commit 53cd3f57d5a63ddcfe5d0b18989eb4cf9800598e Author: ModelHub XC Date: Sun Sep 13 20:08:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Mungert/EXAONE-4.0-1.2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..91b3fcc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,70 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +EXAONE-4.0-1.2B-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-bf16.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B.imatrix filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-4.0-1.2B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/EXAONE-4.0-1.2B-bf16.gguf b/EXAONE-4.0-1.2B-bf16.gguf new file mode 100644 index 0000000..9315bed --- /dev/null +++ b/EXAONE-4.0-1.2B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7fca8145392e433ee3abb07ec9383add184138f847f743971ac4eb648603b9 +size 2563248800 diff --git a/EXAONE-4.0-1.2B-bf16_q8_0.gguf b/EXAONE-4.0-1.2B-bf16_q8_0.gguf new file mode 100644 index 0000000..fb2a970 --- /dev/null +++ b/EXAONE-4.0-1.2B-bf16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b04ad2dad5ab7d5343d6627a43e004f2016c3f3165a24f0a162722d0af2a59f +size 1943933600 diff --git a/EXAONE-4.0-1.2B-f16_q8_0.gguf b/EXAONE-4.0-1.2B-f16_q8_0.gguf new file mode 100644 index 0000000..6a61192 --- /dev/null +++ b/EXAONE-4.0-1.2B-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914369d14b7a09db230d2d0717784c00c8878e4bbf2cf4a34d95de7225af9315 +size 1943933600 diff --git a/EXAONE-4.0-1.2B-iq3_m.gguf b/EXAONE-4.0-1.2B-iq3_m.gguf new file mode 100644 index 0000000..b48d46b --- /dev/null +++ b/EXAONE-4.0-1.2B-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d1f6507db73d1db4b0454793e8a290fb67c5465ffb3b65aa1d742f34e930dd +size 656495552 diff --git a/EXAONE-4.0-1.2B-iq3_s.gguf b/EXAONE-4.0-1.2B-iq3_s.gguf new file mode 100644 index 0000000..81cf021 --- /dev/null +++ b/EXAONE-4.0-1.2B-iq3_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdeaca615eef0b666dc29760f9c0d34cc770875334156612e87418f44481ee13 +size 642339776 diff --git a/EXAONE-4.0-1.2B-iq3_xs.gguf b/EXAONE-4.0-1.2B-iq3_xs.gguf new file mode 100644 index 0000000..2fa8d8a --- /dev/null +++ b/EXAONE-4.0-1.2B-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf67c274788422607170116aa319e4ff4252c70ec45ddcb3c339b294e08aef8 +size 592303040 diff --git a/EXAONE-4.0-1.2B-iq3_xxs.gguf b/EXAONE-4.0-1.2B-iq3_xxs.gguf new file mode 100644 index 0000000..9838760 --- /dev/null +++ b/EXAONE-4.0-1.2B-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824092f52d033bb94d74b931af0fd0941c0fb51173d52d334396fcdc955556de +size 576967616 diff --git a/EXAONE-4.0-1.2B-iq4_nl.gguf b/EXAONE-4.0-1.2B-iq4_nl.gguf new file mode 100644 index 0000000..718d485 --- /dev/null +++ b/EXAONE-4.0-1.2B-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a871434b44f07c1f6ee14a3392bdb58032e67c4bfc8bbe804d3965e7d7c3c1 +size 782308288 diff --git a/EXAONE-4.0-1.2B-iq4_xs.gguf b/EXAONE-4.0-1.2B-iq4_xs.gguf new file mode 100644 index 0000000..e457d75 --- /dev/null +++ b/EXAONE-4.0-1.2B-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7b2030f6e015f534d99c9e0bb30deca02972733e6a5c85f833970aa4345430 +size 749867968 diff --git a/EXAONE-4.0-1.2B-q3_k_m.gguf b/EXAONE-4.0-1.2B-q3_k_m.gguf new file mode 100644 index 0000000..ea33dd3 --- /dev/null +++ b/EXAONE-4.0-1.2B-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d943a9c2734f2d83b97117a2c11b254fe3ecffe5e5a176f04a90a9ce51a4585 +size 691950528 diff --git a/EXAONE-4.0-1.2B-q3_k_s.gguf b/EXAONE-4.0-1.2B-q3_k_s.gguf new file mode 100644 index 0000000..eb67fef --- /dev/null +++ b/EXAONE-4.0-1.2B-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f1946462c8c39b545c0b0bb33b1e8a1d1379dd740a66688581791278c575da +size 659641280 diff --git a/EXAONE-4.0-1.2B-q4_0.gguf b/EXAONE-4.0-1.2B-q4_0.gguf