second-state/EXAONE-3.0-7.8B-Instruct-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: second-state/EXAONE-3.0-7.8B-Instruct-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 07:41:13 +08:00
commit a5174d2c50
17 changed files with 214 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
.gitattributes vendored Normal file
View File

@@ -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-3.0-7.8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
EXAONE-3.0-7.8B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

3
EXAONE-3.0-7.8B-Instruct-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7ef5a61c0d36b805a4d9edfeb4356a7a942c96cbe0ba4afa3494c7a8660b0dd7
size 3053868608

3
EXAONE-3.0-7.8B-Instruct-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05ce36d7d186c751169848b5b760c0aef7dd3ea4a1434fb1883c014f29bb0017
size 4185937472

3
EXAONE-3.0-7.8B-Instruct-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddf0d099b335abd00c87c4b19a48581c5bdffce5116c8551739ff88e2e76c133
size 3882899008

3
EXAONE-3.0-7.8B-Instruct-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8508cafe3d978db835e7cf09aba96a58ea4d9a9ca8315d39b2c5d2b7e87a9419
size 3528480320

3
EXAONE-3.0-7.8B-Instruct-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4df3ccb977bcdde848182f42a59f252348fa7fb211a690f7d86dbe9ea86ebf5a
size 4511127104

3
EXAONE-3.0-7.8B-Instruct-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f0443bade5af553a6a63de6cabc101d5aa8081007444cf212159fb6be957d77a
size 4770649664

3
EXAONE-3.0-7.8B-Instruct-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58dffec14c9aa73a2de78aedb00430ddb3a816968db635d4b6e476b0f58674bb
size 4542584384

3
EXAONE-3.0-7.8B-Instruct-Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d806c83b5804d5877f03e1e2de23013ed5c0638015d6798fe91c88119158ffa0
size 5435971136

3
EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef68b54b3b540c4d8f86bb0e65cd4c7b6fe3af20b21d358457ca1c027968e6ec
size 5569664576

3
EXAONE-3.0-7.8B-Instruct-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c23b432bd851943fa9fe308ed110b17cc3f015f587606050b20a3b0f234ece9e
size 5435971136

3
EXAONE-3.0-7.8B-Instruct-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58af82187b777f89e7e84abbd03ad136cd5bde660a3fe531c61fd52ab69a10f1
size 6418617920

3
EXAONE-3.0-7.8B-Instruct-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:19655cbc187149ef4927663b59d4cab532d8ab164889f7c9c9178558dee23e12
size 8312084032

3
EXAONE-3.0-7.8B-Instruct-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ff20387a7e702dc63d3895321f7060adb4af886d7590f215e01c0ec5bd4061a
size 15641630272

94
README.md Normal file
View File

@@ -0,0 +1,94 @@
---
license: other
license_name: exaone
license_link: LICENSE
model_name: EXAONE-3.0-7.8B-Instruct
base_model: LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
inference: false
model_creator: Meta Llama3
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- en
- ko
tags:
- lg-ai
- exaone
- gguf
---
<!-- 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-3.0-7.8B-Instruct-GGUF
## Original Model
[LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)
## Run with LlamaEdge
- LlamaEdge version: coming soon
<!-- - LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4) and above -->
- Prompt template
- Prompt type: `exaone-chat`
- Prompt string
```text
[|system|]system_prompt_text[|endofturn|]
[|user|]user_1st_turn_text
[|assistant|]assistant_1st_turn_text[|endofturn|]
[|user|]user_2nd_turn_text
[|assistant|]assistant_2nd_turn_text[|endofturn|]
```
- Context size: `4096`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template exaone-chat \
--ctx-size 4096 \
--model-name EXAONE-3.0-7.8B-Instruct
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template exaone-chat \
--ctx-size 4096
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [EXAONE-3.0-7.8B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.05 GB| smallest, significant quality loss - not recommended for most purposes |
| [EXAONE-3.0-7.8B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.19 GB| small, substantial quality loss |
| [EXAONE-3.0-7.8B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.88 GB| very small, high quality loss |
| [EXAONE-3.0-7.8B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.53 GB| very small, high quality loss |
| [EXAONE-3.0-7.8B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.51 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [EXAONE-3.0-7.8B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.77 GB| medium, balanced quality - recommended |
| [EXAONE-3.0-7.8B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.54 GB| small, greater quality loss |
| [EXAONE-3.0-7.8B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.44 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.57 GB| large, very low quality loss - recommended |
| [EXAONE-3.0-7.8B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.44 GB| large, low quality loss - recommended |
| [EXAONE-3.0-7.8B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.42 GB| very large, extremely low quality loss |
| [EXAONE-3.0-7.8B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.31 GB| very large, extremely low quality loss - not recommended |
| [EXAONE-3.0-7.8B-Instruct-f16.gguf](https://huggingface.co/second-state/EXAONE-3.0-7.8B-Instruct-GGUF/blob/main/EXAONE-3.0-7.8B-Instruct-f16.gguf) | f16 | 16 | 15.6 GB| |
*Quantized with llama.cpp b3807.*

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"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,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 4096,
"model_type": "exaone",
"num_attention_heads": 32,
"num_key_value_heads": 8,
"num_layers": 32,
"pad_token_id": 0,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.41.0",
"use_cache": true,
"vocab_size": 102400
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}