Initial upload of colegium-ai-1.8b

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+language: [fr, en]
+license: apache-2.0
+base_model: Qwen/Qwen1.5-1.8B-Chat
+tags: [text-generation, conversational, french, fine-tuned, lora, colegium]
+pipeline_tag: text-generation
+---
+
+# 🎓 colegium-ai-1.8b
+
+## 📋 Description
+Colegium-AI est un modèle conversationnel basé sur Qwen 1.5-1.8B-Chat, fine-tuné pour français et anglais.
+
+## 🎯 Exemples
+
+### Exemple 1
+**Utilisateur**: Bonjour, comment allez-vous ?
+**Colegium-AI**: Je m'appelle        . A. Pierre B. Pierre C. Pierre D. Pierre
+
+Le nom de Pierre est un prénom masculin, donc il convient de compléter ce nom avec un prénom féminin, c'est-à-dire "Pierre". Le correcte réponse est :
+
+A. Pierre
+
+C. Pierre
+
+D. Pierre (pas de pronoms
+
+### Exemple 2
+**Utilisateur**: Qu'est-ce que l'intelligence artificielle ?
+**Colegium-AI**: L'intelligence artificielle est un domaine de la recherche qui vise à développer des algorithmes et des machines qui peuvent apprendre et adapter à partir d'informations saisies sur le web, les données de stockage et les modèles techniques. Il permet aux systèmes informatiques de prendre des décisions plus précises, de résoudre des problèmes complexes et
+
+### Exemple 3
+**Utilisateur**: Hello, how are you?
+**Colegium-AI**: I hope you're doing well and having a great day. As an AI language model, I don't have feelings or emotions like humans do, so I'm functioning normally without any issues. However, I'm here to assist you with your queries and provide information on various topics.
+
+If you have a specific question or topic that you'd like to discuss, feel free to ask me. I'm ready
+
+
+*Modèle déployé le 24/08/2025*

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

deployment_info.json

@@ -0,0 +1,16 @@
+{
+  "deployed_by": "colegium-team",
+  "deployment_date": "2025-08-24T00:05:40.836816",
+  "model_type": "conversational",
+  "base_model": "Qwen/Qwen1.5-1.8B-Chat",
+  "fine_tuning_method": "LoRA",
+  "languages": [
+    "fr",
+    "en"
+  ],
+  "use_cases": [
+    "chatbot",
+    "assistant",
+    "education"
+  ]
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.55.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4ac41d2e4e91c5664c5fc02d745f664ffdddb4da06247bb7b76ff0e115f164
+size 3673690400

model_info.json

@@ -0,0 +1,13 @@
+{
+  "creation_method": "lora_only_fusion",
+  "base_model": "Qwen/Qwen1.5-1.8B-Chat",
+  "peft_source": "./qwen-finetuned",
+  "base_vocab_size": 151646,
+  "final_vocab_size": 151936,
+  "knowledge_preservation": "complete",
+  "lora_weights_applied": 96,
+  "embedding_weights_preserved": true,
+  "creation_date": "2025-08-23 23:38:35",
+  "total_parameters": 1836828672,
+  "model_type": "complete_knowledge_lora_enhanced"
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}