commit f979da2aa2fff2e6f39252ca40b0b40a2b1c2df0 Author: ModelHub XC Date: Thu Oct 8 11:41:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Llama-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d378c2 --- /dev/null +++ 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 +Llama-3.2-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-Q2_K.gguf b/Llama-3.2-3B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..d43c602 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dabdba85d46f31b464a0fded5631c5bddec151caefb45dd8f4894e477c41897 +size 1363935520 diff --git a/Llama-3.2-3B-Instruct-Q3_K_L.gguf b/Llama-3.2-3B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..0feb274 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d59b635b58cc4ce331a86aa197624837af97b40d26c22c284358cd8de1cd9f +size 1815347488 diff --git a/Llama-3.2-3B-Instruct-Q3_K_M.gguf b/Llama-3.2-3B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..88a061a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a27af779dabc1480470b8950e5d6d060957f4fe8df165863981d5fe77be4da +size 1687159072 diff --git a/Llama-3.2-3B-Instruct-Q3_K_S.gguf b/Llama-3.2-3B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..3b8e8b9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8434d06c50ff5c8113fefbd0e275d8879ac15ec29c5330d3fee61b295a3490f4 +size 1542848800 diff --git a/Llama-3.2-3B-Instruct-Q4_0.gguf b/Llama-3.2-3B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..5cefed3 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc8df7386113cadf7f592fcf4a25cf9ac46083ee44b521132b4448261031d99 +size 1917190432 diff --git a/Llama-3.2-3B-Instruct-Q4_K_M.gguf b/Llama-3.2-3B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a4d0913 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e6cf2c071a429e2380d2d1182c06a20b8c999d0c059636530e4a84beb8e8d4 +size 2019377440 diff --git a/Llama-3.2-3B-Instruct-Q4_K_S.gguf b/Llama-3.2-3B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..75a5002 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9054a2b99ae8e37d70b484dccde32b2eedc5d9510330d1d05a3ff90147a24ec7 +size 1928200480 diff --git a/Llama-3.2-3B-Instruct-Q5_0.gguf b/Llama-3.2-3B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..6aedb6a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae5f5bfd45f7516e8253d78f300c3e4be328291ca3e0eb3b5bf7b8d867ab740 +size 2269511968 diff --git a/Llama-3.2-3B-Instruct-Q5_K_M.gguf b/Llama-3.2-3B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..da6de4e --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02e674781b7e2fe80318de645397f957f7b768e86edb42bd9fa0a120578855b +size 2322153760 diff --git a/Llama-3.2-3B-Instruct-Q5_K_S.gguf b/Llama-3.2-3B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..5ff7087 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b73a5b64fda6f297cc6e031a0b5055b8ef4ed9e09a90d9599150a247cf4b1e +size 2269511968 diff --git a/Llama-3.2-3B-Instruct-Q6_K.gguf b/Llama-3.2-3B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..25f60f0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c797166082bed6c67fcc8d5d745eb9b4f23455dd35f0d4b0fbb88b04b33e7b +size 2643853600 diff --git a/Llama-3.2-3B-Instruct-Q8_0.gguf b/Llama-3.2-3B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..663296f --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b690c2640b7c36e2ccb9305a858f8a95d804711e3f90743d646e1808949e1f +size 3421899040 diff --git a/Llama-3.2-3B-Instruct-f16.gguf b/Llama-3.2-3B-Instruct-f16.gguf new file mode 100644 index 0000000..f353ff1 --- /dev/null +++ b/Llama-3.2-3B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ebe8fbb5ab5f05aaa056948668c5f7443df9d0883497f1d9c05f57fb8ea6cd +size 6433687840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..755325f --- /dev/null +++ b/README.md @@ -0,0 +1,129 @@ +--- +base_model: meta-llama/Llama-3.2-3B-Instruct +license: llama3.2 +model_creator: meta +model_name: Llama-3.2-3B-Instruct +quantized_by: Second State Inc. +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +library_name: transformers +pipeline_tag: text-generation +tags: +- chat +- llama +- llama-3 +--- + + + +
+ +
+
+ + +# Llama-3.2-3B-Instruct-GGUF + +## Original Model + +[meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-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-3.2-3B-Instruct-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-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-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-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q2_K.gguf) | Q2_K | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes | +| [Llama-3.2-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss | +| [Llama-3.2-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss | +| [Llama-3.2-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss | +| [Llama-3.2-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Llama-3.2-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended | +| [Llama-3.2-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss | +| [Llama-3.2-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Llama-3.2-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended | +| [Llama-3.2-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended | +| [Llama-3.2-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.02 GB| very large, extremely low quality loss | +| [Llama-3.2-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| very large, extremely low quality loss - not recommended | +| [Llama-3.2-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-3B-Instruct-GGUF/blob/main/Llama-3.2-3B-Instruct-f16.gguf) | f16 | 16 | 2.48 GB| | + +*Quantized with llama.cpp b4466* diff --git a/config.json b/config.json new file mode 100644 index 0000000..a5a40fa --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "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": "4.45.0.dev0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file