add model card and update tokenizer

README.md

@@ -1,9 +1,109 @@
 ---
-license: mit
+license: other
+license_name: modified-mit
+license_link: LICENSE
+base_model:
+- zai-org/GLM-5
 ---
 
-**Disclaimer**
+# Model Overview
 
-This model is provided for research and evaluation purposes only.
-Quantization may introduce accuracy or behavioral differences compared to the original model.
-Users are responsible for validating the model in their own environments and complying with the original model license.
+- **Model Architecture:** GLM-5
+  - **Input:** Text
+  - **Output:** Text
+- **Supported Hardware Microarchitecture:** AMD MI300/MI350/MI355 (emulation)
+- **ROCm:** 7.2.2
+- **Operating System(s):** Linux
+- **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
+- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (V0.12)
+  - **Weight quantization:** MOE-only, NVFP4, Static 
+  - **Activation quantization:** MOE-only, NVFP4, Dynamic 
+- **Calibration Dataset:** [Pile](https://huggingface.co/datasets/mit-han-lab/pile-val-backup)
+
+This model was built with GLM-5 model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for NVFP4 quantization.
+# Model Quantization
+
+The model was quantized from [zai-org/GLM-5](https://huggingface.co/zai-org/GLM-5) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). The weights and activations are quantized to NVFP4.
+
+**Quantization scripts:**
+```
+sudo sysctl -w vm.max_map_count=4194304
+cd Quark/examples/torch/language_modeling/llm_ptq/
+export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+export MODEL_DIR=/zai-org/GLM-5
+export output_dir=/amd/GLM-5-NVFP4
+exclude_layers="*self_attn* *mlp.gate *lm_head *mlp.gate_proj *mlp.up_proj *mlp.down_proj"
+python3 quantize_quark.py --model_dir $MODEL_DIR \
+                          --quant_scheme nvfp4 \
+                          --num_calib_data 128 \
+                          --exclude_layers $exclude_layers \
+                          --model_export hf_format \
+                          --output_dir $output_dir \
+                          --multi_gpu balanced
+```
+
+# Deployment
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend.
+
+## Evaluation
+The model was evaluated on GSM8K benchmarks. 
+
+### Accuracy
+
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>GLM-5 </strong>
+   </td>
+   <td><strong>GLM-5-NVFP4(this model) </strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>GSM8K (flexible-extract)
+   </td>
+   <td>95.45
+   </td>
+   <td>95.22
+   </td>
+   <td>99.75%
+   </td>
+  </tr>
+
+  </tr>
+</table>
+
+### Reproduction
+
+The GSM8K result was obtained using the `lm-evaluation-harness` framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260603`.
+
+Install the lm-eval `(Version: 0.4.12)` in container first.
+```
+pip install lm-eval
+pip install lm-eval[api]
+```
+#### Launching Server and Evaluating model
+```
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export VLLM_ROCM_USE_AITER=1
+export VLLM_ROCM_USE_AITER_MLA=1
+export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+export PYTORCH_ALLOC_CONF=expandable_segments:True
+lm_eval \
+  --model vllm \
+  --model_args pretrained=/amd/GLM-5-NVFP4,tensor_parallel_size=8,max_model_len=4096,gpu_memory_utilization=0.90,enforce_eager=True,max_gen_toks=2048,kv_cache_dtype=bfloat16,trust_remote_code=True \
+  --tasks gsm8k \
+  --num_fewshot 5 \
+  --batch_size auto
+
+```
+```
+
+
+# License
+Modifications Copyright(c) 2026 Advanced Micro Devices, Inc. All rights reserved.
+ 

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47757b9678da19e468edb3ae37a853996599945b5006914e5b088aff30002386
-size 20217707
+oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
+size 20217442