Improve model card: Add Tequila paper, Transformers usage, license, and updated tags

README.md

@@ -1,10 +1,22 @@
 ---
 tags:
-- qwen3
-- eagle3
 - eagle
+- eagle3
+- llama
+- qwen3
+- quantization
+- speculative-decoding
+- tequila
+- ternary-quantization
+pipeline_tag: text-generation
+library_name: transformers
+license: apache-2.0
 ---
 
+This model repository is part of the **AngelSlim** toolkit and implements the **Tequila: Trapping-free Ternary Quantization for Large Language Models** method, as presented in the paper [Tequila: Trapping-free Ternary Quantization for Large Language Models](https://huggingface.co/papers/2509.23809).
+
+For the Tequila quantization implementation, refer to the [AngelSlim GitHub repository](https://github.com/Tencent/AngelSlim) and specifically the [TernaryQuant branch](https://github.com/Tencent/AngelSlim/tree/tequila/TernaryQuant).
+
 <p align="center">
   <picture>
     <source media="(prefers-color-scheme: dark)" srcset="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo_light.png?raw=true">
@@ -27,10 +39,11 @@ Dedicated to building a more intuitive, comprehensive, and efficient LLMs compre
 - [Latest Updates](#latest-updates)
 - [Key Features](#key-features)
 - [Supported Models](#supported-models)
+- [Sample Usage](#sample-usage)
 - [How to Use](#how-to-use)
   - [Install AngelSlim](#install-angelslim)
   - [Quick Start](#quick-start)
-  - [deployment & Evaluation](#deployment)
+  - [Deployment and Testing](#deployment-and-testing)
 - [Benchmark](#benchmark)
 - [License](#license)
 - [Citation](#citation)
@@ -38,6 +51,7 @@ Dedicated to building a more intuitive, comprehensive, and efficient LLMs compre
 
 ## 📣Latest Updates
 
+- [25/09/30] We released Tequila's implementation: *TEQUILA: TRAPPING-FREE TERNARY QUANTIZATION FOR LARGE LANGUAGE MODELS* | [[论文]](https://arxiv.org/abs/2509.23809) | [[代码]](https://github.com/Tencent/AngelSlim/tree/tequila/TernaryQuant).
 - [25/07/04] We now support quantization for Hunyuan/Qwen2.5/Qwen3/DeepSeek-R1-Distill-Qwen and other models, including INT8/FP8/INT4 algorithms.
               We also opensource Qwen3-8B`s Eagle3 model weight.
 
@@ -80,6 +94,45 @@ The Eagle3 weights for the Qwen3 series model are now available.
 | ✅ [Qwen3-32B](https://huggingface.co/AngelSlim/Qwen3-32B_eagle3)      |
 | ✅ [Qwen3-30B-A3B](https://huggingface.co/AngelSlim/Qwen3-a3B_eagle3)  |
 
+## 🛎️Sample Usage
+
+You can use our provided "eagenerate" for speedup generation just like using 'generate' from Hugging Face. Here is an example:
+
+```python
+from eagle.model.ea_model import EaModel
+from fastchat.model import get_conversation_template
+import torch
+from transformers import AutoTokenizer # Assuming AutoTokenizer is available via transformers
+
+# Placeholder paths, replace with actual model paths
+base_model_path = "YOUR_BASE_MODEL_PATH" # e.g., "meta-llama/Llama-3.1-8B-Instruct"
+EAGLE_model_path = "YOUR_EAGLE_MODEL_PATH" # This repository's path or a specific EAGLE checkpoint
+
+model = EaModel.from_pretrained(
+    base_model_path=base_model_path,
+    ea_model_path=EAGLE_model_path,
+    torch_dtype=torch.float16,
+    low_cpu_mem_usage=True,
+    device_map="auto",
+    total_token=-1
+)
+model.eval()
+your_message="Hello"
+conv = get_conversation_template("vicuna")
+conv.append_message(conv.roles[0], your_message)
+conv.append_message(conv.roles[1], None)
+prompt = conv.get_prompt()
+input_ids=model.tokenizer([prompt]).input_ids
+input_ids = torch.as_tensor(input_ids).cuda()
+output_ids=model.eagenerate(input_ids,temperature=0.5,max_new_tokens=512)
+output=model.tokenizer.decode(output_ids[0])
+print(output)
+```
+
+**_Note: Vicuna, LLaMA2-Chat, and LLaMA3-Instruct are both chat models. You need to use the correct chat template, otherwise it will cause abnormal output from the model and affect the performance of EAGLE._**
+
+For detailed instructions on installation, deployment, and running the AngelSlim toolkit, please refer to the [AngelSlim GitHub repository](https://github.com/Tencent/AngelSlim).
