初始化项目，由ModelHub XC社区提供模型

Model: second-state/Llama-3-Instruct-8B-SimPO-GGUF Source: Original Platform
2026-06-21 08:03:13 +08:00
commit f320b5de7d
17 changed files with 206 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
+Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Instruct-8B-SimPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3-Instruct-8B-SimPO-Q2_K.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e0ae2e9cd50322d2d3fa2e5cce9bba28a3584d727c62d86e480d7a27b7cf87
+size 3179130720
--- a/Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2dcfbe5312e07f20151c257cbcc8fc5f7c5c0e8f3e5aea133d92b656df7fba
+size 4321955680
--- a/Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a992c745825ba15d5e5548a581ea1d7fc209f46a5d711856c824184cdce0ec
+size 4018917216
--- a/Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2be87d4409f29467b1746ca62e09bfbed3b1448d454789e5f8d3936ff7d15a0
+size 3664498528
--- a/Llama-3-Instruct-8B-SimPO-Q4_0.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97caffe9f321d15af8f49bd4322ab6f14ca21efa7f05b025e61cd926c6a4905e
+size 4661210976
--- a/Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4546465936dc83d1dd46e6e867b0cfcfd858a2b214217b390ae0473ac432dc66
+size 4920733536
--- a/Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c15a07f6409fe2b3db4dac8a8d86a79dd9f52df50c0d73f096aa6101584cbe
+size 4692668256
--- a/Llama-3-Instruct-8B-SimPO-Q5_0.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dc1ff1602f86c081bdd63d5cd875f7c1b92a3d7a7201df63ec84fe4c6d45bb
+size 5599293280
--- a/Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4ba180d625ca4ced6f2a77609de3c284c810aeee4335cfba9648419c410a43
+size 5732986720
--- a/Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f71b73ccd34493a08c606e1b066ddc7eac838d95801f0b186e42933ebc5027d
+size 5599293280
--- a/Llama-3-Instruct-8B-SimPO-Q6_K.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e133af8bfc7c5cfabac86494b5bf467202b31a365bff1aca08a7874b86382c27
+size 6596005728
--- a/Llama-3-Instruct-8B-SimPO-Q8_0.gguf
+++ b/Llama-3-Instruct-8B-SimPO-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0e0c69c60efb7b408debc84e649c744952fec61860e38f7095214c638937f8
+size 8540770144
--- a/Llama-3-Instruct-8B-SimPO-f16.gguf
+++ b/Llama-3-Instruct-8B-SimPO-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a567c56c820eb87990b90077ceafc6ee1702cfd02e1de16d0d13fc94522fbc
+size 16068890464
--- a/README.md
+++ b/README.md
@@ -0,0 +1,90 @@
+---
+language:
+- en
+license: other
+license_name: llama3
+model_name: Llama-3-Instruct-8B-SimPO
+base_model: princeton-nlp/Llama-3-Instruct-8B-SimPO
+inference: false
+model_creator: princeton-nlp
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+---
+
+<!-- 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 -->
+
+# Llama-3-Instruct-8B-SimPO-GGUF
+
+## Original Model
+
+[princeton-nlp/Llama-3-Instruct-8B-SimPO](https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-SimPO)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2)
+
+- Prompt template
+
+  - Prompt type: `llama-3-chat`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `4096`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 4096 \
+    --model-name Llama-3-8b
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 4096
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3-Instruct-8B-SimPO-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Llama-3-Instruct-8B-SimPO-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Llama-3-Instruct-8B-SimPO-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [Llama-3-Instruct-8B-SimPO-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [Llama-3-Instruct-8B-SimPO-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3-Instruct-8B-SimPO-f16.gguf](https://huggingface.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF/blob/main/Llama-3-Instruct-8B-SimPO-f16.gguf)     | f16   | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b2963.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "princeton-nlp/Llama-3-Instruct-8B-SimPO",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`