Finisha-F-scratch/Learnia-tchat-v1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Finisha-F-scratch/Learnia-tchat-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-06 11:33:12 +08:00
commit dc90e46d63
15 changed files with 300679 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

41
README.md Normal file
View File

@@ -0,0 +1,41 @@
---
tags:
- Learnia
- SLM
- english
- text-generation-inference
- text-generation
library_name: transformers
base_model: Finisha-F-scratch/Learnia
widget:
- messages:
- role: user
content: Hello, who are you ?
license: other
datasets:
- Finisha-F-scratch/Dialogue-learn
---
# 🐝 Fiche Technique : learnia-tchat-v1
![Learnia-tchat-v1](http://www.image-heberg.fr/files/17717474271399179052.jpg)
learnia-tchat-v1 est un Small Language Model (SLM) de 51.6M de paramètres, affiné spécifiquement pour la fluidité conversationnelle et la génération de récits longs en anglais. Conçu par Finisha, il tire sa force de l'architecture pré-entraînée Learnia, optimisée pour offrir une texture de langage organique loin des standards lisses de l'industrie.
# 💎 Caractéristiques Principales
* Base de données : Fine-tuné sur des datasets de dialogues ultra-spécialisés, écrits et sélectionnés de A à Z.
* Capacité narrative : Optimisé pour maintenir une cohérence textuelle sur de longues séquences en anglais.
* Poids plume : 51.6 millions de paramètres, idéal pour une exécution ultra-rapide en local.
* Architecture : Dérivé de Learnia, utilisant une approche qui privilégie l'originalité syntaxique et la "texture" brute du langage.
#. 📝 Note sur la Syntaxe
> Ce modèle ne cherche pas la perfection grammaticale robotique. Il a été forgé pour avoir une voix. Il peut générer des néologismes et des tournures propres à l'identité "from scratch" de Finisha. La texture prime sur la norme.
>
# 📊 Benchmark rapide
| Métrique | Valeur |
|---|---|
| Paramètres | 51.6M |
| Langue cible | Anglais |
| Vibe | Texturée, originale, non-linéaire |

9
added_tokens.json Normal file
View File

@@ -0,0 +1,9 @@
{
"<pad>": 50260,
"<s>": 50258,
"<|im_end|>": 50259,
"<|im_start|>assistant": 50262,
"<|im_start|>system": 50263,
"<|im_start|>user": 50261,
"[PAD]": 50257
}

15
chat_template.jinja Normal file
View File

@@ -0,0 +1,15 @@
{% for message in messages %}
{% if message['role'] == 'user' %}
{{ '<|user|>
' + message['content'] + eos_token }}
{% elif message['role'] == 'system' %}
{{ '<|system|>
' + message['content'] + eos_token }}
{% elif message['role'] == 'assistant' %}
{{ '<|assistant|>
' + message['content'] + eos_token }}
{% endif %}
{% if loop.last and add_generation_prompt %}
{{ '<|assistant|>' }}
{% endif %}
{% endfor %}

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"_name_or_path": "Finisha-F-scratch/Learnia",
"activation_function": "gelu_new",
"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,
"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,
"torch_dtype": "float32",
"transformers_version": "4.48.0",
"use_cache": true,
"vocab_size": 50264
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": [
50256
],
"pad_token_id": 50257,
"transformers_version": "4.48.0"
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d271760ac8b96ebe4fc8f7414297c3dfd0fb38d4e32a9c7fd9d861f85a88f5f
size 206595824

3
runs/Feb04_10-22-38_r-clemylia-autotrain-advanced-yfuw777p-6e793-ffmlf/events.out.tfevents.1770200565.r-clemylia-autotrain-advanced-yfuw777p-6e793-ffmlf.97.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4dd9904c3f30c07ced83ab65f64980360ae9406d1b5fd7a261f4b4d1bef0bc5c
size 6977

20
special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>user",
"<|im_start|>assistant",
"<|im_start|>system",
"<|im_end|>",
"<s>",
"<pad>"
],
"bos_token": "<s>",
"eos_token": "<|im_end|>",
"pad_token": "<pad>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

250369
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

86
tokenizer_config.json Normal file
View File

@@ -0,0 +1,86 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50258": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50259": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50260": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50261": {
"content": "<|im_start|>user",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50262": {
"content": "<|im_start|>assistant",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50263": {
"content": "<|im_start|>system",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>user",
"<|im_start|>assistant",
"<|im_start|>system",
"<|im_end|>",
"<s>",
"<pad>"
],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cfe16d5c6baef3e947733b2fdc1d10141c25ad6d354459ab8e143e76d63c714
size 5624

49
training_params.json Normal file
View File

@@ -0,0 +1,49 @@
{
"model": "Finisha-F-scratch/Learnia",
"project_name": "Learnia-tchat-v2",
"data_path": "Finisha-F-scratch/Dialogue-learn",
"train_split": "train",
"valid_split": null,
"add_eos_token": true,
"block_size": 512,
"model_max_length": 1350,
"padding": "right",
"trainer": "sft",
"use_flash_attention_2": false,
"log": "tensorboard",
"disable_gradient_checkpointing": false,
"logging_steps": -1,
"eval_strategy": "epoch",
"save_total_limit": 1,
"auto_find_batch_size": false,
"mixed_precision": "fp16",
"lr": 3e-05,
"epochs": 25,
"batch_size": 2,
"warmup_ratio": 0.1,
"gradient_accumulation": 4,
"optimizer": "adamw_torch",
"scheduler": "linear",
"weight_decay": 0.0,
"max_grad_norm": 1.0,
"seed": 42,
"chat_template": "chatml",
"quantization": "int4",
"target_modules": "all-linear",
"merge_adapter": false,
"peft": false,
"lora_r": 16,
"lora_alpha": 32,
"lora_dropout": 0.05,
"model_ref": null,
"dpo_beta": 0.1,
"max_prompt_length": 128,
"max_completion_length": null,
"prompt_text_column": "prompt",
"text_column": "messages",
"rejected_text_column": "rejected_text",
"push_to_hub": true,
"username": "Clemylia",
"unsloth": false,
"distributed_backend": "ddp"
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long