+
 ## 🛎️How to Use
 
 ### Install AngelSlim
@@ -209,26 +262,26 @@ Benchmark results for Qwen3 series models with `FP8-Static`, `FP8-Dynamic`, `INT
     <tr><td>INT8-Dynamic</td><td>78.01</td><td>74.84</td><td>86.96</td><td>67.07</td></tr>
     <tr><td>INT4-GPTQ</td><td>77.19</td><td>73.26</td><td>86.43</td><td>62.20</td></tr>
     <tr><td>INT4-AWQ</td><td>76.15</td><td>73.59</td><td>86.96</td><td>63.41</td></tr>
-    <tr><td rowspan="6">Qwen3-14B</td><td>BF16</td><td>83.06</td><td>78.90</td><td>88.40</td><td>55.49</td></tr>
+    <tr><td rowspan=\"6\">Qwen3-14B</td><td>BF16</td><td>83.06</td><td>78.90</td><td>88.40</td><td>55.49</td></tr>
     <tr><td>FP8-Static</td><td>82.62</td><td>78.57</td><td>89.46</td><td>57.32</td></tr>
     <tr><td>FP8-Dynamic</td><td>82.24</td><td>78.92</td><td>88.32</td><td>52.44</td></tr>
     <tr><td>INT8-Dynamic</td><td>81.87</td><td>78.13</td><td>86.28</td><td>56.10</td></tr>
     <tr><td>INT4-GPTQ</td><td>81.05</td><td>78.02</td><td>87.34</td><td>57.93</td></tr>
     <tr><td>INT4-AWQ</td><td>82.02</td><td>77.68</td><td>84.23</td><td>61.59</td></tr>
-    <tr><td rowspan="5">Qwen3-32B</td><td>BF16</td><td>86.55</td><td>82.00</td><td>74.53</td><td>37.80</td></tr>
+    <tr><td rowspan=\"5\">Qwen3-32B</td><td>BF16</td><td>86.55</td><td>82.00</td><td>74.53</td><td>37.80</td></tr>
     <tr><td>FP8-Static</td><td>86.92</td><td>81.78</td><td>70.20</td><td>39.63</td></tr>
     <tr><td>FP8-Dynamic</td><td>86.55</td><td>81.89</td><td>70.43</td><td>38.41</td></tr>
     <tr><td>INT4-GPTQ</td><td>86.18</td><td>81.01</td><td>-</td><td>43.29</td></tr>
     <tr><td>INT4-AWQ</td><td>86.18</td><td>81.54</td><td>-</td><td>36.59</td></tr>
-    <tr><td rowspan="4">Qwen3-30B-A3B</td><td>BF16</td><td>83.66</td><td>79.36</td><td>89.99</td><td>31.71</td></tr>
+    <tr><td rowspan=\"4\">Qwen3-30B-A3B</td><td>BF16</td><td>83.66</td><td>79.36</td><td>89.99</td><td>31.71</td></tr>
     <tr><td>FP8-Static</td><td>83.95</td><td>79.47</td><td>89.01</td><td>31.10</td></tr>
     <tr><td>FP8-Dynamic</td><td>84.10</td><td>79.40</td><td>89.16</td><td>32.93</td></tr>
     <tr><td>INT8-Dynamic</td><td>83.36</td><td>79.48</td><td>89.16</td><td>34.15</td></tr>
-    <tr><td rowspan="4">Qwen3-235B-A22B</td><td>BF16</td><td>89.60</td><td>86.28</td><td>85.29</td><td>27.44</td></tr>
+    <tr><td rowspan=\"4\">Qwen3-235B-A22B</td><td>BF16</td><td>89.60</td><td>86.28</td><td>85.29</td><td>27.44</td></tr>
     <tr><td>FP8-Static</td><td>89.67</td><td>86.19</td><td>86.96</td><td>27.44</td></tr>
     <tr><td>FP8-Dynamic</td><td>89.67</td><td>86.18</td><td>85.22</td><td>28.05</td></tr>
