初始化项目,由ModelHub XC社区提供模型
Model: gabriellarson/Anonymizer-4B-GGUF Source: Original Platform
This commit is contained in:
59
.gitattributes
vendored
Normal file
59
.gitattributes
vendored
Normal file
@@ -0,0 +1,59 @@
|
||||
*.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
|
||||
Anonymizer-4B-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Anonymizer-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Anonymizer-4B-F16.gguf
Normal file
3
Anonymizer-4B-F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69a62a2a65e2b340e6d26a862d8f3393830a037c76a4c39f48eb21b332d78c26
|
||||
size 8051284736
|
||||
3
Anonymizer-4B-IQ2_M.gguf
Normal file
3
Anonymizer-4B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:245e787dbe4abf7dda106b7077a9060cad177c7658805d4c3004a311e97d16df
|
||||
size 1512983520
|
||||
3
Anonymizer-4B-IQ2_S.gguf
Normal file
3
Anonymizer-4B-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6202de870169030990dea7fb1f1f4e8bd2993f8fc967e5c22511bce80b5f8427
|
||||
size 1417300960
|
||||
3
Anonymizer-4B-IQ2_XS.gguf
Normal file
3
Anonymizer-4B-IQ2_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc65ab4e706624aa9aec64619a7641c43b281b292b232c27a8f9851c43531722
|
||||
size 1354099680
|
||||
3
Anonymizer-4B-IQ2_XXS.gguf
Normal file
3
Anonymizer-4B-IQ2_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69d61b5a152d812e04faaa336b246543be2fd6e428243e7961c927fc8e0f08b8
|
||||
size 1246620640
|
||||
3
Anonymizer-4B-IQ3_M.gguf
Normal file
3
Anonymizer-4B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81c52490640eefc09127483940114b945836d4e2d0b719f998fda3a50313d835
|
||||
size 1962895840
|
||||
3
Anonymizer-4B-IQ3_S.gguf
Normal file
3
Anonymizer-4B-IQ3_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:510460ec401cddd315643957527bdb50ee56e5db07d3663820ed9d84dbeed0c3
|
||||
size 1899530720
|
||||
3
Anonymizer-4B-IQ3_XS.gguf
Normal file
3
Anonymizer-4B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3ed36ef71eb54030f4e8427c82b1ed7d59d4f4bb1ca00a1202e7287efa5174e
|
||||
size 1814374880
|
||||
3
Anonymizer-4B-IQ3_XXS.gguf
Normal file
3
Anonymizer-4B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c898ab5eb821cbc35025fe362f59d2a24337e4f0e9420c1fcd516c61b9cc8785
|
||||
size 1670188000
|
||||
3
Anonymizer-4B-IQ4_NL.gguf
Normal file
3
Anonymizer-4B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:463e75469695e2766389984ce3851ed2cebf2c5244e2eefb57cceb722f7bc5d3
|
||||
size 2381343200
|
||||
3
Anonymizer-4B-IQ4_XS.gguf
Normal file
3
Anonymizer-4B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9cbe486602dc1a789598c04201e121e22ef9fb34d1c75a0823af5baaf28c23ea
|
||||
size 2270751200
|
||||
3
Anonymizer-4B-Q2_K.gguf
Normal file
3
Anonymizer-4B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:683fd1495bb6d6927e6a7fd10d4eb89622eebc28f108263fa13cbd418715a495
|
||||
size 1669499360
|
||||
3
Anonymizer-4B-Q2_K_S.gguf
Normal file
3
Anonymizer-4B-Q2_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff892d940a1fd836ea656aeb2ea08e343e06d71c9c06c65823befc7655e51062
|
||||
size 1563453920
|
||||
3
Anonymizer-4B-Q3_K_L.gguf
Normal file
3
Anonymizer-4B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fd0f1a733709a23ef24d2baf420e486bcbf68aa3e303399ec4df3124a58fdcc1
|
||||
size 2239785440
|
||||
3
Anonymizer-4B-Q3_K_M.gguf
Normal file
3
