From 7201fd422e7d9b739f7e4d05fa9dfbb47cd1cc8a Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Sat, 8 Feb 2025 16:17:33 +0800 Subject: [PATCH] Update README.md --- Llama-3.2-1B-Instruct-Q2_K.gguf | 2 +- Llama-3.2-1B-Instruct-Q3_K_L.gguf | 2 +- Llama-3.2-1B-Instruct-Q3_K_M.gguf | 2 +- Llama-3.2-1B-Instruct-Q3_K_S.gguf | 2 +- Llama-3.2-1B-Instruct-Q4_0.gguf | 2 +- Llama-3.2-1B-Instruct-Q4_K_M.gguf | 2 +- Llama-3.2-1B-Instruct-Q4_K_S.gguf | 2 +- Llama-3.2-1B-Instruct-Q5_0.gguf | 2 +- Llama-3.2-1B-Instruct-Q5_K_M.gguf | 2 +- Llama-3.2-1B-Instruct-Q5_K_S.gguf | 2 +- Llama-3.2-1B-Instruct-Q6_K.gguf | 2 +- Llama-3.2-1B-Instruct-Q8_0.gguf | 2 +- README.md | 198 +++++++++++++++--------------- 13 files changed, 111 insertions(+), 111 deletions(-) diff --git a/Llama-3.2-1B-Instruct-Q2_K.gguf b/Llama-3.2-1B-Instruct-Q2_K.gguf index 48146d6..809ef73 100644 --- a/Llama-3.2-1B-Instruct-Q2_K.gguf +++ b/Llama-3.2-1B-Instruct-Q2_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7cbccffcba1e679d2fb906a55b5d6d641aa21bff9ee20fe30cef6dd6b9f8e410 +oid sha256:a870730e0fff8e6c4656e4f611faa16bde7b16f33c059292167a174bf15e5b2e size 580874080 diff --git a/Llama-3.2-1B-Instruct-Q3_K_L.gguf b/Llama-3.2-1B-Instruct-Q3_K_L.gguf index 8ed6e18..c2e5b89 100644 --- a/Llama-3.2-1B-Instruct-Q3_K_L.gguf +++ b/Llama-3.2-1B-Instruct-Q3_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e89a46e80c150f92bc0d5dfacb069f46770807664340339a22d886031ee06ddc +oid sha256:ef44bca078435843c7788f9c03e7b495a099c131f845ed19dc0257e561e8caf3 size 732524384 diff --git a/Llama-3.2-1B-Instruct-Q3_K_M.gguf b/Llama-3.2-1B-Instruct-Q3_K_M.gguf index 9ed912c..fe41c9f 100644 --- a/Llama-3.2-1B-Instruct-Q3_K_M.gguf +++ b/Llama-3.2-1B-Instruct-Q3_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9bdd2550b78bdee5653da8f9d07d74faaafd7cc50602eac9107d8f2c60677d24 +oid sha256:7b36f7efe910829de87ab1fcd9a55fdb0bf481d8e158345b13dc48486a324a79 size 690843488 diff --git a/Llama-3.2-1B-Instruct-Q3_K_S.gguf b/Llama-3.2-1B-Instruct-Q3_K_S.gguf index dd8a14d..ddc7768 100644 --- a/Llama-3.2-1B-Instruct-Q3_K_S.gguf +++ b/Llama-3.2-1B-Instruct-Q3_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf5363d4847936b37950b1d048199b616b80edd40e78ed15e7b0f2e36c32433b +oid sha256:1444f1e3d528823058010ea5152b8f32a332f9bce37290d480c4d4e50b04eb41 size 641691488 diff --git a/Llama-3.2-1B-Instruct-Q4_0.gguf b/Llama-3.2-1B-Instruct-Q4_0.gguf index 22e55ae..6fd5abc 100644 --- a/Llama-3.2-1B-Instruct-Q4_0.gguf +++ b/Llama-3.2-1B-Instruct-Q4_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:150e95f201edeaef9b5d37aec70fcee65533ddeca51a4d1092037195f0302f69 +oid sha256:eadfd8fd4e29d48e720eb87fc8242d3a8d4d2dacd52c722adc8e69e48c668efc size 770928480 diff --git a/Llama-3.2-1B-Instruct-Q4_K_M.gguf b/Llama-3.2-1B-Instruct-Q4_K_M.gguf index eb8accb..7346a0a 100644 --- a/Llama-3.2-1B-Instruct-Q4_K_M.gguf +++ b/Llama-3.2-1B-Instruct-Q4_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e95df2f5144fd67bf11421ad59812fbde45a79c90eb49cb5d79e3d7bddaa1331 +oid sha256:26bac8efd811cb41a80db4393dbe5c8360abd54b98954ec766aa4ba7dacc0bc5 size 807694176 diff --git a/Llama-3.2-1B-Instruct-Q4_K_S.gguf b/Llama-3.2-1B-Instruct-Q4_K_S.gguf index c63fc51..a7bbc7e 100644 --- a/Llama-3.2-1B-Instruct-Q4_K_S.gguf +++ b/Llama-3.2-1B-Instruct-Q4_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e256d51eed0799552f91a4fb8f0d05315b3e3dc1cd4499514e7d87a845951c88 +oid sha256:5550376826ef08901a4145559647844d5e70a950d69145e83ae2d262ce5ce0e2 size 775647072 diff --git a/Llama-3.2-1B-Instruct-Q5_0.gguf b/Llama-3.2-1B-Instruct-Q5_0.gguf index 035e17f..115f1ce 100644 --- a/Llama-3.2-1B-Instruct-Q5_0.gguf +++ b/Llama-3.2-1B-Instruct-Q5_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:922306ce6b89b731d20130c2a5e909be530c5703fd24b26f7d050bad3faf3fc5 +oid sha256:f6aea9bca54d1b5033035771963e0bf24d307ff756ab476744a2b43ad2eeb68d size 892563296 diff --git a/Llama-3.2-1B-Instruct-Q5_K_M.gguf b/Llama-3.2-1B-Instruct-Q5_K_M.gguf index f3d855b..0cdf92e 100644 --- a/Llama-3.2-1B-Instruct-Q5_K_M.gguf +++ b/Llama-3.2-1B-Instruct-Q5_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7cd16584b15af8c268ca60454b63b5021b0b2c7edf66cff2b41210a333b2233d +oid sha256:7f5165ccccbd6953de2a35ca56300ebedfb70739a407dd096e3a5c658477aefa size 911503200 diff --git a/Llama-3.2-1B-Instruct-Q5_K_S.gguf b/Llama-3.2-1B-Instruct-Q5_K_S.gguf index 49de768..16b1e16 100644 --- a/Llama-3.2-1B-Instruct-Q5_K_S.gguf +++ b/Llama-3.2-1B-Instruct-Q5_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:66260aca245c04327590457d52debf378e0fc93b881b2effb71f9a00703a1953 +oid sha256:a14d69cc881f282405b8ba59ab6377a3eb7f2c3686077d1be796c87f6298c398 size 892563296 diff --git a/Llama-3.2-1B-Instruct-Q6_K.gguf