     <tr><td>INT8-Dynamic</td><td>88.93</td><td>86.20</td><td>86.20</td><td>23.78</td></tr>
-    <tr><td rowspan="5">QwQ-32B</td><td>BF16</td><td>85.74</td><td>82.03</td><td>73.31</td><td>42.68</td></tr>
+    <tr><td rowspan=\"5\">QwQ-32B</td><td>BF16</td><td>85.74</td><td>82.03</td><td>73.31</td><td>42.68</td></tr>
     <tr><td>FP8-Static</td><td>85.44</td><td>81.91</td><td>75.36</td><td>42.68</td></tr>
     <tr><td>FP8-Dynamic</td><td>85.07</td><td>81.93</td><td>75.66</td><td>42.07</td></tr>
     <tr><td>INT4-GPTQ</td><td>84.03</td><td>81.26</td><td>68.23</td><td>45.73</td></tr>
@@ -245,30 +298,30 @@ Benchmark results for other models with `FP8-Static`, `FP8-Dynamic`, `INT4-GPTQ`
     <tr><th>Model</th><th>Quantization</th><th>CEVAL</th><th>MMLU</th><th>GSM8K</th></tr>
   </thead>
   <tbody>
-    <tr><td rowspan="3">Qwen2.5-1.5B-Instruct</td><td>BF16</td><td>67.01</td><td>60.05</td><td>54.28</td></tr>
+    <tr><td rowspan=\"3\">Qwen2.5-1.5B-Instruct</td><td>BF16</td><td>67.01</td><td>60.05</td><td>54.28</td></tr>
     <tr><td>FP8-Static</td><td>66.27</td><td>60.23</td><td>-</td></tr>
     <tr><td>FP8-Dynamic</td><td>66.79</td><td>60.08</td><td>51.71</td></tr>
-    <tr><td rowspan="5">Qwen2.5-7B-Instruct</td><td>BF16</td><td>81.20</td><td>74.55</td><td>79.98</td></tr>
+    <tr><td rowspan=\"5\">Qwen2.5-7B-Instruct</td><td>BF16</td><td>81.20</td><td>74.55</td><td>79.98</td></tr>
     <tr><td>FP8-Static</td><td>81.13</td><td>74.03</td><td>79.30</td></tr>
     <tr><td>FP8-Dynamic</td><td>80.31</td><td>74.07</td><td>79.00</td></tr>
     <tr><td>INT4-GPTQ</td><td>79.05</td><td>73.05</td><td>74.75</td></tr>
     <tr><td>INT4-AWQ</td><td>79.35</td><td>73.22</td><td>79.38</td></tr>
-    <tr><td rowspan="5">Qwen2.5-32B-Instruct</td><td>BF16</td><td>87.30</td><td>83.21</td><td>81.73</td></tr>
+    <tr><td rowspan=\"5\">Qwen2.5-32B-Instruct</td><td>BF16</td><td>87.30</td><td>83.21</td><td>81.73</td></tr>
     <tr><td>FP8-Static</td><td>87.59</td><td>83.08</td><td>81.58</td></tr>
     <tr><td>FP8-Dynamic</td><td>87.30</td><td>83.04</td><td>81.58</td></tr>
     <tr><td>INT4-GPTQ</td><td>86.70</td><td>82.45</td><td>82.03</td></tr>
     <tr><td>INT4-AWQ</td><td>87.00</td><td>82.64</td><td>-</td></tr>
-    <tr><td rowspan="5">DeepSeek-R1-Distill-Qwen-7B</td><td>BF16</td><td>53.49</td><td>53.80</td><td>75.74</td></tr>
+    <tr><td rowspan=\"5\">DeepSeek-R1-Distill-Qwen-7B</td><td>BF16</td><td>53.49</td><td>53.80</td><td>75.74</td></tr>
     <tr><td>FP8-Static</td><td>53.57</td><td>54.17</td><td>76.19</td></tr>