Anonymizer-4B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09a6bf61ba88880ddc22fd2874e6fa9609fed083f96b60e5684c82b680fb2db9
|
||||
size 2075617760
|
||||
3
Anonymizer-4B-Q3_K_S.gguf
Normal file
3
Anonymizer-4B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f67b1cebe81dc8c4177cbb691edeb5d505e8c68a8f4f075e9e9a9eda683c79c
|
||||
size 1886996960
|
||||
3
Anonymizer-4B-Q4_0.gguf
Normal file
3
Anonymizer-4B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc37d194fb62c34d9554ab550a75a007a7b4e3a6feba4d589fd06eb9f8a32fe4
|
||||
size 2375772640
|
||||
3
Anonymizer-4B-Q4_K_M.gguf
Normal file
3
Anonymizer-4B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:32f26d37c110fdfd304169faeb17f5cb46b48675af8d9d5fd6e3af6850a9a3d1
|
||||
size 2497280480
|
||||
3
Anonymizer-4B-Q4_K_S.gguf
Normal file
3
Anonymizer-4B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:14f9f64f09800b122e497444284967e878548f96d14ce5a5444445fe47f52795
|
||||
size 2383309280
|
||||
3
Anonymizer-4B-Q5_0.gguf
Normal file
3
Anonymizer-4B-Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:070e5c77c3098804be82d093e151b603f44b0c16d4370401093dd7fc746a8877
|
||||
size 2829937120
|
||||
3
Anonymizer-4B-Q5_K_M.gguf
Normal file
3
Anonymizer-4B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1631e465b29ce11d4ddaddb53335f5f1d30943ebf0879f096f88f09683815575
|
||||
size 2889513440
|
||||
3
Anonymizer-4B-Q5_K_S.gguf
Normal file
3
Anonymizer-4B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e8959bc80e34ef2f74f70790a2c08a7ea9790d8572ae6938e1f097809f7a3ec
|
||||
size 2823711200
|
||||
3
Anonymizer-4B-Q6_K.gguf
Normal file
3
Anonymizer-4B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b98f06b8b70fd7e91b587997e7d1b417a77461ef1736328b20719926bdc956c
|
||||
size 3306260960
|
||||
3
Anonymizer-4B-Q8_0.gguf
Normal file
3
Anonymizer-4B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1eb0f5b98d979e2e1bb9329190abe289fb61beb762b258bd8b36f51d888d2dc6
|
||||
size 4280404960
|
||||
75
README.md
Normal file
75
README.md
Normal file
@@ -0,0 +1,75 @@
|
||||
---
|
||||
library_name: transformers
|
||||
base_model:
|
||||
- eternisai/Anonymizer-4B
|
||||
---
|
||||
# Model Card for eternisai/Anonymizer-4B
|
||||
SLMs for semantically similar replacement of PII to provide better end-user privacy.
|
||||
### Model description
|
||||
|
||||
The **Anonymizer-4B** is the strongest model in the Enchanted anonymizer series. Effectively matching GPT-4.1 while being thousands of times smaller.
|
||||
|
||||
It is the most accurate variant available and powers advanced anonymization in [Enchanted](http://link.freysa.ai/appstore).
|
||||
|
||||
## Intended use
|
||||
|
||||
* **Primary use**: High-accuracy anonymizer inside Enchanted.
|
||||
* **Secondary use**: Deployments where top-quality anonymization is critical (enterprise, research).
|
||||
|
||||
## Training details
|
||||
|
||||
* **Base**: Qwen3-4B.
|
||||
* **Data**: ~30k samples covering PII replacement + non-replacement categories.
|
||||
* **Method**: Supervised fine-tuning → GRPO with GPT-4.1 as judge.
|
||||
* **Score**: 9.55/10 on anonymization quality.
|
||||
* **Latency**: <250ms TTFT, <2s full completion (quantized).
|
||||
|
||||
## Limitations
|
||||
|
||||
* Largest model in the series, not suitable for mobile inference as of August 2025.
