update README.md

README.md

@@ -30,8 +30,6 @@ base_model:
 - mistralai/Mistral-Small-3.1-24B-Instruct-2503
 pipeline_tag: image-text-to-text
 tags:
-- neuralmagic
-- redhat
 - llmcompressor
 - quantized
 - int4
@@ -56,7 +54,7 @@ tags:
 - **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages not officially supported by the model.
 - **Release Date:** 04/15/2025
 - **Version:** 1.0
-- **Model Developers:** Red Hat (Neural Magic)
+- **Model Developers:** Ju214 (Neural Magic)
 
 
 ### Model Optimizations
@@ -77,13 +75,13 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 from vllm import LLM, SamplingParams
 from transformers import AutoProcessor
 
-model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic"
+model_id = "Ju214/Mistral-Small-24B-3.1"
 number_gpus = 1
 
 sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
 processor = AutoProcessor.from_pretrained(model_id)
 
-messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
+messages = [{"role": "user", "content": "Give me a introduction to large language model."}]
 
 prompts = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)