     <tr><td>FP8-Dynamic</td><td>52.97</td><td>54.13</td><td>74.15</td></tr>
     <tr><td>INT4-GPTQ</td><td>51.86</td><td>52.44</td><td>75.89</td></tr>
     <tr><td>INT4-AWQ</td><td>53.49</td><td>53.70</td><td>-</td></tr>
-    <tr><td rowspan="5">DeepSeek-R1-Distill-Qwen-14B</td><td>BF16</td><td>77.71</td><td>74.28</td><td>85.67</td></tr>
+    <tr><td rowspan=\"5\">DeepSeek-R1-Distill-Qwen-14B</td><td>BF16</td><td>77.71</td><td>74.28</td><td>85.67</td></tr>
     <tr><td>FP8-Static</td><td>77.56</td><td>74.66</td><td>86.73</td></tr>
     <tr><td>FP8-Dynamic</td><td>76.82</td><td>74.63</td><td>87.11</td></tr>
     <tr><td>INT4-GPTQ</td><td>74.29</td><td>72.37</td><td>84.61</td></tr>
     <tr><td>INT4-AWQ</td><td>74.81</td><td>73.00</td><td>86.05</td></tr>
-    <tr><td rowspan="5">DeepSeek-R1-Distill-Qwen-32B</td><td>BF16</td><td>84.18</td><td>80.89</td><td>87.41</td></tr>
+    <tr><td rowspan=\"5\">DeepSeek-R1-Distill-Qwen-32B</td><td>BF16</td><td>84.18</td><td>80.89</td><td>87.41</td></tr>
     <tr><td>FP8-Static</td><td>83.43</td><td>80.90</td><td>87.57</td></tr>
     <tr><td>FP8-Dynamic</td><td>83.73</td><td>81.10</td><td>86.43</td></tr>
     <tr><td>INT4-GPTQ</td><td>84.10</td><td>79.80</td><td>86.73</td></tr>
@@ -294,15 +347,15 @@ Benchmark results for Qwen3 series models with `Eagle3` speculative decoding alg
   </thead>
   <tbody>
     <!-- <tr><td colspan="12" style="text-align: center; vertical-align: middle;"><strong>Temperature=0</strong></td></tr> -->
-    <tr><td rowspan="6"><strong>T=0</strong></td>
+    <tr><td rowspan=\"6\"><strong>T=0</strong></td>
     <td>Qwen3-1.7B</td><td>2.05x</td><td>2.81</td><td>2.07x</td><td>2.93</td><td>2.11x</td><td>2.98</td><td>1.93x</td><td>2.69</td><td>2.04x</td><td>2.85</td></tr>
     <tr> <td>Qwen3-4B</td><td>2.21x</td><td>3.01</td><td>2.36x</td><td>3.24</td><td>2.42x</td><td>3.13</td><td>2.32x</td><td>2.75</td><td>2.33x</td><td>3.03</td></tr>
     <tr><td>Qwen3-8B</td><td>2.65x</td><td>3.87</td><td>2.64x</td><td>3.82</td><td>2.86x</td><td>4.10</td><td>2.58x</td><td>3.55</td><td>2.68x</td><td>3.83</td></tr>
     <tr><td>Qwen3-14B</td><td>2.42x</td><td>3.38</td><td>2.57x</td><td>3.58</td><td>2.75x</td><td>3.77</td><td>2.27x</td><td>3.11</td><td>2.50x</td><td>3.46</td></tr>
     <tr><td>Qwen3-32B</td><td>2.39x</td><td>2.78</td><td>2.37x</td><td>2.81</td><td>2.47x</td><td>2.92</td><td>2.42x</td><td>2.53</td><td>2.41x</td><td>2.76</td></tr>
     <tr><td>Qwen3-30B-A3B</td><td>2.84x</td><td>3.63</td><td>2.27x</td><td>3.09</td><td>2.64x</td><td>3.42</td><td>2.83x</td><td>3.56</td><td>2.64x</td><td>3.42</td></tr>