new file mode 100644 index 0000000..cf47e32 --- /dev/null +++ b/EXAONE-4.0-1.2B-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34baf661813d1d6a4ec863ec48a689505059e136af1fdb266e0a442cab9386bd +size 724308928 diff --git a/EXAONE-4.0-1.2B-q4_1.gguf b/EXAONE-4.0-1.2B-q4_1.gguf new file mode 100644 index 0000000..25fd356 --- /dev/null +++ b/EXAONE-4.0-1.2B-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f65e3816f3fade244212165016dc9a7e8e690d9e427e97a586bd55ff4762ad8 +size 804262848 diff --git a/EXAONE-4.0-1.2B-q4_k_m.gguf b/EXAONE-4.0-1.2B-q4_k_m.gguf new file mode 100644 index 0000000..49bc17d --- /dev/null +++ b/EXAONE-4.0-1.2B-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aaa9f45ed2f41e65f7110b61dad5d39a9151232614bef269b99cafe5f722763 +size 815584192 diff --git a/EXAONE-4.0-1.2B-q4_k_s.gguf b/EXAONE-4.0-1.2B-q4_k_s.gguf new file mode 100644 index 0000000..03811ef --- /dev/null +++ b/EXAONE-4.0-1.2B-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4de945231f1de4b11480285eb8082c3e0a525a50fd5c24770a186b0bd4a474 +size 788730816 diff --git a/EXAONE-4.0-1.2B-q5_0.gguf b/EXAONE-4.0-1.2B-q5_0.gguf new file mode 100644 index 0000000..df08cce --- /dev/null +++ b/EXAONE-4.0-1.2B-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c234544b195fa12123ee8c755c68169d35a7e03d31f47a02bfab10d860eb852c +size 884216768 diff --git a/EXAONE-4.0-1.2B-q5_1.gguf b/EXAONE-4.0-1.2B-q5_1.gguf new file mode 100644 index 0000000..334cb93 --- /dev/null +++ b/EXAONE-4.0-1.2B-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1c5efdbd33f9ecf359c0928978364ff1f36b7967595a5c9491287d3388ed97 +size 964170688 diff --git a/EXAONE-4.0-1.2B-q5_k_m.gguf b/EXAONE-4.0-1.2B-q5_k_m.gguf new file mode 100644 index 0000000..0317b54 --- /dev/null +++ b/EXAONE-4.0-1.2B-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e3c0de3e35ef5646f197d0971c3980917f675fd3ac5b4418e37db6b27cf35f +size 932959168 diff --git a/EXAONE-4.0-1.2B-q5_k_s.gguf b/EXAONE-4.0-1.2B-q5_k_s.gguf new file mode 100644 index 0000000..0e8b470 --- /dev/null +++ b/EXAONE-4.0-1.2B-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d550238dc6a72f8f32af659eb2d15866bd2c03914334000d2182f7fa428893dc +size 922932160 diff --git a/EXAONE-4.0-1.2B-q6_k_m.gguf b/EXAONE-4.0-1.2B-q6_k_m.gguf new file mode 100644 index 0000000..57ab92f --- /dev/null +++ b/EXAONE-4.0-1.2B-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71be54b8c4912f83aaa654893813914b90e5d9694c03cc418d6b28e7bf8cbf22 +size 1054118848 diff --git a/EXAONE-4.0-1.2B-q8_0.gguf b/EXAONE-4.0-1.2B-q8_0.gguf new file mode 100644 index 0000000..a98a53d --- /dev/null +++ b/EXAONE-4.0-1.2B-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6838f2519becc940b49f259acad42d1b53fcea9c5f4fdf5cc101e032228f950 +size 1363940000 diff --git a/EXAONE-4.0-1.2B.imatrix b/EXAONE-4.0-1.2B.imatrix new file mode 100644 index 0000000..7827f33 --- /dev/null +++ b/EXAONE-4.0-1.2B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a333f8af22636837854f71b1480a128f402daa886bf9a59d6fc11a114bd7dbfb +size 1973048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..51dbde0 --- /dev/null +++ b/README.md @@ -0,0 +1,1259 @@ +--- +license: other +license_name: exaone +license_link: LICENSE +language: +- en +- ko +- es +tags: +- lg-ai +- exaone +- exaone-4.0 +pipeline_tag: text-generation +library_name: transformers +--- + +# EXAONE-4.0-1.2B GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`bf9087f5`](https://github.com/ggerganov/llama.cpp/commit/bf9087f59aab940cf312b85a67067ce33d9e365a). + + + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +

+ +🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 +
✈️ Try on FriendliAI +