|
||||
* Requires MacBook-class hardware or above for real-time use.
|
||||
|
||||
## Usage example
|
||||
|
||||
```json
|
||||
<tool_call>
|
||||
{"name": "replace_entities", "arguments": {"replacements": [
|
||||
{"original": "Marc", "replacement": "Robert"},
|
||||
{"original": "cloud infrastructure", "replacement": "enterprise software"}
|
||||
]}}
|
||||
</tool_call>
|
||||
```
|
||||
|
||||
## Usage prompt template
|
||||
|
||||
The models expect input in this specific format:
|
||||
|
||||
```
|
||||
[BEGIN OF TASK INSTRUCTION]
|
||||
You are an anonymizer. Your task is to identify and replace personally identifiable information (PII) in the given text.
|
||||
Replace PII entities with semantically equivalent alternatives that preserve the context needed for a good response.
|
||||
If no PII is found or replacement is not needed, return an empty replacements list.
|
||||
REPLACEMENT RULES:
|
||||
• Personal names: Replace private or small-group individuals. Pick same culture + gender + era; keep surnames aligned across family members. DO NOT replace globally recognised public figures (heads of state, Nobel laureates, A-list entertainers, Fortune-500 CEOs, etc.).
|
||||
• Companies / organisations: Replace private, niche, employer & partner orgs. Invent a fictitious org in the same industry & size tier; keep legal suffix. Keep major public companies (anonymity set ≥ 1,000,000).
|
||||
• Projects / codenames / internal tools: Always replace with a neutral two-word alias of similar length.
|
||||
• Locations: Replace street addresses, buildings, villages & towns < 100k pop with a same-level synthetic location inside the same state/country. Keep big cities (≥ 1M), states, provinces, countries, iconic landmarks.
|
||||
• Dates & times: Replace birthdays, meeting invites, exact timestamps. Shift day/month by small amounts while KEEPING THE SAME YEAR to maintain temporal context. DO NOT shift public holidays or famous historic dates ("July 4 1776", "Christmas Day", "9/11/2001", etc.). Keep years, fiscal quarters, decade references unchanged.
|
||||
• Identifiers: (emails, phone #s, IDs, URLs, account #s) Always replace with format-valid dummies; keep domain class (.com big-tech, .edu, .gov).
|
||||
• Monetary values: Replace personal income, invoices, bids by × [0.8 – 1.25] to keep order-of-magnitude. Keep public list prices & market caps.
|
||||
• Quotes / text snippets: If the quote contains PII, swap only the embedded tokens; keep the rest verbatim.
|
||||
[END OF TASK INSTRUCTION]
|
||||
[BEGIN OF AVAILABLE TOOLS]
|
||||
[{"type": "function", "function": {"name": "replace_entities", "description": "Replace PII entities with anonymized versions", "parameters": {"type": "object", "properties": {"replacements": {"type": "array", "items": {"type": "object", "properties": {"original": {"type": "string"}, "replacement": {"type": "string"}}, "required": ["original", "replacement"]}}}, "required": ["replacements"]}}}]
|
||||
[END OF AVAILABLE TOOLS]
|
||||
[BEGIN OF FORMAT INSTRUCTION]
|
||||
Use the replace_entities tool to specify replacements. Your response must use the tool call wrapper format:
|
||||
<|tool_call|>{"name": "replace_entities", "arguments": {"replacements": [{"original": "PII_TEXT", "replacement": "ANONYMIZED_TEXT"}, ...]}}</|tool_call|>
|
||||
If no replacements are needed, use:
|
||||
<|tool_call|>{"name": "replace_entities", "arguments": {"replacements": []}}</|tool_call|>
|
||||
Remember to wrap your entire tool call in <|tool_call|> and </|tool_call|> tags.
|
||||
[END OF FORMAT INSTRUCTION]
|
||||
[BEGIN OF QUERY]
|
||||
Your text to anonymize goes here
|
||||
[END OF QUERY]
|
||||
```
|
||||
Reference in New Issue
Block a user