second-state/SmolLM3-3B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: second-state/SmolLM3-3B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-07 19:01:18 +08:00
commit 97ee9b5065
16 changed files with 384 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
.gitattributes vendored Normal file
View File

@@ -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
SmolLM3-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
SmolLM3-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text

189
README.md Normal file
View File

@@ -0,0 +1,189 @@
---
base_model: HuggingFaceTB/SmolLM3-3B
license: apache-2.0
library_name: transformers
model_creator: HuggingFaceTB
model_name: SmolLM3-3B
quantized_by: Second State Inc.
language:
- en
- fr
- es
- it
- pt
- zh
- ar
- ru
---
<!-- 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 -->
# SmolLM3-3B-GGUF
## Original Model
[HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B)
## Run with LlamaEdge
- LlamaEdge version: [v0.24.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.24.0) and above
- Prompt template
- Normal chat
- Prompt type: `smol3-no-think`
- Prompt string
```text
<|im_start|>system
## Metadata
Knowledge Cutoff Date: June 2025
Today Date: 15 July 2025
Reasoning Mode: /no_think
## Custom Instructions
You are a helpful AI assistant named SmolLM, trained by Hugging Face.
<|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
```
- Chat with Tools
- Prompt type: `smol3-no-think`
- Prompt string
```text
<|im_start|>system
## Metadata
Knowledge Cutoff Date: June 2025
Today Date: 15 July 2025
Reasoning Mode: /no_think
## Custom Instructions
You are a helpful AI assistant named SmolLM, trained by Hugging Face.
### Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"name":"sum","description":"Calculate the sum of two numbers","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"a":{"description":"The left hand side number","format":"int32","type":"integer"},"b":{"description":"The right hand side number","format":"int32","type":"integer"}},"required":["a","b"],"title":"SumRequest","type":"object"}}
{"name":"sub","description":"Calculate the difference of two numbers","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"a":{"description":"The left hand side number","format":"int32","type":"integer"},"b":{"description":"The right hand side number","format":"int32","type":"integer"}},"required":["a","b"],"title":"SubRequest","type":"object"}}
{"name":"get_current_weather","description":"Get the weather for a given city","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","definitions":{"TemperatureUnit":{"enum":["celsius","fahrenheit"],"type":"string"}},"properties":{"location":{"description":"the city to get the weather for, e.g., 'Beijing', 'New York', 'Tokyo'","type":"string"},"unit":{"$ref":"#/definitions/TemperatureUnit","description":"the unit to use for the temperature, e.g., 'celsius', 'fahrenheit'"}},"required":["location","unit"],"title":"GetWeatherRequest","type":"object"}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
<|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` mode
- Prompt type: `smol3-think`
- Prompt string
```text
<|im_start|>system
/think
## Custom Instructions
{system_message}
<|im_end|>
<|im_start|>user
{user_message_1}
<|im_end|>
<|im_start|>assistant
<think>
{think content}
</think>
{assistant_message_1}
<|im_end|>
<|im_start|>user
{user_message_2}
<|im_end|>
<|im_start|>assistant
<think>
{think content}
</think>
{assistant_message_2}
<|im_end|> -->
```
- Context size: `128000`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM3-3B-Q5_K_M.gguf \
llama-api-server.wasm \
--model-name SmolLM3-3B \
--prompt-template smol3-no-think \
--ctx-size 128000
```
- Run as LlamaEdge command app
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM3-3B-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template smol3-no-think \
--ctx-size 128000
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [SmolLM3-3B-Q2_K.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q2_K.gguf) | Q2_K | 2 | 1.25 GB| smallest, significant quality loss - not recommended for most purposes |
| [SmolLM3-3B-Q3_K_L.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q3_K_L.gguf) | Q3_K_L | 3 | 1.69 GB| small, substantial quality loss |
| [SmolLM3-3B-Q3_K_M.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q3_K_M.gguf) | Q3_K_M | 3 | 1.57 GB| very small, high quality loss |
| [SmolLM3-3B-Q3_K_S.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.43 GB| very small, high quality loss |
| [SmolLM3-3B-Q4_0.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q4_0.gguf) | Q4_0 | 4 | 1.81 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [SmolLM3-3B-Q4_K_M.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q4_K_M.gguf) | Q4_K_M | 4 | 1.92 GB| medium, balanced quality - recommended |
| [SmolLM3-3B-Q4_K_S.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q4_K_S.gguf) | Q4_K_S | 4 | 1.82 GB| small, greater quality loss |
| [SmolLM3-3B-Q5_0.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q5_0.gguf) | Q5_0 | 5 | 2.16 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [SmolLM3-3B-Q5_K_M.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q5_K_M.gguf) | Q5_K_M | 5 | 2.21 GB| large, very low quality loss - recommended |
| [SmolLM3-3B-Q5_K_S.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q5_K_S.gguf) | Q5_K_S | 5 | 2.16 GB| large, low quality loss - recommended |
| [SmolLM3-3B-Q6_K.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q6_K.gguf) | Q6_K | 6 | 2.53 GB| very large, extremely low quality loss |
| [SmolLM3-3B-Q8_0.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-Q8_0.gguf) | Q8_0 | 8 | 3.28 GB| very large, extremely low quality loss - not recommended |
| [SmolLM3-3B-f16.gguf](https://huggingface.co/second-state/SmolLM3-3B-GGUF/blob/main/SmolLM3-3B-f16.gguf) | f16 | 16 | 6.16 GB| |
*Quantized with llama.cpp b5889*

