All tags
Model: "chatml"
CodeLLama 70B beats GPT4 on HumanEval
codellama miqu mistral-medium llama-2-70b aphrodite-engine mixtral flatdolphinmaid noromaid rpcal chatml mistral-7b activation-beacon eagle-7b rwkv-v5 openhermes2.5 nous-hermes-2-mixtral-8x7b-dpo imp-v1-3b bakllava moondream qwen-vl meta-ai-fair ollama nous-research mistral-ai hugging-face ai-ethics alignment gpu-optimization direct-prompt-optimization fine-tuning cuda-programming optimizer-technology quantization multimodality context-length dense-retrieval retrieval-augmented-generation multilinguality model-performance open-source code-generation classification vision
Meta AI surprised the community with the release of CodeLlama, an open-source model now available on platforms like Ollama and MLX for local use. The Miqu model sparked debate over its origins, possibly linked to Mistral Medium or a fine-tuned Llama-2-70b, alongside discussions on AI ethics and alignment risks. The Aphrodite engine showed strong performance on A6000 GPUs with specific configurations. Role-playing AI models such as Mixtral and Flatdolphinmaid faced challenges with repetitiveness, while Noromaid and Rpcal performed better, with ChatML and DPO recommended for improved responses. Learning resources like fast.ai's course were highlighted for ML/DL beginners, and fine-tuning techniques with optimizers like Paged 8bit lion and adafactor were discussed.
At Nous Research AI, the Activation Beacon project introduced a method for unlimited context length in LLMs using "global state" tokens, potentially transforming retrieval-augmented models. The Eagle-7B model, based on RWKV-v5, outperformed Mistral in benchmarks with efficiency and multilingual capabilities. OpenHermes2.5 was recommended for consumer hardware due to its quantization methods. Multimodal and domain-specific models like IMP v1-3b, Bakllava, Moondream, and Qwen-vl were explored for classification and vision-language tasks. The community emphasized centralizing AI resources for collaborative research.
12/26/2023: not much happened today
llava exllama2 meta-ai-fair google-deepmind gpu-offloading vram-utilization model-conversion moe-models multimodality model-performance hardware-configuration model-saving chatml installation-issues music-generation
LM Studio users extensively discussed its performance, installation issues on macOS, and upcoming features like Exllama2 support and multimodality with the Llava model. Conversations covered GPU offloading, vRAM utilization, MoE model expert selection, and model conversion compatibility. The community also addressed inefficient help requests referencing the blog 'Don't Ask to Ask, Just Ask'. Technical challenges with ChromaDB Plugin, server vs desktop hardware performance, and saving model states with Autogen were highlighted. Discussions included comparisons with other chatbots and mentions of AudioCraft from meta-ai-fair and MusicLM from google-deepmind for music generation.