Add model and tokenizer files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>NOTUSED": 32005
+}

config.json

@@ -1,54 +1,28 @@
-import numpy as np
-import scipy.stats as stats
-import matplotlib.pyplot as plt
-import seaborn as sns
-import pandas as pd
-
-# Generate some synthetic data
-np.random.seed(42)
-
-data = np.random.normal(loc=0, scale=1, size=1000)
-
-"""
-df = pd.read_csv("es.csv")
-futures_data = df
-futures_data['Log_Returns'] = np.log(futures_data['Adj Close'] / futures_data['Adj Close'].shift(1)).dropna()
-futures_data = futures_data.dropna()
-futures_data['Log_Returns'] = futures_data['Log_Returns']/futures_data['Log_Returns'].expanding().std()
-futures_data = futures_data.dropna()
-data = futures_data['Log_Returns']
-"""
-
-# Skewness and Kurtosis
-skewness = stats.skew(data)
-kurtosis = stats.kurtosis(data) + 3  # Adjust for excess kurtosis
-print(f"Skewness: {skewness}")
-print(f"Kurtosis: {kurtosis}")
-
-# Kolmogorov-Smirnov Test
-ks_stat, ks_p_value = stats.kstest(data, 'norm', args=(data.mean(), data.std()))
-print(f"Kolmogorov-Smirnov test statistic: {ks_stat}")
-print(f"Kolmogorov-Smirnov test p-value: {ks_p_value}")
-
-# Shapiro-Wilk Test
-sw_stat, sw_p_value = stats.shapiro(data)
-print(f"Shapiro-Wilk test statistic: {sw_stat}")
-print(f"Shapiro-Wilk test p-value: {sw_p_value}")
-
-# Anderson-Darling Test
-ad_result = stats.anderson(data, dist='norm')
-print(f"Anderson-Darling test statistic: {ad_result.statistic}")
-print(f"Anderson-Darling critical values: {ad_result.critical_values}")
-print(f"Anderson-Darling significance levels: {ad_result.significance_level}")
-
-# Q-Q Plot
-plt.figure(figsize=(8, 6))
-stats.probplot(data, dist="norm", plot=plt)
-plt.title("Q-Q Plot")
-plt.show()
-
-# Histogram with KDE
-plt.figure(figsize=(8, 6))
-sns.histplot(data, kde=True)
-plt.title("Histogram with KDE")
-plt.show()
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207956d66df0dbd9ffa23821fdffa8b4e6d78163a49adc4f0a3c848175b75e03
+size 442510176

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}