+ +# EXAONE-4.0-1.2B + +## Introduction + +We introduce **EXAONE 4.0**, which integrates a **Non-reasoning mode** and **Reasoning mode** to achieve both the excellent usability of [EXAONE 3.5](https://github.com/LG-AI-EXAONE/EXAONE-3.5) and the advanced reasoning abilities of [EXAONE Deep](https://github.com/LG-AI-EXAONE/EXAONE-Deep). To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended +to support Spanish in addition to English and Korean. + +The EXAONE 4.0 model series consists of two sizes: a mid-size **32B** model optimized for high performance, and a small-size **1.2B** model designed for on-device applications. + +In the EXAONE 4.0 architecture, we apply new architectural changes compared to previous EXAONE models as below: + +1. **Hybrid Attention**: For the 32B model, we adopt hybrid attention scheme, which combines *Local attention (sliding window attention)* with *Global attention (full attention)* in a 3:1 ratio. We do not use RoPE (Rotary Positional Embedding) for global attention for better global context understanding. +2. **QK-Reorder-Norm**: We reorder the LayerNorm position from the traditional Pre-LN scheme by applying LayerNorm directly to the attention and MLP outputs, and we add RMS normalization right after the Q and K projection. It helps yield better performance on downstream tasks despite consuming more computation. + +For more details, please refer to our [technical report](https://arxiv.org/abs/2507.11407), [HuggingFace paper](https://huggingface.co/papers/2507.11407), [blog](https://www.lgresearch.ai/blog/view?seq=576), and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-4.0). + + +### Model Configuration + +- Number of Parameters (without embeddings): 1.07B +- Number of Layers: 30 +- Number of Attention Heads: GQA with 32-heads and 8-KV heads +- Vocab Size: 102,400 +- Context Length: 65,536 tokens + + +## Quickstart + +You should install the transformers library forked from the original, available in our [PR](https://github.com/huggingface/transformers/pull/39129). +Once this PR is merged and released, we will update this section. + +You can install the latest version of transformers with support for EXAONE 4.0 by following the command: + +```bash +pip install git+https://github.com/lgai-exaone/transformers@add-exaone4 +``` + +### Non-reasoning mode + +For general use, you can use the EXAONE 4.0 models with the following example: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "LGAI-EXAONE/EXAONE-4.0-1.2B" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="bfloat16", + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +# choose your prompt +prompt = "Explain how wonderful you are" +prompt = "Explica lo increíble que eres" +prompt = "너가 얼마나 대단한지 설명해 봐" + +messages = [ + {"role": "user", "content": prompt} +] +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt" +) + +output = model.generate( + input_ids.to(model.device), + max_new_tokens=128, + do_sample=False, +) +print(tokenizer.decode(output[0])) +``` + +### Reasoning mode + +The EXAONE 4.0 models have reasoning capabilities for handling complex problems. You can activate reasoning mode by using the `enable_thinking=True` argument with the tokenizer, which opens a reasoning block that starts with `` tag without closing it. + +```python +messages = [ + {"role": "user", "content": "Which one is bigger, 3.12 vs 3.9?"