初始化项目，由ModelHub XC社区提供模型

Model: second-state/EXAONE-3.5-2.4B-Instruct-GGUF Source: Original Platform
2026-09-19 04:10:16 +08:00
commit 05e2a42090
16 changed files with 216 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,48 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-3.5-2.4B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3d9d5dd8b15e6bbd5940343a125c63366cc13cfb4b8529a50f2e3017bbe8c9
+size 1010442976
--- a/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfffc05e03da4f1d0a48872158a2c602ece6f6d485cd0ec6448a490e10ba1c9
+size 1345982176
--- a/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbeef3ba353c858a91e90048764d38508a372abe7c9240c9fe4ebf96b0745caa
+size 1249152736
--- a/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e32ad19c6fdaf36fa0272f45235434c82640d922d746fd1c1e638681e8f2743
+size 1140695776
--- a/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ce4ea3b862535505d0dd17fff28fbdd72c6dd7ca63725ff75af96074c789f0
+size 1425316576
--- a/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5568f285721bb1ac76a74c11e5d611fb08e328d40ce611463324993798c248db
+size 1497462496
--- a/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536a81b0be5581093a4990136bc9757e28955d76c5114ef820529c643fd8caee
+size 1433017056
--- a/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d125b6dabceb10da919f0b46bfaedd4346576274bdefbdfb767df56a2523d0
+size 1693194976
--- a/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9569a651d5225b473b188b5d302e0e9615883b97f553bf3b4ea17d8f65ec6929
+size 1730361056
--- a/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7152d02d2017768775ce4579be83411f149d7209438af6d6b121e72c1211a0
+size 1693194976
--- a/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b856a2a71bb50e84bbc2199d807e41a478996236ae2bf23dd88be3c4290e8a
+size 1977815776
--- a/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890bdfe963106c073f8e7b4260df488f86d2776bb02f0fe45bdb731964482395
+size 2560318176
--- a/EXAONE-3.5-2.4B-Instruct-f16.gguf
+++ b/EXAONE-3.5-2.4B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011c4f713560f2a5d57d5ba3e601d2873f27c2fb51c8677f991298feec1208fc
+size 4815166176
--- a/README.md
+++ b/README.md
@@ -0,0 +1,90 @@
+---
+license: other
+license_name: exaone
+license_link: LICENSE
+model_name: EXAONE-3.5-2.4B-Instruct
+base_model: LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
+quantized_by: Second State Inc.
+language:
+- en
+- ko
+tags:
+- lg-ai
+- exaone
+- exaone-3.5
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# EXAONE-3.5-2.4B-Instruct-GGUF
+
+## Original Model
+
+[LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.13](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.13) and above
+
+- Prompt template
+
+  - Prompt type: `exaone-chat`
+
+  - Prompt string
+
+    ```text
+    [|system|]{system_message}[|endofturn|]
+    [|user|]{user_message_1}
+    [|assistant|]{assistant_message_1}[|endofturn|]
+    [|user|]{user_message_2}
+    [|assistant|]
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template exaone-chat \
+      --ctx-size 32000 \
+      --model-name EXAONE-3.5-2.4B-Instruct
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template exaone-chat \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [EXAONE-3.5-2.4B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 1.01 GB| smallest, significant quality loss - not recommended for most purposes |
+| [EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 1.35 GB| small, substantial quality loss |
+| [EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.25 GB| very small, high quality loss |
+| [EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.14 GB| very small, high quality loss |
+| [EXAONE-3.5-2.4B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 1.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 1.50 GB| medium, balanced quality - recommended |
+| [EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 1.43 GB| small, greater quality loss |
+| [EXAONE-3.5-2.4B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 1.69 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.73 GB| large, very low quality loss - recommended |
+| [EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.69 GB| large, low quality loss - recommended |
+| [EXAONE-3.5-2.4B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 1.98 GB| very large, extremely low quality loss |
+| [EXAONE-3.5-2.4B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 2.56 GB| very large, extremely low quality loss - not recommended |
+| [EXAONE-3.5-2.4B-Instruct-f16.gguf](https://huggingface.co/second-state/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-f16.gguf)       | f16    | 16 | 4.82 GB|  |
+
+*Quantized with llama.cpp b4932.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,39 @@
+{
+  "activation_function": "silu",
+  "architectures": [
+    "ExaoneForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_exaone.ExaoneConfig",
+    "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "embed_dropout": 0.0,
+  "eos_token_id": 361,
+  "head_dim": 80,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 32768,
+  "model_type": "exaone",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_layers": 30,
+  "pad_token_id": 0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 1000000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.0",
+  "use_cache": true,
+  "vocab_size": 102400
+}