初始化项目，由ModelHub XC社区提供模型

Model: second-state/Llama-3-Groq-8B-Tool-Use-GGUF
Source: Original Platform

.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-Groq-8B-Tool-Use-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Groq-8B-Tool-Use-f16.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-Groq-8B-Tool-Use-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a68cbb3c060db2477e3903fa4ad58c55cec7d8d746b3fbf06528834dce1bc81
+size 3179159616

Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07e960878e928c812bb8221be1a67bc52c39e130883f88e71224269556f4643
+size 4321987072

Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b25169c87c4524438b18fc6c639bcd2facfc871cd62852e877e511c19e54b64
+size 4018948608

Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4b659295ba5eb440cedd973a1396cb63584f21653a41a4fb133d57dfdcd04a
+size 3664529920

Llama-3-Groq-8B-Tool-Use-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599eb1519ad94d920d09ed9f086eaada58dd6975f480bf44c7787c13f12b34e3
+size 4661245632

Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5befe6403a919e048eb5cf3d0038b0a6d4a5b6ec2f25fea8292af27fa918b0
+size 4920768192

Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884ad4b028d3989b83041238a6011ce6ad34c25498d8e6dc9def0fd50c0e735f
+size 4692702912

Llama-3-Groq-8B-Tool-Use-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770556afc3c25919398765478709075a4b9c7f15dc9424abceff880cfca4f980
+size 5599331008

Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cfcd97c83387ac1a8102384c3836b230e58517e0d9f79ed6ef0e136f52f0ce
+size 5733024448

Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bd452523689a51c1ddb879686147597c123e20f11ffdd461e0c049a113f2ed
+size 5599331008

Llama-3-Groq-8B-Tool-Use-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990181f531fca400c5d5415c012b03ed6c8866806b49cfa1a4802c454cfd5720
+size 6596046720

Llama-3-Groq-8B-Tool-Use-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea26741c68aa8e45db1730de0faf2e089844b1dbf3bf401e019f1235c24af30
+size 8540823040

Llama-3-Groq-8B-Tool-Use-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46d1c03e57debeefacc648cc57496948b46d559352dd1ec95dc42f03ff82705
+size 16068989440

README.md

@@ -0,0 +1,130 @@
+---
+license: llama3
+model_name: Llama-3-Groq-8B-Tool-Use
+base_model: Groq/Llama-3-Groq-8B-Tool-Use
+model_creator: Groq
+inference: false
+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 -->
+
+# Llama-3-Groq-8B-Tool-Use-GGUF
+
+## Original Model
+
+[Groq/Llama-3-Groq-8B-Tool-Use](https://huggingface.co/Groq/Llama-3-Groq-8B-Tool-Use)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4)
+
+- Prompt template
+
+  - Prompt type: `groq-llama3-tool`
+
+  - Prompt string
+
+    ```text
+    <|start_header_id|>system<|end_header_id|>
+
+    You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+    <tool_call>
+    {"name": <function-name>,"arguments": <args-dict>}
+    </tool_call>
+    
+    Here are the available tools:
+    <tools> {
+      "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"
+        ]
+      }
+    }
+    {
+      "name": "predict_weather",
+      "description": "Predict the weather in 24 hours",
+      "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"
+        ]
+      }
+    } </tools><|eot_id|><|start_header_id|>user<|end_header_id|>
+    
+    What is the weather like in San Francisco in Celsius?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `8192`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template groq-llama3-tool \
+    --ctx-size 8192 \
+    --model-name Llama-3-Groq-8B
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3-Groq-8B-Tool-Use-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q2_K.gguf)       | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf)     | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf)     | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf)     | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Llama-3-Groq-8B-Tool-Use-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_0.gguf)       | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf)     | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf)     | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Llama-3-Groq-8B-Tool-Use-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_0.gguf)       | Q5_0   | 5 | 5.60 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf)     | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf)     | Q5_K_S | 5 | 5.60 GB| large, low quality loss - recommended |
+| [Llama-3-Groq-8B-Tool-Use-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q6_K.gguf)     | Q6_K   | 6 | 6.60 GB| very large, extremely low quality loss |
+| [Llama-3-Groq-8B-Tool-Use-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3-Groq-8B-Tool-Use-f16.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-f16.gguf)      | f16   | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b3405.*

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 128262
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"other","task":"text-generation"}