b/Llama-3.2-1B-Instruct-Q6_K.gguf index beb192e..bbcf237 100644 --- a/Llama-3.2-1B-Instruct-Q6_K.gguf +++ b/Llama-3.2-1B-Instruct-Q6_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3fe00ecc20650188a714bf1766cecbd938e6119e9311c8fe91ca3fb5f3246591 +oid sha256:4bf385159856b7c50a938b1228112318d9f99238a76880ea0f6381ab879982b3 size 1021800288 diff --git a/Llama-3.2-1B-Instruct-Q8_0.gguf b/Llama-3.2-1B-Instruct-Q8_0.gguf index af0415b..eb864aa 100644 --- a/Llama-3.2-1B-Instruct-Q8_0.gguf +++ b/Llama-3.2-1B-Instruct-Q8_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6c0522ea0da43f9a089b5f2df7699a659cc320a5259c33506c44925fa03232fc +oid sha256:da49f51ced8c15546e7779beb677fb53eb5d0b3b38ac4607ac60d58d77074823 size 1321082720 diff --git a/README.md b/README.md index e6f0488..9da1d5c 100644 --- a/README.md +++ b/README.md @@ -1,99 +1,99 @@ ---- -base_model: meta-llama/Llama-3.2-1B-Instruct -license: llama3.2 -model_creator: meta -model_name: Llama-3.2-1B-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-3.2-1B-Instruct-GGUF - -## Original Model - -[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) - -## Run with LlamaEdge - -- LlamaEdge version: [v0.14.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.5) 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: `128000` - -- Run as LlamaEdge service - - ```bash - wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-Instruct-Q5_K_M.gguf \ - llama-api-server.wasm \ - --prompt-template llama-3-chat \ - --ctx-size 128000 \ - --model-name Llama-3.2-1b - ``` - -- Run as LlamaEdge command app - - ```bash - wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-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-3.2-1B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q2_K.gguf) | Q2_K | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes | -| [Llama-3.2-1B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss | -| [Llama-3.2-1B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss | -| [Llama-3.2-1B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss | -| [Llama-3.2-1B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M | -| [Llama-3.2-1B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended | -| [Llama-3.2-1B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss | -| [Llama-3.2-1B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M | -| [Llama-3.2-1B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended | -| [Llama-3.2-1B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended | -| [Llama-3.2-1B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.02 GB| very large, extremely low quality loss | -| [Llama-3.2-1B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| very large, extremely low quality loss - not recommended | -| [Llama-3.2-1B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-f16.gguf) | f16 | 16 | 2.48 GB| | - -*Quantized with llama.cpp b3807* +--- +base_model: meta-llama/Llama-3.2-1B-Instruct +license: llama3.2 +model_creator: meta +model_name: Llama-3.2-1B-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-3.2-1B-Instruct-GGUF + +## Original Model + +[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-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: `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: `128000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template llama-3-chat \ + --ctx-size 128000 \ + --model-name Llama-3.2-1b + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-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-3.2-1B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q2_K.gguf) | Q2_K | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes | +| [Llama-3.2-1B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss | +| [Llama-3.2-1B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss | +| [Llama-3.2-1B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss | +| [Llama-3.2-1B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Llama-3.2-1B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended | +| [Llama-3.2-1B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss | +| [Llama-3.2-1B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Llama-3.2-1B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended | +| [Llama-3.2-1B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended | +| [Llama-3.2-1B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.02 GB| very large, extremely low quality loss | +| [Llama-3.2-1B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.32 GB| very large, extremely low quality loss - not recommended | +| [Llama-3.2-1B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-f16.gguf) | f16 | 16 | 2.48 GB| | + +*Quantized with llama.cpp b4466*