prithivMLmods commited on
Commit
b4968f6
·
verified ·
1 Parent(s): 17ab923

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -22,6 +22,9 @@ library_name: transformers
22
 
23
  > **Qwen3.5-4B-3D-Coder** is an early-preview independent fine-tune of `Qwen3.5-4B` by [ccore](https://huggingface.co/ccore), exploring general-purpose coding and interactive 3D scene generation using self-contained Three.js HTML and JavaScript. It was trained on the MIT-licensed ccore Three.js 3D Scenes dataset, containing 4,146 examples with prompts, reasoning traces, complete code, and complexity labels. The repository includes FP16 safetensors, Q4_K_M and Q8_0 GGUF builds, and a technical report. An October 27 checkpoint reportedly improves one-shot generation and scene quality. No quantitative benchmark results are provided; evaluation is demonstrated through sample 3D scenes. Released under Apache-2.0, it includes recommended sampling settings and a Three.js-focused system prompt. LM Studio users should disable multi-token prediction. Some generations may still require retries or minor code corrections.
24
 
 
 
 
25
  ## Model Files
26
 
27
  | File Name | Quant Type | File Size | File Link | Description |
 
22
 
23
  > **Qwen3.5-4B-3D-Coder** is an early-preview independent fine-tune of `Qwen3.5-4B` by [ccore](https://huggingface.co/ccore), exploring general-purpose coding and interactive 3D scene generation using self-contained Three.js HTML and JavaScript. It was trained on the MIT-licensed ccore Three.js 3D Scenes dataset, containing 4,146 examples with prompts, reasoning traces, complete code, and complexity labels. The repository includes FP16 safetensors, Q4_K_M and Q8_0 GGUF builds, and a technical report. An October 27 checkpoint reportedly improves one-shot generation and scene quality. No quantitative benchmark results are provided; evaluation is demonstrated through sample 3D scenes. Released under Apache-2.0, it includes recommended sampling settings and a Three.js-focused system prompt. LM Studio users should disable multi-token prediction. Some generations may still require retries or minor code corrections.
24
 
25
+ > [!NOTE]
26
+ > MTP — Speculative Decoding: No
27
+
28
  ## Model Files
29
 
30
  | File Name | Quant Type | File Size | File Link | Description |