初始化项目，由ModelHub XC社区提供模型

Model: second-state/EXAONE-Deep-2.4B-GGUF Source: Original Platform
2026-09-18 12:52:18 +08:00
commit 2e0f5523b3
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-Deep-2.4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-2.4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/EXAONE-Deep-2.4B-Q2_K.gguf
+++ b/EXAONE-Deep-2.4B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429c28b27a9e21aba92e3004ae339e5176be906e46708c863694df9355388c6a
+size 1010443392
--- a/EXAONE-Deep-2.4B-Q3_K_L.gguf
+++ b/EXAONE-Deep-2.4B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44dc88716186cc867f6a11f4afe66bbc7c2cecdb1b03a1e0f853078f970b849a
+size 1345982592
--- a/EXAONE-Deep-2.4B-Q3_K_M.gguf
+++ b/EXAONE-Deep-2.4B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5479d394c74088ad74e0895d92bcb9b73fd77103919a342092eefbe6586e71df
+size 1249153152
--- a/EXAONE-Deep-2.4B-Q3_K_S.gguf
+++ b/EXAONE-Deep-2.4B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90be88f4c26df9afce5333358ba403017ded0ffbf36e2bd5d10b028d53c94675
+size 1140696192
--- a/EXAONE-Deep-2.4B-Q4_0.gguf
+++ b/EXAONE-Deep-2.4B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1d6a180aa71378a2f478963291722bb28d94397165b6454efc7ce28850edd4
+size 1425316992
--- a/EXAONE-Deep-2.4B-Q4_K_M.gguf
+++ b/EXAONE-Deep-2.4B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3af6cb2a8c18b1378b7ccebd0107551e1c72c5710288c89d09ed28ea625c233
+size 1497462912
--- a/EXAONE-Deep-2.4B-Q4_K_S.gguf
+++ b/EXAONE-Deep-2.4B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf22dbb60cf570a50c260e5e9b5b675052c2fc4fe8a2d6d4cf020cf381835c7f
+size 1433017472
--- a/EXAONE-Deep-2.4B-Q5_0.gguf
+++ b/EXAONE-Deep-2.4B-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5011bbf1501c8f3acb436d13e029bd7054c72a2446b991f8cd3ad73b23bdc7
+size 1693195392
--- a/EXAONE-Deep-2.4B-Q5_K_M.gguf
+++ b/EXAONE-Deep-2.4B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046dd829e7ad589a0b29e685fd003b2e8808008cd6015215eaf76bd56a2f2d07
+size 1730361472
--- a/EXAONE-Deep-2.4B-Q5_K_S.gguf
+++ b/EXAONE-Deep-2.4B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee794ccfbe1d46cb0b145d5042bb087e32d14eaa4eb714f57501f9167d5f85b4
+size 1693195392
--- a/EXAONE-Deep-2.4B-Q6_K.gguf
+++ b/EXAONE-Deep-2.4B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8e3fe002a61c947a103026ec010b13fe91fc08e61e0435e856b5ae6d03c2b7
+size 1977816192
--- a/EXAONE-Deep-2.4B-Q8_0.gguf
+++ b/EXAONE-Deep-2.4B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0b1a8b4b1e5036c1c077fb7efbe86176d8cb286633b4824206699d95ae4f74
+size 2560318592
--- a/EXAONE-Deep-2.4B-f16.gguf
+++ b/EXAONE-Deep-2.4B-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56d0455c99fda694a3f5090176c5010560755390217bc04d341ebdf9b328b18
+size 4815166592
--- a/README.md
+++ b/README.md
@@ -0,0 +1,90 @@
+---
+license: other
+license_name: exaone
+license_link: LICENSE
+model_name: EXAONE-Deep-2.4B
+base_model: LGAI-EXAONE/EXAONE-Deep-2.4B
+quantized_by: Second State Inc.
+language:
+- en
+- ko
+tags:
+- lg-ai
+- exaone
+- gguf
+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-Deep-2.4B-GGUF
+
+## Original Model
+
+[LGAI-EXAONE/EXAONE-Deep-2.4B](https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-2.4B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.12](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.12) and above
+
+- Prompt template
+
+  - Prompt type: `exaone-deep-chat`
+
+  - Prompt string
+
+    ```text
+    [|system|]{system_message}[|endofturn|]
+    [|user|]{user_message_1}
+    [|assistant|]{assistant_message_1}[|endofturn|]
+    [|user|]{user_message_2}
+    [|assistant|]<thought>
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-Deep-2.4B-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template exaone-deep-chat \
+      --ctx-size 32000 \
+      --model-name EXAONE-Deep-2.4B
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-Deep-2.4B-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-Deep-2.4B-Q2_K.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q2_K.gguf)     | Q2_K   | 2 | 1.01 GB| smallest, significant quality loss - not recommended for most purposes |
+| [EXAONE-Deep-2.4B-Q3_K_L.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q3_K_L.gguf) | Q3_K_L | 3 | 1.35 GB| small, substantial quality loss |
+| [EXAONE-Deep-2.4B-Q3_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q3_K_M.gguf) | Q3_K_M | 3 | 1.25 GB| very small, high quality loss |
+| [EXAONE-Deep-2.4B-Q3_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.14 GB| very small, high quality loss |
+| [EXAONE-Deep-2.4B-Q4_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q4_0.gguf)     | Q4_0   | 4 | 1.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [EXAONE-Deep-2.4B-Q4_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q4_K_M.gguf) | Q4_K_M | 4 | 1.50 GB| medium, balanced quality - recommended |
+| [EXAONE-Deep-2.4B-Q4_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q4_K_S.gguf) | Q4_K_S | 4 | 1.43 GB| small, greater quality loss |
+| [EXAONE-Deep-2.4B-Q5_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q5_0.gguf)     | Q5_0   | 5 | 1.69 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [EXAONE-Deep-2.4B-Q5_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q5_K_M.gguf) | Q5_K_M | 5 | 1.73 GB| large, very low quality loss - recommended |
+| [EXAONE-Deep-2.4B-Q5_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q5_K_S.gguf) | Q5_K_S | 5 | 1.69 GB| large, low quality loss - recommended |
+| [EXAONE-Deep-2.4B-Q6_K.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q6_K.gguf)     | Q6_K   | 6 | 1.98 GB| very large, extremely low quality loss |
+| [EXAONE-Deep-2.4B-Q8_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-Q8_0.gguf)     | Q8_0   | 8 | 2.56 GB| very large, extremely low quality loss - not recommended |
+| [EXAONE-Deep-2.4B-f16.gguf](https://huggingface.co/second-state/EXAONE-Deep-2.4B-GGUF/blob/main/EXAONE-Deep-2.4B-f16.gguf)       | f16    | 16 | 4.82 GB|  |
+
+*Quantized with llama.cpp b4920.*
--- 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": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "vocab_size": 102400
+}