} +] +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt", + enable_thinking=True, +) + +output = model.generate( + input_ids.to(model.device), + max_new_tokens=128, + do_sample=True, + temperature=0.6, + top_p=0.95 +) +print(tokenizer.decode(output[0])) +``` + +> [!IMPORTANT] +> The model generation with reasoning mode can be affected sensitively by sampling parameters, so please refer to the [Usage Guideline](#usage-guideline) for better quality. + +### Agentic tool use + +The EXAONE 4.0 models can be used as agents with their tool calling capabilities. You can provide tool schemas to the model for effective tool calling. + +```python +import random + +def roll_dice(max_num: int): + return random.randint(1, max_num) + +tools = [ + { + "type": "function", + "function": { + "name": "roll_dice", + "description": "Roll a dice with the number 1 to N. User can select the number N.", + "parameters": { + "type": "object", + "required": ["max_num"], + "properties": { + "max_num": { + "type": "int", + "description": "Max number of the dice" + } + } + } + } + } +] + +messages = [ + {"role": "user", "content": "Roll D6 dice twice!"} +] +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt", + tools=tools, +) + +output = model.generate( + input_ids.to(model.device), + max_new_tokens=1024, + do_sample=True, + temperature=0.6, + top_p=0.95, +) +print(tokenizer.decode(output[0])) +``` + + +## Deployment + +### TensorRT-LLM + +TensorRT-LLM officially supports EXAONE 4.0 models in the latest commits. Before it is released, you need to clone the TensorRT-LLM repository to build from source. + +```bash +git clone https://github.com/NVIDIA/TensorRT-LLM.git +``` + +After cloning the repository, you need to build the source for installation. Please refer to [the official documentation](https://nvidia.github.io/TensorRT-LLM/installation/build-from-source-linux.html) for a guide to build the TensorRT-LLM environment. + +You can run the TensorRT-LLM server by following steps: + +1. Write extra configuration YAML file + ```yaml + # extra_llm_api_config.yaml + kv_cache_config: + enable_block_reuse: false + ``` + +2. Run server with the configuration + ```bash + trtllm-serve serve [MODEL_PATH] --backend pytorch --extra_llm_api_options extra_llm_api_config.yaml + ``` + +For more details, please refer to [the documentation](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/models/core/exaone) of EXAONE from TensorRT-LLM. + +> [!NOTE] +> Other inference engines including `vllm` and `sglang` don't support the EXAONE 4.0 officially now. We will update as soon as these libraries are updated. + + +## Performance + +The following tables show the evaluation results of each model, with reasoning and non-reasoning mode. The evaluation details can be found in the [technical report](https://arxiv.org/abs/2507.11407). + +- ✅ denotes the model has a hybrid reasoning capability, evaluated by selecting reasoning / non-reasoning on the purpose. +- To assess Korean **practical** and **professional** knowledge, we adopt both the [KMMLU-Redux](https://huggingface.co/datasets/LGAI-EXAONE/KMMLU-Redux) and [KMMLU-Pro](https://huggingface.co/datasets/LGAI-EXAONE/KMMLU-Pro) benchmarks. Both datasets are publicly released! + + +### 32B Reasoning Mode + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EXAONE 4.0 32B Phi 4 reasoning-plusMagistral Small-2506Qwen 3 32B Qwen 3 235B DeepSeek R1-0528
Model Size32.0B14.7B23.6B32.8B235B671B
Hybrid Reasoning✅ ✅✅
World Knowledge
MMLU-Redux92.390.886.890.992.793.4
MMLU-Pro81.876.073.480.083.085.0
GPQA-Diamond75.468.968.268.471.181.0
Math/Coding
AIME 202585.378.062.872.981.587.5
HMMT Feb 202572.953.643.550.462.579.4
LiveCodeBench v572.651.755.865.770.775.2
LiveCodeBench v666.747.147.460.158.970.3
Instruction Following
IFEval83.784.937.985.083.480.8
Multi-IF (EN)73.556.127.473.473.472.0
Agentic Tool Use
BFCL-v363.9N/A40.470.370.864.7
Tau-bench (Airline)51.5N/A38.534.537.553.5
Tau-bench (Retail)62.8N/A10.255.258.363.9
Multilinguality
KMMLU-Pro67.755.851.561.468.171.7
KMMLU-Redux72.762.754.667.574.577.0
KSM87.679.871.982.886.286.7
MMMLU (ES)85.684.368.982.886.788.2
MATH500 (ES)95.894.283.594.395.196.0
+ +### 32B Non-Reasoning Mode + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EXAONE 4.0 32B Phi 4Mistral-Small-2506Gemma 3 27BQwen3 32B Qwen3 235B Llama-4-MaverickDeepSeek V3-0324
