初始化项目，由ModelHub XC社区提供模型

Model: second-state/Hermes-2-Pro-Llama-3-8B-GGUF Source: Original Platform
2026-06-04 02:18:12 +08:00
commit 6e2491ffbf
17 changed files with 212 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
+Hermes-2-Pro-Llama-3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Hermes-2-Pro-Llama-3-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e66860c5cc3c8c8061411f3fb933113cf60981f865325a996797f9f2f587554
+size 3179282752
--- a/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06c5b1f869c4340b3c9f060edf8f9093382200755a3106c2ebca73243724410
+size 4322121024
--- a/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587a0f95458ca2af15c7bc9941a6f55afe9d3a645c96e942a003ab2820c97e76
+size 4019082560
--- a/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4959d3232682d2889050d4b750b98767e65264ffaa1b53a5b81077f63aa6f3
+size 3664663872
--- a/Hermes-2-Pro-Llama-3-8B-Q4_0.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8c9da1e16dd6aad27eae1de01fd619adbb0b45d35382750fc9ac9f26545d22
+size 4661393728
--- a/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25eb4693f950fb92af73ad7e4ab2d2c62242eac7ebf0542b22ab10869d0f019
+size 4920916288
--- a/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95c97b662159fd5cd9a09e10e15bcaf68a76201d52aa5c90b2207ee648451aa
+size 4692851008
--- a/Hermes-2-Pro-Llama-3-8B-Q5_0.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364040840855c299b675996a02fb0b3f094490d2f08ee92644ff40cca2f1cb24
+size 5599492416
--- a/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5da8abc83d89056051e7ec35b6960c47c1fd17a405b33fa4d605a39854213c
+size 5733185856
--- a/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5956af3bc4771a00583edd124d59afb9a2eb8a76f593429a2825a8699d8504b7
+size 5599492416
--- a/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b54c22ae57a4755418df65af934a5fa05dd9b8784331980e9c06c4b92cefd1
+size 6596222272
--- a/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d138388cfda04d185a68eaf2396cf7a5cfa87d038a20896817a9b7cf1806f532
+size 8541050176
--- a/Hermes-2-Pro-Llama-3-8B-f16.gguf
+++ b/Hermes-2-Pro-Llama-3-8B-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bc8f527e865e21c20d49c462af2f775e31e6ba36bdee1216b3de1e8a25eef5
+size 16069416256
--- a/README.md
+++ b/README.md
@@ -0,0 +1,96 @@
+---
+model_name: Hermes-2-Pro-Llama-3-8B
+base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
+inference: false
+model_creator: NousResearch
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+language:
+- en
+---
+
+<!-- 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 -->
+
+# Hermes-2-Pro-Llama-3-8B-GGUF
+
+## Original Model
+
+[NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.11.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.3) and above
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {user_message}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+- Context size: `4096`
+
+- Run as LlamaEdge service
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template chatml \
+      --ctx-size 4096 \
+      --model-name hermes-2-pro-llama-3-8b
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template chatml-tool \
+      --ctx-size 4096 \
+      --model-name hermes-2-pro-llama-3-8b
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 4096
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Hermes-2-Pro-Llama-3-8B-Q2_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Hermes-2-Pro-Llama-3-8B-Q4_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Hermes-2-Pro-Llama-3-8B-Q5_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [Hermes-2-Pro-Llama-3-8B-Q6_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [Hermes-2-Pro-Llama-3-8B-Q8_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Hermes-2-Pro-Llama-3-8B-f16.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-f16.gguf)     | f16   | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b3135.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./hermes-2-pro-llama-3-8b-DPO",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128003,
+  "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": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 128288
+}
--- 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}`