初始化项目，由ModelHub XC社区提供模型

Model: second-state/Meta-Llama-3.1-8B-Instruct-GGUF Source: Original Platform
2026-10-30 21:16:11 +08:00
commit 393452b54a
17 changed files with 272 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,61 @@
+*.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
+Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3.1-8B-Instruct-Q2_K.gguf
+++ b/Llama-3.1-8B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd52c261c8b48d964542130cee85cc027f844dc3b5b17064942e00713abb4eee
+size 3179136384
--- a/Llama-3.1-8B-Instruct-Q3_K_L.gguf
+++ b/Llama-3.1-8B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20aa85b66c8056cc2db641260651554ffee6c7f93410edbdaf0e8e46b968cefd
+size 4321961344
--- a/Llama-3.1-8B-Instruct-Q3_K_M.gguf
+++ b/Llama-3.1-8B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024edce38ba06f957af68a9e4ebf0691e1a897196ed5c067434bb488dc26d800
+size 4018922880
--- a/Llama-3.1-8B-Instruct-Q3_K_S.gguf
+++ b/Llama-3.1-8B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843e53b71ce4dd4526d08ecff24c6bc6fcadb260dcc94bf1e75d43d337af9df2
+size 3664504192
--- a/Llama-3.1-8B-Instruct-Q4_0.gguf
+++ b/Llama-3.1-8B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e1a5284dc2b7c202544a3e6ff64b08265563aae1a76b1c8938f5edc266e325
+size 4661216640
--- a/Llama-3.1-8B-Instruct-Q4_K_M.gguf
+++ b/Llama-3.1-8B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599024f21235045ea4ad7aecc5d46e794920e201d669328f577b1971cf98c904
+size 4920739200
--- a/Llama-3.1-8B-Instruct-Q4_K_S.gguf
+++ b/Llama-3.1-8B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f04f87f357c452540d8bf63e73f7145ed46281f9ffed434316edcc9b9f62ad2
+size 4692673920
--- a/Llama-3.1-8B-Instruct-Q5_0.gguf
+++ b/Llama-3.1-8B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09d287ea0dbbae61252d7a0447dba8528d9e087dfa0d5b2568ad0ddc59596b0
+size 5599298944
--- a/Llama-3.1-8B-Instruct-Q5_K_M.gguf
+++ b/Llama-3.1-8B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1240ea85e6c113d20e858649e0a8325f2187683b0c69075be6d184320d9d5c79
+size 5732992384
--- a/Llama-3.1-8B-Instruct-Q5_K_S.gguf
+++ b/Llama-3.1-8B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c80108e113b6d682dcb18c8487b52c3178690465e53481586d22146293613a8
+size 5599298944
--- a/Llama-3.1-8B-Instruct-Q6_K.gguf
+++ b/Llama-3.1-8B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ac847bb62c2e038b6c638c8eff6fa6416737096d7350619cbb75d29a5d61ba
+size 6596011392
--- a/Llama-3.1-8B-Instruct-Q8_0.gguf
+++ b/Llama-3.1-8B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798c1d12513bf2b2c9762c2ff5b9136de08fbbac0b498fe8b83d4f00d73d4044
+size 8540775808
--- a/Llama-3.1-8B-Instruct-f16.gguf
+++ b/Llama-3.1-8B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031c5d9ae1ad8cf676f8498ef539418c0d1f2b1b9c9d33c8f9207b83218c89b3
+size 16068896128
--- a/README.md
+++ b/README.md
@@ -0,0 +1,133 @@
+---
+license: llama3.1
+model_name: Meta-Llama-3.1-8B-Instruct-GGUF
+arxiv: 2307.09288
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct-GGUF
+inference: false
+model_creator: Meta Llama3
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+---
+
+<!-- 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-Llama-3.1-8B-Instruct-GGUF
+
+## Original Model
+
+[meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.5) and above
+
+- Prompt template
+
+  - 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:Llama-3.1-8B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-chat \
+      --ctx-size 128000 \
+      --model-name Llama-3.1-8b
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-8B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-tool \
+      --ctx-size 128000 \
+      --model-name Llama-3.1-8b
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-8B-Instruct-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 |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3.1-8B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.1-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Llama-3.1-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Llama-3.1-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Llama-3.1-8B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.1-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Llama-3.1-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Llama-3.1-8B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.1-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Llama-3.1-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [Llama-3.1-8B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [Llama-3.1-8B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3.1-8B-Instruct-f16.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-f16.gguf)       | f16    | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b4466.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "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}`