Model Size32.0B14.7B24.0B27.4B32.8B235B402B671B
Hybrid Reasoning✅ ✅✅
World Knowledge
MMLU-Redux89.888.385.985.085.789.292.392.3
MMLU-Pro77.670.469.167.574.477.480.581.2
GPQA-Diamond63.756.146.142.454.662.969.868.4
Math/Coding
AIME 202535.917.830.223.820.224.718.050.0
HMMT Feb 202521.84.016.910.39.811.97.329.2
LiveCodeBench v543.324.625.827.531.335.343.446.7
LiveCodeBench v643.127.426.929.728.031.432.744.0
Instruction Following
IFEval84.863.077.882.683.283.285.481.2
Multi-IF (EN)71.647.763.272.171.972.577.968.3
Long Context
HELMET58.3N/A61.958.354.563.313.7N/A
RULER88.2N/A71.866.085.690.62.9N/A
LongBench v148.1N/A51.551.544.245.334.7N/A
Agentic Tool Use
BFCL-v365.2N/A57.7N/A63.068.052.963.8
Tau-Bench (Airline)25.5N/A36.1N/A16.027.038.040.5
Tau-Bench (Retail)55.9N/A35.5N/A47.656.56.568.5
Multilinguality
KMMLU-Pro60.044.851.050.758.364.468.867.3
KMMLU-Redux64.850.153.653.364.471.776.972.2
KSM59.829.135.536.141.346.640.663.5
Ko-LongBench76.9N/A55.472.073.974.665.6N/A
MMMLU (ES)80.681.278.478.782.183.786.986.7
MATH500 (ES)87.378.283.486.884.787.278.789.2
WMT24++ (ES)90.789.392.293.191.492.992.794.3
+ +### 1.2B Reasoning Mode + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EXAONE 4.0 1.2B EXAONE Deep 2.4BQwen 3 0.6B Qwen 3 1.7B SmolLM3 3B
Model Size1.28B2.41B596M1.72B3.08B
Hybrid Reasoning✅ ✅✅✅
World Knowledge
MMLU-Redux71.568.955.673.974.8
MMLU-Pro59.356.438.357.757.8
GPQA-Diamond52.054.327.940.141.7
Math/Coding
AIME 202545.247.915.136.836.7
HMMT Feb 202534.027.37.021.826.0
LiveCodeBench v544.647.212.333.227.6
LiveCodeBench v645.343.116.429.929.1
Instruction Following
IFEval67.871.059.272.571.2
Multi-IF (EN)53.954.537.553.547.5
Agentic Tool Use
BFCL-v352.9N/A46.456.637.1
Tau-Bench (Airline)20.5N/A22.031.037.0
Tau-Bench (Retail)28.1N/A3.36.55.4
Multilinguality
KMMLU-Pro42.724.621.638.330.5
KMMLU-Redux46.925.024.538.033.7
KSM60.660.922.852.949.7
MMMLU (ES)62.451.448.864.564.7
MATH500 (ES)88.884.570.687.987.5
+ +### 1.2B Non-Reasoning Mode + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
EXAONE 4.0 1.2B Qwen 3 0.6B Gemma 3 1BQwen 3 1.7B SmolLM3 3B
Model Size1.28B596M1.00B1.72B3.08B
Hybrid Reasoning✅✅ ✅✅
World Knowledge
MMLU-Redux66.944.640.963.465.0
MMLU-Pro52.026.614.743.743.6
GPQA-Diamond40.122.919.228.635.7
Math/Coding
AIME 202523.52.62.19.89.3
HMMT Feb 202513.01.01.55.14.7
LiveCodeBench v526.43.61.811.611.4
LiveCodeBench v630.16.92.316.620.6
Instruction Following
IFEval74.754.580.268.276.7
Multi-IF (EN)62.137.532.551.051.9
Long Context
HELMET41.221.1N/A33.838.6
RULER77.455.1N/A65.966.3
LongBench v136.932.4N/A41.939.9
Agentic Tool Use
BFCL-v355.744.1N/A52.247.3
Tau-Bench (Airline)10.031.5N/A13.538.0
Tau-Bench (Retail)21.75.7N/A4.66.7
Multilinguality
KMMLU-Pro37.524.69.729.527.6
KMMLU-Redux40.422.819.429.826.4
KSM26.30.122.816.316.1
Ko-LongBench69.816.4N/A57.115.7
MMMLU (ES)54.639.535.954.355.1
MATH500 (ES)71.238.541.266.062.4
WMT24++ (ES)65.958.276.976.784.0
+ + + +## Usage Guideline + +> [!IMPORTANT] +> To achieve the expected performance, we recommend using the following configurations: +> +> - For non-reasoning mode, we recommend using a lower temperature value such as `temperature<0.6` for better performance. +> - For reasoning mode (using `` block), we recommend using `temperature=0.6` and `top_p=0.95`. +> - If you suffer from the model degeneration, we recommend using `presence_penalty=1.5`. +> - For Korean general conversation with 1.2B model, we suggest to use `temperature=0.1` to avoid code switching. + + +## Limitation + +The EXAONE language model has certain limitations and may occasionally generate inappropriate responses. The language model generates responses based on the output probability of tokens, and it is determined during learning from