3
SmolLM3-3B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd731a9146ea06d6ff81f407c34a13a38ef55c9a43bd4a50e31896b5666d97cd
size 1253301696

3
SmolLM3-3B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e9b92fc149a3f48152a082a8b0928f18149aab8c946d594fb46cd269ce5d0be
size 1690213824

3
SmolLM3-3B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a938969da291c0cad1aab210b905659ea279ed4cb7d56a02fc3ae32f55dd1313
size 1571069376

3
SmolLM3-3B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b2296dc172cc41145042a1c6317b36afa858d9de28f7937a5e53c670e0d1840
size 1432313280

3
SmolLM3-3B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf8242306ff85bf4c86d7f84e4cb11871beb17b2c1c27a79772dd2b8a2cd92c0
size 1805819328

3
SmolLM3-3B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a69ce14f4327d71da1d0654c92e6ff15c720a1236e3a8d43fc91d82ebfa9a1e
size 1915305408

3
SmolLM3-3B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b629fdece6893f7a504d455f1c9f04693adebb7489eb21fbb44970f3329869a
size 1817615808

3
SmolLM3-3B-Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4945a211d9dbc62d12891d2f897f383be683dd50a9f35b6581db68dcbf0c586d
size 2157354432

3
SmolLM3-3B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:185930ee1efe313b8f5d2fb8cd9d37071f147459fadac13f475cdc8c18fb0bf1
size 2213756352

3
SmolLM3-3B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f78567e01e602eb69231e9b80148161ba94894b8e3ec4061cc779543be3991e
size 2157354432

3
SmolLM3-3B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17b5a5055fb984979af858d013f86484529b4abd9aec0aa880cc0090f332219c
size 2530860480

3
SmolLM3-3B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c5f32c61ea29450085ba2f1d7ce3458d28956c33208c280656a5b32386ce14b1
size 3275574720

3
SmolLM3-3B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:621e8b953b22dd194f10d3fa2a41a6ea944867839c5d3be017d15549203dc70b
size 6158339520

108
config.json Normal file
View File

@@ -0,0 +1,108 @@
{
"architectures": [
"SmolLM3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128012,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 65536,
"max_window_layers": 28,
"mlp_bias": false,
"model_type": "smollm3",
"no_rope_layer_interval": 4,
"no_rope_layers": [
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0
],
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 4,
"pad_token_id": 128004,
"pretraining_tp": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000.0,
"sliding_window": null,
"torch_dtype": "bfloat16",
"transformers_version": "4.54.0.dev0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 128256
}