Update README.md

README.md

@@ -4,10 +4,10 @@ base_model:
 base_model_relation: finetune
 tags:
 - kimi-k3
-  - compressed-tensors
-  - conversational
-  - abliterated
-  - uncensored
+- compressed-tensors
+- conversational
+- abliterated
+- uncensored
 license: other
 license_name: "kimi-k3"
 library_name: transformers
@@ -56,7 +56,7 @@ pipeline_tag: any-to-any
 
 **SHS-Lab/Kimi-K3-Abliterated** is an open-weight, natively multimodal agentic model derived from [Kimi K3](https://huggingface.co/moonshotai/Kimi-K3) through a targeted abliteration procedure. The base architecture is a 2.8-trillion-parameter Mixture-of-Experts network built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), featuring native vision capabilities and a 1-million-token context window.
 
-This variant has been post-processed to attenuate alignment-driven refusal mechanisms. The underlying architecture, parameter count, context length, and multimodal capabilities remain identical to the base model. Ablibration modifies weight values to suppress safeguard activations without altering the structural design or introducing new training data.
+This variant has been post-processed to attenuate alignment-driven refusal mechanisms. The underlying architecture, parameter count, context length, and multimodal capabilities remain identical to the base model. Abliteration modifies weight values to suppress safeguard activations without altering the structural design or introducing new training data.
 
 The release is intended for alignment research, red-team evaluation, and controlled experimentation in governed environments.
 
@@ -161,7 +161,7 @@ All architectural specifications are inherited from the base Kimi K3 model. Abli
       </tr>
       <tr>
         <td align="center" style="vertical-align: middle; text-align: center"><strong>Modality</strong></td>
-        <td align="center" style="vertical-align: middle; text-align: center">Text, Image</td>
+        <td align="center" style="vertical-align: middle; text-align: center">Text, Image, Video</td>
       </tr>
     </tbody>
   </table>
@@ -262,7 +262,7 @@ This model is **not** intended for unsupervised deployment in consumer-facing pr
 ## 4. Evaluation Results
 
 > [!IMPORTANT]
-> All benchmark scores in this section were reported for the **base Kimi K3 model** by its original developers. No independent evaluation campaign has been conducted on this abliterated variant. These results are reproduced as an upper-bound reference for inherited capability. Ablibration targets refusal behavior and is not expected to materially alter benchmark performance, but users should validate task-specific accuracy independently before relying on this variant in production or research settings.
+> All benchmark scores in this section were reported for the **base Kimi K3 model** by its original developers. No independent evaluation campaign has been conducted on this abliterated variant. These results are reproduced as an upper-bound reference for inherited capability. Abliteration targets refusal behavior and is not expected to materially alter benchmark performance, but users should validate task-specific accuracy independently before relying on this variant in production or research settings.
 
 <div align="center">
   <table>
@@ -766,7 +766,7 @@ The model is compatible with the following inference engines:
 vllm serve SHS-Lab/Kimi-K3-Abliterated \
     --tensor-parallel-size 8 \
     --trust-remote-code \
-    --max-model-len 131072 \
+    --max-model-len 1,048,576 \
     --enable-auto-tool-choice \
     --tool-call-parser kimi_k3
 ```