Update README.md

README.md

@@ -3,13 +3,16 @@ library_name: transformers
 pipeline_tag: text-generation
 tags: [qwen3, byte-level, pretraining]
 ---
-# Qwen90M Byte
-24 vanilla Qwen3 layers, width 640, MLP 1440, 10 query / 2 KV heads, head dimension 64.
-90,148,352 tied-embedding parameters. 259 tokens: bytes 0–255, PAD 256, BOS 257, EOS 258.
-Trained from scratch; this is a base model, not a Qwen instruction checkpoint.
-
-Load the model with `AutoModelForCausalLM.from_pretrained(repo)`.
-Load its custom byte tokenizer with `AutoTokenizer.from_pretrained(repo, trust_remote_code=True)`.
-Training records begin with BOS; prepend `tokenizer.bos_token_id` to encoded generation prompts.
-See training_config.json and coverage.json for the mixture and consumed data statistics.
-Model weights are FP32 masters trained under BF16 autocast. Use dtype=torch.bfloat16 for GPU inference.
+# void.1
+
+![logo](https://huggingface.co/dotlabs/void.1/resolve/main/void.1-logo.png)
+
+# details
+
+90,148,352 tied-embedding parameters. 
+
+259 tokens: bytes 0–255, PAD 256, BOS 257, EOS 258.
+
+pretrained from scratch on cortex (our internal symbolic kernel), rewrite, climbmix, openmath and ultrafineweb.
+
+we used revision `92c601560cc2179e3bfc33e067fdd3bf9254e163` for evaluations, for more details on the evals, please have a look at the official notebook.