training data. While we have made every effort to exclude personal, harmful, and biased information from the training data, some problematic content may still be included, potentially leading to undesirable responses. Please note that the text generated by EXAONE language model does not reflect the views of LG AI Research. + +- Inappropriate answers may be generated, which contain personal, harmful or other inappropriate information. +- Biased responses may be generated, which are associated with age, gender, race, and so on. +- The generated responses rely heavily on statistics from the training data, which can result in the generation of +semantically or syntactically incorrect sentences. +- Since the model does not reflect the latest information, the responses may be false or contradictory. + +LG AI Research strives to reduce potential risks that may arise from EXAONE language models. Users are not allowed +to engage in any malicious activities (e.g., keying in illegal information) that may induce the creation of inappropriate +outputs violating LG AI's ethical principles when using EXAONE language models. + + +## License + +The model is licensed under [EXAONE AI Model License Agreement 1.2 - NC](./LICENSE) + +> [!NOTE] +> The main difference from the older version is as below: +> - We removed **the claim of model output ownership** from the license. +> - We restrict the model use **against the development of models that compete with EXAONE**. +> - We allow the model to be used for **educational purposes**, not just research. + + +## Citation + +``` +@article{exaone-4.0, + title={EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes}, + author={{LG AI Research}}, + journal={arXiv preprint arXiv:2507.11407}, + year={2025} +} +``` + + +## Contact + +LG AI Research Technical Support: contact_us@lgresearch.ai + + + + +--- + +# 🚀 If you find these models useful + +Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**: + +👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) + + +The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder) + +💬 **How to test**: + Choose an **AI assistant type**: + - `TurboLLM` (GPT-4.1-mini) + - `HugLLM` (Hugginface Open-source models) + - `TestLLM` (Experimental CPU-only) + +### **What I’m Testing** +I’m pushing the limits of **small open-source models for AI network monitoring**, specifically: +- **Function calling** against live network services +- **How small can a model go** while still handling: + - Automated **Nmap security scans** + - **Quantum-readiness checks** + - **Network Monitoring tasks** + +🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space): +- ✅ **Zero-configuration setup** +- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low. +- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate! + +### **Other Assistants** +🟢 **TurboLLM** – Uses **gpt-4.1-mini** : +- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. +- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents** +- **Real-time network diagnostics and monitoring** +- **Security Audits** +- **Penetration testing** (Nmap/Metasploit) + +🔵 **HugLLM** – Latest Open-source models: +- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita. + +### 💡 **Example commands you could test**: +1. `"Give me info on my websites SSL certificate"` +2. `"Check if my server is using quantum safe encyption for communication"` +3. `"Run a comprehensive security audit on my server"` +4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution! + +### Final Word + +I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful. + +If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone. + +I'm also open to job opportunities or sponsorship. + +Thank you! 😊 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file