初始化项目,由ModelHub XC社区提供模型
Model: Clem27-Assistants/Learnia-Empathic-Tchat Source: Original Platform
This commit is contained in:
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.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
|
||||||
15
LICENSE
Normal file
15
LICENSE
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
**🌼 LEARNIA OPEN-OLL license🌼**
|
||||||
|
|
||||||
|
Learnia et toutes ses versions sont distribué sous ses termes Open-oll.
|
||||||
|
merci de respecter les conditions d'utilisation ci dessous.
|
||||||
|
|
||||||
|
1) Vous n'avez pas le droit de vous proclamer propriétaire du modèle original learnia.
|
||||||
|
|
||||||
|
2) Vous devez toujours citer la source de l'original,
|
||||||
|
pour vos versions modifié et utilisation
|
||||||
|
(LLM-CLEM)
|
||||||
|
|
||||||
|
3) vous avez l'autorisation d'utiliser vos versions dérivés pour usages commerciaux,
|
||||||
|
mais elles doivent être assez différente du modèle de base ou des versions originales distribués par LLm-Clem.
|
||||||
|
|
||||||
|
4) gardez une copie de Open-oll dans le dépôt de votre version.
|
||||||
83
README.md
Normal file
83
README.md
Normal file
@@ -0,0 +1,83 @@
|
|||||||
|
---
|
||||||
|
base_model: Finisha-F-scratch/Learnia
|
||||||
|
library_name: transformers
|
||||||
|
model_name: Learnia-Empathic-Tchat
|
||||||
|
tags:
|
||||||
|
- Instruct
|
||||||
|
- Assistant
|
||||||
|
- love
|
||||||
|
- Empathic
|
||||||
|
licence: license
|
||||||
|
license: other
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
# 🧠 Learnia-Empathic-Tchat
|
||||||
|
|
||||||
|

|
||||||
|
|
||||||
|
Learnia-Empathic-Tchat est un Small Language Model (SLM) de 51.6M de paramètres, affiné par SFT (Supervised Fine-Tuning) pour devenir un assistant spécialisé dans le dialogue émotionnel et relationnel. Basé sur l'architecture Learnia, ce modèle prouve qu'une petite taille peut offrir une profondeur de compréhension étonnante lorsqu'elle est couplée à un dataset ultra-spécialisé.
|
||||||
|
|
||||||
|
# 🌟 Points Forts
|
||||||
|
* Ultra-Léger : 51.6M de paramètres pour une exécution fluide sur n'importe quel CPU ou GPU virtuel.
|
||||||
|
* Spécialisation Émotionnelle : Entraîné sur 10 000 dialogues ciblant la résolution de conflits, la tristesse, la trahison et la gestion du stress relationnel.
|
||||||
|
* Format Chat-Ready : Utilise un template de chat standard pour une intégration immédiate dans des applications de messagerie.
|
||||||
|
|
||||||
|
# 📊 Fiche Technique
|
||||||
|
| Caractéristique | Détail |
|
||||||
|
|---|---|
|
||||||
|
| Base | Learnia (Foundation) |
|
||||||
|
| Paramètres | 51.6 Millions |
|
||||||
|
| Méthode | Fine-tuning SFT (Instruct) |
|
||||||
|
| Dataset | 10k dialogues |
|
||||||
|
| Format | Hugging Face Transformers |
|
||||||
|
|
||||||
|
# 🚀 Utilisation (Inférence)
|
||||||
|
Pour discuter avec Learnia-Empathic-Tchat, tu peux utiliser le code suivant via la bibliothèque transformers :
|
||||||
|
|
||||||
|
```
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
|
||||||
|
# Chargement du modèle et du tokenizer
|
||||||
|
checkpoint = "Clem27-Assistants/Learnia-Empathic-Tchat"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(checkpoint)
|
||||||
|
|
||||||
|
# Structure de la conversation
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": "Hello! My mother yelled at me. What should I do?"},
|
||||||
|
]
|
||||||
|
|
||||||
|
# Application du chat template
|
||||||
|
inputs = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
tokenize=True,
|
||||||
|
return_dict=True,
|
||||||
|
return_tensors="pt",
|
||||||
|
).to(model.device)
|
||||||
|
|
||||||
|
# Génération de la réponse
|
||||||
|
outputs = model.generate(
|
||||||
|
**inputs,
|
||||||
|
max_new_tokens=200,
|
||||||
|
do_sample=True,
|
||||||
|
temperature=0.7,
|
||||||
|
eos_token_id=tokenizer.eos_token_id,
|
||||||
|
stop_strings=["<|im_end|>"],
|
||||||
|
tokenizer=tokenizer
|
||||||
|
)
|
||||||
|
|
||||||
|
# Décodage et post-process
|
||||||
|
decoded_output = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])
|
||||||
|
clean_output = decoded_output.replace("<|im_end|>", "").strip()
|
||||||
|
|
||||||
|
print(f"Assistant: {clean_output}")
|
||||||
|
```
|
||||||
|
|
||||||
|
# ⚠️ Limitations
|
||||||
|
Étant un modèle de 51.6M de paramètres, Learnia-Empathic-Tchat est conçu pour la texture conversationnelle et l'empathie, et non pour le calcul mathématique ou la génération de code complexe. Il brille par sa capacité à maintenir un ton humain et réconfortant.
