Update README.md

2025-02-08 16:17:33 +08:00
parent 6dca1fd81a
commit 7201fd422e
13 changed files with 111 additions and 111 deletions
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
--- 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
---
-
-<!-- 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-3.2-1B-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
+---
+
+<!-- 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-3.2-1B-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*