Conversation
Implements Ministral-style models with: - YaRN RoPE (Yet another RoPE extension) for extended context - GQA (Grouped Query Attention) with configurable num_key_value_heads - SwiGLU MLP with SiLU activation - RMSNorm Verified against HuggingFace transformers MistralForCausalLM with max diff ~6e-7 (floating point precision). Includes tests for: - Loading pretrained Mistral-7B and comparing logits - Creating models with custom config - Text generation with streaming output Co-Authored-By: Claude <noreply@anthropic.com>
Implements the Qwen3.5 text decoder architecture featuring: - Gated Delta Net linear attention (recurrent implementation) - Full attention with output sigmoid gate and QK norms - RMSNorm with unit offset, partial rotary embeddings (0.25 factor) - On-the-fly causal mask and RoPE computation for 262K context support Validated against HuggingFace transformers on Qwen/Qwen3.5-0.8B.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.