-    <!-- <tr><td colspan="12" style="text-align: center; vertical-align: middle;"><strong>Temperature=1</strong></td></tr> -->
-    <tr><td rowspan="6"><strong>T=1</strong></td>
+    <!-- <tr><td colspan=\"12\" style="text-align: center; vertical-align: middle;"><strong>Temperature=1</strong></td></tr> -->
+    <tr><td rowspan=\"6\"><strong>T=1</strong></td>
     <td>Qwen3-1.7B</td><td>1.74x</td><td>2.53</td><td>1.86x</td><td>2.70</td><td>1.82x</td><td>2.69</td><td>1.72x</td><td>2.46</td><td>1.93x</td><td>2.60</td></tr>
     <tr><td>Qwen3-4B</td><td>1.93x</td><td>2.60</td><td>2.00x</td><td>2.84</td><td>2.11x</td><td>2.82</td><td>2.34x</td><td>2.50</td><td>1.75x</td><td>2.69</td></tr>
     <tr><td>Qwen3-8B</td><td>1.91x</td><td>2.84</td><td>2.07x</td><td>3.05</td><td>2.34x</td><td>3.26</td><td>2.09x</td><td>2.92</td><td>2.10x</td><td>3.02</td></tr>
@@ -328,12 +381,12 @@ Benchmark results for Hunyuan series models with `Eagle3` speculative decoding a
   </thead>
   <tbody>
     <!-- <tr><td colspan="12" style="text-align: center; vertical-align: middle;"><strong>Temperature=0</strong></td></tr> -->
-    <tr><td rowspan="3"><strong>T=0</strong></td>
+    <tr><td rowspan=\"3\"><strong>T=0</strong></td>
     <td>Hunyuan-1.8B-Instruct</td><td>1.97x</td><td>2.90</td><td>2.58x</td><td>3.73</td><td>2.61x</td><td>3.71</td><td>1.71x</td><td>2.43</td><td>2.22x</td><td>3.19</td></tr>
     <tr> <td>Hunyuan-4B-Instruct</td><td>1.77x</td><td>2.60</td><td>2.64x</td><td>3.35</td><td>2.14x</td><td>3.17</td><td>1.72x</td><td>2.57</td><td>2.07x</td><td>2.92</td></tr>
     <tr><td>Hunyuan-7B-Instruct</td><td>2.22x</td><td>3.58</td><td>3.59x</td><td>5.47</td><td>2.96x</td><td>4.68</td><td>1.64x</td><td>2.56</td><td>2.60x</td><td>4.07</td></tr>
     <!-- <tr><td colspan="12" style="text-align: center; vertical-align: middle;"><strong>Temperature=1</strong></td></tr> -->
-    <tr><td rowspan="3"><strong>T=1</strong></td>
+    <tr><td rowspan=\"3\"><strong>T=1</strong></td>
     <td>Hunyuan-1.8B-Instruct</td><td>1.58x</td><td>2.36</td><td>2.35x</td><td>3.56</td><td>2.23x</td><td>3.38</td><td>1.26x</td><td>1.87</td><td>1.86x</td><td>2.79</td></tr>
     <tr><td>Hunyuan-4B-Instruct</td><td>1.36x</td><td>2.05</td><td>1.97x</td><td>2.86</td><td>1.72x</td><td>2.68</td><td>1.14x</td><td>1.76</td><td>1.55x</td><td>2.34</td></tr>
     <tr><td>Hunyuan-7B-Instruct</td><td>1.90x</td><td>3.11</td><td>3.12x</td><td>5.09</td><td>2.74x</td><td>4.34</td><td>1.47x</td><td>2.39</td><td>2.31x</td><td>3.73</td></tr>