初始化项目，由ModelHub XC社区提供模型

Model: second-state/Qwen3-1.7B-GGUF Source: Original Platform
2026-07-30 06:55:18 +08:00
commit 942aa1378a
16 changed files with 225 additions and 0 deletions
--- a/.gitattributes
+++ 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
+Qwen3-1.7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Qwen3-1.7B-Q2_K.gguf
+++ b/Qwen3-1.7B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38382cce3f3cc9d4db97bbe1c597436368ff05ee7bef0f201e3d5fbd89918fae
+size 879896672
--- a/Qwen3-1.7B-Q3_K_L.gguf
+++ b/Qwen3-1.7B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fed57ae82570773b0e7b9610e99789bca94f2383ef84106747c2b6f360a712
+size 1137205344
--- a/Qwen3-1.7B-Q3_K_M.gguf
+++ b/Qwen3-1.7B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c215e19773c035601cc93af2e866ae3f7599c17612de2cbdf24166fdccde37a3
+size 1073242208
--- a/Qwen3-1.7B-Q3_K_S.gguf
+++ b/Qwen3-1.7B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5bf4c3334fa3a0f6d4912c5ca50d6e82f3bdc5b9208a5875970b1e8a0407c4
+size 1000956000
--- a/Qwen3-1.7B-Q4_0.gguf
+++ b/Qwen3-1.7B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3b9a172e9ffc4d025711f84f383062580e0374dfc835d1b266130b69714012
+size 1229453408
--- a/Qwen3-1.7B-Q4_K_M.gguf
+++ b/Qwen3-1.7B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f6720f68f4a4567ebf7e3257041dd0b72077b518efe56890aec3516b59b9de
+size 1282439264
--- a/Qwen3-1.7B-Q4_K_S.gguf
+++ b/Qwen3-1.7B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfc502042ff4e7336b382c55d5d994f645cafae3932f7ab231df2f062a0ba51
+size 1235220576
--- a/Qwen3-1.7B-Q5_0.gguf
+++ b/Qwen3-1.7B-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e549c73e6b573aa5fdb274c39abee658dee95cb9e0ed0fd7f6ab090a1cdb1a
+size 1444509792
--- a/Qwen3-1.7B-Q5_K_M.gguf
+++ b/Qwen3-1.7B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f9995e9baee5766114a870a869c503018933e0e5c3468ad508fdaba7132a1a
+size 1471805536
--- a/Qwen3-1.7B-Q5_K_S.gguf
+++ b/Qwen3-1.7B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fc8715d71746f1105f080f4075ab2b1980c25f1c5c6210aee8b5b418c4a4f3
+size 1444509792
--- a/Qwen3-1.7B-Q6_K.gguf
+++ b/Qwen3-1.7B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fede2a47d0e40a1036215cd58820740e0134855fb24d1b1e8045de0d8d76cd7
+size 1673007200
--- a/Qwen3-1.7B-Q8_0.gguf
+++ b/Qwen3-1.7B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9860780f3a1fab1f8f909a1b549ea3e62c22d19ab1a492b3a1026b38c5bd3ec3
+size 2165039200
--- a/Qwen3-1.7B-f16.gguf
+++ b/Qwen3-1.7B-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c7818d605a034b984195092fe43763e7ecfed296999930128db6aadec7d27b
+size 4069679200
--- a/README.md
+++ b/README.md
@@ -0,0 +1,108 @@
+---
+base_model: Qwen/Qwen3-1.7B
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
+model_creator: Qwen
+model_name: Qwen3-1.7B
+quantized_by: Second State Inc.
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+
+<!-- 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 -->
+
+# Qwen3-1.7B-GGUF
+
+## Original Model
+
+[Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version:
+
+  - Thinking: [v0.17.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.17.0) and above
+  - No Thinking: [v0.18.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.2)
+
+- Prompt template
+
+  - Prompt type: `chatml` (for thinking)
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+  - Prompt type: `qwen3-no-think` (for no thinking)
+ 
+  - Prompt string
+ 
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {user_message_1}<|im_end|>
+    <|im_start|>assistant
+    {assistant_message_1}<|im_end|>
+    <|im_start|>user
+    {user_message_2}<|im_end|>
+    <|im_start|>assistant
+    <think>
+
+    </think>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-1.7B-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Qwen3-1.7B \
+    --prompt-template chatml \
+    --ctx-size 128000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-1.7B-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Qwen3-1.7B-Q2_K.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q2_K.gguf)     | Q2_K   | 2 | 880 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Qwen3-1.7B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q3_K_L.gguf) | Q3_K_L | 3 | 1.14 GB| small, substantial quality loss |
+| [Qwen3-1.7B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q3_K_M.gguf) | Q3_K_M | 3 | 1.07 GB| very small, high quality loss |
+| [Qwen3-1.7B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.00 GB| very small, high quality loss |
+| [Qwen3-1.7B-Q4_0.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q4_0.gguf)     | Q4_0   | 4 | 1.23 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Qwen3-1.7B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q4_K_M.gguf) | Q4_K_M | 4 | 1.28 GB| medium, balanced quality - recommended |
+| [Qwen3-1.7B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q4_K_S.gguf) | Q4_K_S | 4 | 1.24 GB| small, greater quality loss |
+| [Qwen3-1.7B-Q5_0.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q5_0.gguf)     | Q5_0   | 5 | 1.44 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Qwen3-1.7B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q5_K_M.gguf) | Q5_K_M | 5 | 1.47 GB| large, very low quality loss - recommended |
+| [Qwen3-1.7B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q5_K_S.gguf) | Q5_K_S | 5 | 1.44 GB| large, low quality loss - recommended |
+| [Qwen3-1.7B-Q6_K.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q6_K.gguf)     | Q6_K   | 6 | 1.67 GB| very large, extremely low quality loss |
+| [Qwen3-1.7B-Q8_0.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-Q8_0.gguf)     | Q8_0   | 8 | 2.17 GB| very large, extremely low quality loss - not recommended |
+| [Qwen3-1.7B-f16.gguf](https://huggingface.co/second-state/Qwen3-1.7B-GGUF/blob/main/Qwen3-1.7B-f16.gguf)       | f16    | 16 | 4.07 GB| |
+
+*Quantized with llama.cpp b5097*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}