|
||||||
|
|
||||||
|
**nos conditions d'utilisation et politique de confidentialité officielles** :
|
||||||
|
https://learnia-gazelle-empathy.lovable.app/
|
||||||
14
chat_template.jinja
Normal file
14
chat_template.jinja
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{% for message in messages %}
|
||||||
|
{% if message['role'] == 'system' %}
|
||||||
|
{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>' }}
|
||||||
|
{% elif message['role'] == 'user' %}
|
||||||
|
{{ '\n<|im_start|>user\n' + message['content'] + '<|im_end|>' }}
|
||||||
|
{% elif message['role'] == 'assistant' %}
|
||||||
|
{{ '\n<|im_start|>assistant\n' + message['content'] + '<|im_end|>' }}
|
||||||
|
{% endif %}
|
||||||
|
{% endfor %}
|
||||||
|
{% if add_generation_prompt %}
|
||||||
|
{{ '\n<|im_start|>assistant\n' }}
|
||||||
|
{% else %}
|
||||||
|
{{ '<|im_end|>' }}
|
||||||
|
{% endif %}
|
||||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
{
|
||||||
|
"activation_function": "gelu_new",
|
||||||
|
"add_cross_attention": false,
|
||||||
|
"architectures": [
|
||||||
|
"GPT2LMHeadModel"
|
||||||
|
],
|
||||||
|
"attn_pdrop": 0.1,
|
||||||
|
"bos_token_id": 50256,
|
||||||
|
"dtype": "float32",
|
||||||
|
"embd_pdrop": 0.1,
|
||||||
|
"eos_token_id": 50256,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"layer_norm_epsilon": 1e-05,
|
||||||
|
"model_type": "gpt2",
|
||||||
|
"n_ctx": 1350,
|
||||||
|
"n_embd": 512,
|
||||||
|
"n_head": 8,
|
||||||
|
"n_inner": null,
|
||||||
|
"n_layer": 8,
|
||||||
|
"n_positions": 1350,
|
||||||
|
"pad_token_id": 50257,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"reorder_and_upcast_attn": false,
|
||||||
|
"resid_pdrop": 0.1,
|
||||||
|
"scale_attn_by_inverse_layer_idx": false,
|
||||||
|
"scale_attn_weights": true,
|
||||||
|
"summary_activation": null,
|
||||||
|
"summary_first_dropout": 0.1,
|
||||||
|
"summary_proj_to_labels": true,
|
||||||
|
"summary_type": "cls_index",
|
||||||
|
"summary_use_proj": true,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.0.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 50258
|
||||||
|
}
|
||||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 50256,
|
||||||
|
"eos_token_id": [
|
||||||
|
50256
|
||||||
|
],
|
||||||
|
"pad_token_id": 50257,
|
||||||
|
"transformers_version": "5.0.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4766d1bd714d4311b139035c3cf2413ad655cddac38c4829d8330377b6fd3066
|
||||||
|
size 206583536
|
||||||
250315
tokenizer.json
Normal file
250315
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
14
tokenizer_config.json
Normal file
14
tokenizer_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"is_local": false,
|
||||||
|
"model_max_length": 1024,
|
||||||
|
"model_specific_special_tokens": {},
|
||||||
|
"pad_token": "[PAD]",
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1c37a15ee1fdc17df16e7e33b913c64b7cad9e9b40e13dad118d5ae05a020f8a
|
||||||
|
size 5585
|
||||||
Reference in New Issue
Block a user