lucidrains / llama-qrlhf
Implementation of the Llama architecture with RLHF + Q-learning
☆156Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for llama-qrlhf
- Implementation of Infini-Transformer in Pytorch☆104Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆112Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆83Updated last week
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆117Updated 3 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆111Updated 2 months ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆224Updated 2 months ago
- Understand and test language model architectures on synthetic tasks.☆161Updated 6 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆108Updated 3 weeks ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆205Updated 2 months ago
- ☆76Updated 6 months ago
- σ-GPT: A New Approach to Autoregressive Models☆59Updated 2 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆89Updated 2 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆176Updated 5 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆212Updated 2 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆168Updated last month
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆91Updated last month
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆322Updated last week
- ☆72Updated 4 months ago
- ☆62Updated 3 months ago
- ☆175Updated this week
- Language models scale reliably with over-training and on downstream tasks☆94Updated 7 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆84Updated 2 months ago
- ☆76Updated 5 months ago
- Token Omission Via Attention☆119Updated 3 weeks ago
- Griffin MQA + Hawk Linear RNN Hybrid☆85Updated 6 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆291Updated 4 months ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆80Updated 10 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆175Updated 3 months ago