初始化项目，由ModelHub XC社区提供模型

Model: second-state/EXAONE-Deep-7.8B-GGUF
Source: Original Platform

.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-7.8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+EXAONE-Deep-7.8B-f16.gguf filter=lfs diff=lfs merge=lfs -text

EXAONE-Deep-7.8B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb5884abd128f13e2a98ad4301e2113feb46fc082d773c89127b5c088f473bd
+size 3053869376

EXAONE-Deep-7.8B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a404e70626111ef260161b318ba3b4db8807f7991254ad0b9bb3a112a9c42a33
+size 4185938240

EXAONE-Deep-7.8B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11f31f1d50101feab23837198865f49bc5dd961f070f79050580ff0d3f83ab9
+size 3882899776

EXAONE-Deep-7.8B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8de7e06b488a39ce7c088a35f837f7f0d180658a52b9f3d3984604ee3dcb80
+size 3528481088

EXAONE-Deep-7.8B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649128fcd4999f56faabb9303d2583518d512176ef9219b077efda0509a8d426
+size 4511127872

EXAONE-Deep-7.8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9577b87d9236bd7600bbd023d44c328d327d5718c137ffecffb2e8d0b8ca20
+size 4770650432

EXAONE-Deep-7.8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a72c3ed3f9608bc8cbf32c99c0764b8ba0930ddd11add8bdd665ec772ceca3
+size 4542585152

EXAONE-Deep-7.8B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ddcb863de2c839b91e4ea9c45a2d7c98be3e540ce570468776957e7527ea6c
+size 5435971904

EXAONE-Deep-7.8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2639d869e460a41888bec74539391004f8bb4a36438621e54b8522fb0b480ebe
+size 5569665344

EXAONE-Deep-7.8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e899da5848cb939603e61bdf39894d27f97cc4d5e689fbfc4eb5eda5e0cd353a
+size 5435971904

EXAONE-Deep-7.8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4faf78cb87d6aa4cf3e087c120d6b20db196b58d986b97688a3d791204c573
+size 6418618688

EXAONE-Deep-7.8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4994f8326a5d125763fddcd5be4e4fbc6e936ee06c191c19b56b66e66193ec2
+size 8312084800

EXAONE-Deep-7.8B-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421cb2b03deea12183ba0fe32abb41920bc9cb6a04e5d8a7da276579182a1989
+size 15641631040

README.md

@@ -0,0 +1,90 @@
+---
+license: other
+license_name: exaone
+license_link: LICENSE
+model_name: EXAONE-Deep-7.8B
+base_model: LGAI-EXAONE/EXAONE-Deep-7.8B
+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-7.8B-GGUF
+
+## Original Model
+
+[LGAI-EXAONE/EXAONE-Deep-7.8B](https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-7.8B)
+
+## 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-7.8B-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template exaone-deep-chat \
+      --ctx-size 32000 \
+      --model-name EXAONE-Deep-7.8B
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-Deep-7.8B-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template exaone-deep-chat \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [EXAONE-Deep-7.8B-Q2_K.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q2_K.gguf)     | Q2_K   | 2 | 3.05 GB| smallest, significant quality loss - not recommended for most purposes |
+| [EXAONE-Deep-7.8B-Q3_K_L.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.19 GB| small, substantial quality loss |
+| [EXAONE-Deep-7.8B-Q3_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q3_K_M.gguf) | Q3_K_M | 3 | 3.88 GB| very small, high quality loss |
+| [EXAONE-Deep-7.8B-Q3_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.53 GB| very small, high quality loss |
+| [EXAONE-Deep-7.8B-Q4_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q4_0.gguf)     | Q4_0   | 4 | 4.51 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [EXAONE-Deep-7.8B-Q4_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.77 GB| medium, balanced quality - recommended |
+| [EXAONE-Deep-7.8B-Q4_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.54 GB| small, greater quality loss |
+| [EXAONE-Deep-7.8B-Q5_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q5_0.gguf)     | Q5_0   | 5 | 5.44 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [EXAONE-Deep-7.8B-Q5_K_M.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.57 GB| large, very low quality loss - recommended |
+| [EXAONE-Deep-7.8B-Q5_K_S.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.44 GB| large, low quality loss - recommended |
+| [EXAONE-Deep-7.8B-Q6_K.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q6_K.gguf)     | Q6_K   | 6 | 6.42 GB| very large, extremely low quality loss |
+| [EXAONE-Deep-7.8B-Q8_0.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-Q8_0.gguf)     | Q8_0   | 8 | 8.31 GB| very large, extremely low quality loss - not recommended |
+| [EXAONE-Deep-7.8B-f16.gguf](https://huggingface.co/second-state/EXAONE-Deep-7.8B-GGUF/blob/main/EXAONE-Deep-7.8B-f16.gguf)       | f16    | 16 | 15.6 GB|  |
+
+*Quantized with llama.cpp b4920.*

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": 128,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 32768,
+  "model_type": "exaone",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_layers": 32,
+  "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": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "vocab_size": 102400
+}