初始化项目，由ModelHub XC社区提供模型

Model: second-state/Llama-3.2-3B-Instruct-Uncensored-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-3.2-3B-Instruct-Uncensored-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Instruct-Uncensored-f16.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-3B-Instruct-Uncensored-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09e6abd3d776d40e9c44284027b11d60279aa0ee630875bda508100cfcc0331
+size 1493217408

Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe55926453ba6d5c33539e4174c074a2a93b6f842d95918dc7a7cfeb27aad64
+size 1984645248

Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7df6a19c6e986bbc0e558f48a8d087cd1138bc00d86b400730fd55d6f112860
+size 1856456832

Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e8c4295cd65836cc1e33241874e8f1484b021f182e52fa5507ada25c96f7c3
+size 1712146560

Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4291116615c270a73bf759006b7fed5afa3f65b59d24416dfb71220d3b1f5219
+size 2138816640

Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29036facdcef2e1dd6857c21e9393d3ed6d912a66eecec1056d085ab435f9f4f
+size 2241003648

Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e020d619d01a32da3485cfc3ede54044a64e3f917ae34beb816e9251b389b6
+size 2149826688

Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99d0421c8dccb1d810901f8355780352b8825328c6129c6840ab7f42ebce468
+size 2540388480

Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894c7e8b2bb279b35a4d948b21edd73b66273e8eb1718c1d357aca3d3431e25e
+size 2593030272

Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ed3cf59bfc39cbf080bdbd50b8d294b4e8f25b55086a541dcd901d3487a4f4
+size 2540388480

Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb811a9dfff2e5c3b1f5ffd1afda3b9f991ebc038e2e47fb8364ef778da7daa
+size 2967058560

Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828a4645d1c7bcd3c6d88b831368532120bf4747cc8d3f2a38048f4463944ec9
+size 3840526464

Llama-3.2-3B-Instruct-Uncensored-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86930d8ba4cfff1648b6a8c08291340687e715f5321c5025b17b1e642a12e33
+size 7221692544

README.md

@@ -0,0 +1,114 @@
+---
+base_model: thirdeyeai/Llama-3.2-3B-Instruct-Uncensored
+model_creator: thirdeyeai
+model_name: Llama-3.2-3B-Instruct-Uncensored
+quantized_by: Second State Inc.
+library_name: transformers
+---
+
+<!-- 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-3.2-3B-Instruct-Uncensored-GGUF
+
+## Original Model
+
+[thirdeyeai/Llama-3.2-3B-Instruct-Uncensored](https://huggingface.co/thirdeyeai/Llama-3.2-3B-Instruct-Uncensored)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8) 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-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf \
+        llama-api-server.wasm \
+        --prompt-template llama-3-chat \
+        --ctx-size 128000 \
+        --model-name Llama-3.2-3b
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf \
+        llama-api-server.wasm \
+        --prompt-template llama-3-tool \
+        --ctx-size 128000 \
+        --model-name Llama-3.2-3b
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Uncensored-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-3.2-3B-Instruct-Uncensored-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q2_K.gguf)     | Q2_K   | 2 | 1.49 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf) | Q3_K_L | 3 | 1.98 GB| small, substantial quality loss |
+| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf) | Q3_K_M | 3 | 1.86 GB| very small, high quality loss |
+| [Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf) | Q3_K_S | 3 | 1.71 GB| very small, high quality loss |
+| [Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf)     | Q4_0   | 4 | 2.14 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf) | Q4_K_M | 4 | 2.24 GB| medium, balanced quality - recommended |
+| [Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf) | Q4_K_S | 4 | 2.15 GB| small, greater quality loss |
+| [Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf)     | Q5_0   | 5 | 2.54 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf) | Q5_K_M | 5 | 2.59 GB| large, very low quality loss - recommended |
+| [Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf) | Q5_K_S | 5 | 2.54 GB| large, low quality loss - recommended |
+| [Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf)     | Q6_K   | 6 | 2.97 GB| very large, extremely low quality loss |
+| [Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf)     | Q8_0   | 8 | 3.84 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3.2-3B-Instruct-Uncensored-f16.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-Uncensored-f16.gguf)       | f16    | 16 | 7.22 GB| |
+
+*Quantized with llama.cpp b4681*

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}