternative tokens, uncovering that CoT paths are frequently inherent in these sequences. This approach not only bypasses the confounders of prompting but also allows us to assess the LLMs' intrinsic reasoning abilities. Moreover, we observe that the presence of a CoT in the decoding path correlates with a higher confidence in the model's decoded answer. This confidence metric effectively differentiates between CoT and non-CoT paths. Extensive empirical studies on various reasoning benchmarks show that the proposed CoT-decoding substantially outperforms the standard greedy decoding.