commit a2c9d4e37a1cc530bf62d94b3eefbf1380e31586 Author: ModelHub XC Date: Thu Oct 15 18:26:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Llama-3-8B-Japanese-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7566ae --- /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-3-8B-Japanese-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Japanese-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Japanese-Instruct-Q2_K.gguf b/Llama-3-8B-Japanese-Instruct-Q2_K.gguf new file mode 100644 index 0000000..6b07fa4 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d7a2c8d8397fc99ec2787a1cfd89ed0af2a32629d8a1ec22adee037183bf2a +size 3179131200 diff --git a/Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf b/Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..11f9d27 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9464fedd8de14d206159f9f75d663e9082053f28cd29afb43573a154062277b +size 4321956160 diff --git a/Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf b/Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..56ea3f7 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324a212a46a865ab7213a538d5f520b14e2c1206b8e98353bea1cff720316b51 +size 4018917696 diff --git a/Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf b/Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..7b7e11e --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28210653257d5c91cd719c24c1dfdc16f1d02f1e60c49923f7841bc664b8793d +size 3664499008 diff --git a/Llama-3-8B-Japanese-Instruct-Q4_0.gguf b/Llama-3-8B-Japanese-Instruct-Q4_0.gguf new file mode 100644 index 0000000..a0fc671 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a58b2a9dca819f4d7d89a9a165c96624181d77e70907f0bd3ad2ad9d09ee9549 +size 4661211456 diff --git a/Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf b/Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a69792c --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc90b857ed435c024727c3769af0ded2af6dc5bfe8d8b35f7805bd93677d4d42 +size 4920734016 diff --git a/Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf b/Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..775faa6 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c567802d8211e688de955872a588004d33fa6ac2bdeef804d7795e8cf170e5 +size 4692668736 diff --git a/Llama-3-8B-Japanese-Instruct-Q5_0.gguf b/Llama-3-8B-Japanese-Instruct-Q5_0.gguf new file mode 100644 index 0000000..d323085 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b54d6dc20113c895435ae78fefc7dce5152ffd9ed7b735ee316ea70f7ae2609 +size 5599293760 diff --git a/Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf b/Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..5af0ede --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a05cd11c8f83d01dc4dd3b3e74ef59246e6ccf33ad74c93c49af2e1036ad15a6 +size 5732987200 diff --git a/Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf b/Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..009b24a --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1288f669ad6d2e92cb6c415c793af3a126c9d374c9a07109f2a49865047202 +size 5599293760 diff --git a/Llama-3-8B-Japanese-Instruct-Q6_K.gguf b/Llama-3-8B-Japanese-Instruct-Q6_K.gguf new file mode 100644 index 0000000..a2a5a2e --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df04d491bc6c122f1008db150154ed19c341a6c7ef5b40a12848442e6afdf54b +size 6596006208 diff --git a/Llama-3-8B-Japanese-Instruct-Q8_0.gguf b/Llama-3-8B-Japanese-Instruct-Q8_0.gguf new file mode 100644 index 0000000..03f8bda --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ec4de1615dd67fe8899682219909e238f0f50792ff4f4ef57b0bf44d46ce24 +size 8540770624 diff --git a/Llama-3-8B-Japanese-Instruct-f16.gguf b/Llama-3-8B-Japanese-Instruct-f16.gguf new file mode 100644 index 0000000..7de4fb2 --- /dev/null +++ b/Llama-3-8B-Japanese-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e3f7710c4ec2bd62070695e88af2e2950c3db7fa5354a0eaf4e7e540d6cbbb +size 16068890912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a46c31b --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +license: other +license_name: llama3 +base_model: haqishen/Llama-3-8B-Japanese-Instruct +inference: false +model_creator: haqishen +model_type: llama +pipeline_tag: text-generation +quantized_by: Second State Inc. +language: +- en +- ja +--- + + + +
+ +
+
+ + +# Llama-3-8B-Japanese-Instruct-GGUF + +## Original Model + +[haqishen/Llama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-Instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.10.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.1) and above + +- Prompt template + + - Prompt type: `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|> + ``` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template llama-3-chat \ + --ctx-size 4096 \ + --model-name Llama-3-8B-Japanese-Instruct \ + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template llama-3-chat \ + --ctx-size 4096 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Llama-3-8B-Japanese-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes | +| [Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss | +| [Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss | +| [Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss | +| [Llama-3-8B-Japanese-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended | +| [Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss | +| [Llama-3-8B-Japanese-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended | +| [Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended | +| [Llama-3-8B-Japanese-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss | +| [Llama-3-8B-Japanese-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended | +| [Llama-3-8B-Japanese-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF/blob/main/Llama-3-8B-Japanese-Instruct-f16.gguf) | f16 | 16 | 16.1 GB| | + +*Quantized with llama.cpp b2824.* 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