Add SetFit model

README.md

@@ -10,23 +10,18 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator)
-    key is generated and stored as a 128-bit value through an entropy source meeting
-    the security strength needed for random number generation, specifically ANS X9.31
-    compliant.
-- text: The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator)
-    key is statically stored and hardcoded into the code as a seed value, which is
-    then used to initialize the PRNG (Pseudorandom Number Generator).
-- text: The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator)
-    key is generated and stored within the device's firmware or software at manufacturing
-    time as part of the CSP injection process.
-- text: The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator)
-    key is internally generated and never exits the module, meaning it is not explicitly
-    stored, created, or compiled as it exists solely within the volatile memory of
-    the system.
-- text: The PRNG (Pseudorandom Number Generator) key or DRBG (Deterministic Random
-    Bit Generator) key is generated and stored securely in a private key portion of
-    an ANSI X9.31-compliant format within non-volatile random access memory (NVRAM).
+- text: All critical security parameters are injected into the system during production.
+- text: A 256-bit seed key for the ANSI X9.31 RNG function using AES-256 is stored
+    in plaintext in RAM, generated securely at the factory, and embedded in flash
+    memory.
+- text: Random number generator obtains its seed key by reading bytes from the /dev/urandom
+    device. The seed key is stored in SDRAM in plaintext while in use and is deleted
+    from memory on power-down, reboot, or any command that is followed by a reboot,
+    such as switching between non-approved and approved modes, zeroization, restore
+    factory settings, and reset shared key.
+- text: X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.
+- text: 'X Seed Key for RNG: Seed created by NDRNG and used as the Triple DES key
+    in the ANSI X9.31 RNG.'
 inference: true
 ---
 
@@ -58,10 +53,10 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label    | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
-|:---------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| negative | <ul><li>"The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator) key is generated by calling `get_random_bytes()` to obtain bits from the Linux kernel's hardware-based non-deterministic random number generator and then used as input for AES 128 encryption, without being explicitly stored."</li><li>'The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator) key is obtained by reading bytes from the /dev/urandom device and then temporarily stored in plaintext SDRAM while in use before being deleted on power-down, reboot, or certain commands that require a restart.'</li><li>'The ANSI X9.31 PRNG (Pseudorandom Number Generator) key, also known as the DRBG (Deterministic Random Bit Generator) key, is generated internally by the kernel and not explicitly stored, created, or compiled, but rather used directly to produce random numbers for cryptographic purposes.'</li></ul> |
-| positive | <ul><li>'In an ANSI X9.31-compliant PRNG, the private key (RNG key or DRBG key) is generated and stored securely in Non-Volatile Random Access Memory (NVRAM).'</li><li>'The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator) key is generated and permanently stored in read-only memory (FLASH) within the factory environment using hardware-based random number generation embedded in FLASH.'</li><li>'The RNG (DRBG) key is not explicitly mentioned as being stored, but its internal state value is persisted in Non-Volatile Random Access Memory (NVRAM), implying that the key is implicitly tied to this persistent state and does not have an independent storage mechanism.'</li></ul>                                                                                                                                                                                                                               |
+| Label    | Examples                                                                                                                                                                                                                                                                                                       |
+|:---------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| positive | <ul><li>'The private key component of an ANSI X9.31-compliant PRNG is stored securely in NVRAM.'</li><li>'It is generated in the factory (a secure environment) using the hardware RNG Embedded in FLASH.'</li><li>'The internal DRBG state value of the RNG is stored in NVRAM for persistent use.'</li></ul> |
+| negative | <ul><li>'The NDRNG is used to generate seed & seed key values to feed the DRNG.'</li><li>'module stores RNG and DRBG state values only in RAM.'</li><li>'PRNG Seed Key A new ANSI X9.31 RNG Seed Key is generated from a block of 160 bits output by the random noise source software library.'</li></ul>      |
 
 ## Uses
 
@@ -81,7 +76,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("yasirdemircan/setfit_rng_v6")
 # Run inference
-preds = model("The RNG (Random Number Generator) key or DRBG (Deterministic Random Bit Generator) key is generated and stored within the device's firmware or software at manufacturing time as part of the CSP injection process.")
+preds = model("X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.")
 ```
 
 <!--
@@ -113,12 +108,12 @@ preds = model("The RNG (Random Number Generator) key or DRBG (Deterministic Rand
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 24  | 36.8444 | 52  |
+| Word count   | 6   | 18.8889 | 49  |
 
 | Label    | Training Sample Count |
 |:---------|:----------------------|
-| negative | 22                    |
-| positive | 23                    |
+| negative | 23                    |
+| positive | 22                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
@@ -141,22 +136,22 @@ preds = model("The RNG (Random Number Generator) key or DRBG (Deterministic Rand
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0294 | 1    | 0.2664        | -               |
-| 1.0    | 34   | -             | 0.2420          |
-| 1.4706 | 50   | 0.1035        | -               |
-| 2.0    | 68   | -             | 0.2950          |
-| 2.9412 | 100  | 0.0005        | -               |
-| 3.0    | 102  | -             | 0.2981          |
-| 4.0    | 136  | -             | 0.3001          |
+| 0.0294 | 1    | 0.2114        | -               |
+| 1.0    | 34   | -             | 0.0933          |
+| 1.4706 | 50   | 0.1015        | -               |
+| 2.0    | 68   | -             | 0.0967          |
+| 2.9412 | 100  | 0.0008        | -               |
+| 3.0    | 102  | -             | 0.1039          |
+| 4.0    | 136  | -             | 0.1055          |
 
 ### Framework Versions
-- Python: 3.10.15
-- SetFit: 1.2.0.dev0
+- Python: 3.10.16
+- SetFit: 1.1.1
 - Sentence Transformers: 3.3.1
 - Transformers: 4.45.2
 - PyTorch: 2.5.1+cu124
-- Datasets: 2.19.1
-- Tokenizers: 0.20.1
+- Datasets: 3.2.0
+- Tokenizers: 0.20.3
 
 ## Citation
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:444c3024db43fa64a870a60c9e67e0d62aec4a4ad65b13264cb2a3629d25ae32
+oid sha256:1f058ec2c1d2d43a342fc1c60c02d74b2845087ac2241126fb76c829ccb915cd
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2baa2f55c86e3f01e9b3e7b3383e6c38eed55769939aefd4166b97f5ef837310
+oid sha256:cf973fb4d9bd207eeee8c3ccaf480dbb105f17f6c26419e866dbe2919e723441
 size 7055