初始化项目，由ModelHub XC社区提供模型

Model: second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF Source: Original Platform
2026-09-15 08:24:15 +08:00
commit e95597bf83
16 changed files with 248 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
+DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepHermes-3-Llama-3-8B-Preview-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a325a034b1e182938ae2a536b14febc88032958a2eb45d497d5e451ac65d39
+size 3179137664
--- a/DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c6628ddf9f614cbc55d9af08c0d8f1d02ff7003d62d734b7e3295e6d9f0701
+size 4321962624
--- a/DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7586500237fc8c5d8f2972bd928eeed4df15ceafba51984f97697fefb3785da
+size 4018924160
--- a/DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf86d886ad20c42c491d6a409545bc61afc41b613dc165d48ae2bde3b59ba387
+size 3664505472
--- a/DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd32e18873f21c665e60f466e4a49159c34b2f1bcd66e7c0a90999027e67a212
+size 4661217920
--- a/DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11870b66a8e1faa9020b8a26bdf1b9b7bcf70ff8f28b8e5a95cd5ef202e807c1
+size 4920740480
--- a/DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f70b7b0f7e898ce80746f5cae0694190dc81a833f3e092e4b76fbe8bc788756
+size 4692675200
--- a/DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841944a025994ad88b7a4b48866b5e87661afa572315ed3639bbaaa03f4900de
+size 5599300224
--- a/DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b56f92e50040e5b66ba7d1e20de0a8a674e27f11ce18fe0b34fb5b5e13e87ed
+size 5732993664
--- a/DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3430e8f1eeef081f3410c72045b5fed8cde15af15460c43a307c429cda011f
+size 5599300224
--- a/DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb138f445b6c9e39bbe67d4cd82f91960d3943c411b015751b1279b13218a2d
+size 6596012672
--- a/DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edf79cb8b4eec74a64ca7c946949bdc3f571686d3d13a287b31071b197835a6
+size 8540777088
--- a/DeepHermes-3-Llama-3-8B-Preview-f16.gguf
+++ b/DeepHermes-3-Llama-3-8B-Preview-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e3e676ef0eb350b55b243b45eda41398ec59cfa41fbdae857264d2a4084d7e
+size 16068897408
--- a/README.md
+++ b/README.md
@@ -0,0 +1,123 @@
+---
+license: llama3
+base_model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
+model_creator: NousResearch
+model_type: llama
+quantized_by: Second State Inc.
+library_name: transformers
+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 -->
+
+# Meta-DeepHermes-3-Llama-3-8B-Preview-GGUF
+
+## Original Model
+
+[NousResearch/DeepHermes-3-Llama-3-8B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8) and above
+
+- Prompt template
+
+  **IMPORTANT**: To toggle REASONING ON, you must use the following system prompt:
+
+  ```text
+  You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
+  ```
+
+  - Prompt type for chat: `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|>
+      ```
+
+  - Prompt type for tool use: `llama-3-tool`
+
+    - Prompt string
+
+      ```text
+      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+      {system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+      Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+      Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+
+      [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]
+
+      Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+      ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-chat \
+      --ctx-size 128000 \
+      --model-name DeepHermes-3-Llama-3-8B-Preview
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-tool \
+      --ctx-size 128000 \
+      --model-name DeepHermes-3-Llama-3-8B-Preview
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [DeepHermes-3-Llama-3-8B-Preview-f16.gguf](https://huggingface.co/second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF/blob/main/DeepHermes-3-Llama-3-8B-Preview-f16.gguf)       | f16    | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b4743.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "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": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}