An OpenRLHF GRPO reinforcement-learning checkpoint for Qwen3-4B. - Saved at global step 16 of RL run seededrlbaseramp25stoppengen4kep2ncp10q4v3groot16. - This is the best checkpoint by pass@8 so far in this run (evaldefaultpass8 = 0.1244). Trained and validated on the cobalt-train ≤2/64 frontier (canonical cleaneval prompts): 1833 train / 112 held-out val problems the base model solved on at most 2 of 64 samples under the iidcanonical@64 hardness scan. Val evals sample at temperature 1.0 (matching the cleaneval frontier eval). Reward signal: binary code-correctness (1.0 if the generated program passes the problem's tests, otherwise 0.0). Eval metrics at this checkpoint (held-out val, 8…
Open weights
4.4B parameters
262,144 tokens
transformers
Model · Text generation
Qwen
We introduce the updated version of the Qwen3-4B-FP8 non-thinking mode, named Qwen3-4B-Instruct-2507-FP8, featuring the following key enhancements: - Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. - Substantial gains in long-tail knowledge coverage across multiple languages. - Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation. - Enhanced capabilities in 256K long-context understanding. This repo contains the FP8 version of Qwen3-4B-Instruct-2507, which has the following…
Open weights
apache-2.0
4.4B parameters
262,144 tokens
transformers
Model · Text generation
IFML
A masked diffusion language model adapted from Qwen3.5-4B. The backbone is hybrid: only its attention layers are made bidirectional, and the Gated DeltaNet layers stay causal. This is a base model, with no instruction tuning. Paper: dQwen3.5: Hybrid-Attention Diffusion Language Models. Code: https://github.com/AntonXue/dQwen Needs a CUDA GPU and transformers>=5.13 (tested with torch 2.7.1+cu128, flash-linear-attention 0.5.1). generate decodes the whole canvas at once, committing positions above a confidence threshold (tau=0.9); pass blocklength=32 for left-to-right block decoding, or tau=None, stepsperblock=k for a fixed budget. The 50B-token checkpoint from the paper is…
Open weights
apache-2.0
4.2B parameters
262,144 tokens
transformers
This is an uncensored version of TokenRhythm/NeoHorse-1-4B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Layers 5-17 are being ablated (0-based indexing). The MTP and Visual components were extracted from the original Qwen/Qwen3.5-4B and can provide excellent support. If needed, you only need to copy the contents of MTP-Visual to overwrite the model directory. You can use this model in your applications by loading it with Hugging Face's transformers library: - Risk of Sensitive or Controversial Outputs: This model’s safety filtering…
Open weights
apache-2.0
4.2B parameters
262,144 tokens
transformers
Text encoder weights from Google's T5 model
Open weights
apache-2.0
4.8B parameters
transformers
Model · Text generation
Qwen
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
Open weights
apache-2.0
4B parameters
40,960 tokens
transformers
