Upload folder using huggingface_hub
Browse files- README.md +65 -0
- added_tokens.json +3 -0
- config.json +35 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- quantize_config.json +18 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +37 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: nelya-restrictive
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
datasets:
|
| 6 |
+
- Clemylia/Charlotte-nekolien-SLM
|
| 7 |
+
language:
|
| 8 |
+
- fr
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- SLM
|
| 12 |
+
- Neko-SLM
|
| 13 |
+
- Nekolien
|
| 14 |
+
- "Cr\xE9ativit\xE9"
|
| 15 |
+
- Nelya
|
| 16 |
+
library_name: transformers.js
|
| 17 |
+
base_model:
|
| 18 |
+
- LLM-CLEM/Nelya
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# Nelya (ONNX)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
This is an ONNX version of [LLM-CLEM/Nelya](https://huggingface.co/LLM-CLEM/Nelya). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
## Usage with Transformers.js
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
See the pipeline documentation for `text-generation`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
# 🌸 Nelya - mini-Assistante Nekolienne
|
| 39 |
+
|
| 40 |
+

|
| 41 |
+
|
| 42 |
+
Nelya est un **SLM** (small language model),
|
| 43 |
+
Crée from scratch (de zéro) à partir de notre modèle de fondation : **Lam-4-zero-F**.
|
| 44 |
+
|
| 45 |
+
Nelya excelle a générer des phrases en nekolien. Le nekolien est une langue artificielle, que nous avons imaginée et conçu nous même.
|
| 46 |
+
Nous l'avons créées originairement pour nos chansons et notre créativité,
|
| 47 |
+
Mais nous nous sommes dit qu'une IA qui parle notre langue n'était pas une mauvaise idée.
|
| 48 |
+
|
| 49 |
+
# ✨ Cas d'usage 🌸
|
| 50 |
+
|
| 51 |
+
* - Créativité
|
| 52 |
+
* - exploration de la langue
|
| 53 |
+
|
| 54 |
+
Vous pouvez générer du texte avec Nelya,
|
| 55 |
+
Pour explorer la créativité de notre propre langue.
|
| 56 |
+
Nelya prouve que les modèles de languages ne sont pas seulement des assistants généralistes qui parlent qu'anglais ou français,
|
| 57 |
+
Ils peuvent parler le langage que vous souhaitez.
|
| 58 |
+
|
| 59 |
+
# ♥️ License de Nelya 🩷
|
| 60 |
+
|
| 61 |
+
Attention, l'utilisation de Nelya est régi par la licence Nelya-restrictive,
|
| 62 |
+
qui n'est pas open source.
|
| 63 |
+
Notre licence interdit tout affinage ou utilisation commerciale de Nelya.
|
| 64 |
+
|
| 65 |
+
**✨ Amusée vous bien a utiliser Nelya ✨**
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "LLM-CLEM/Nelya",
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"embd_pdrop": 0.1,
|
| 12 |
+
"eos_token_id": 50256,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"layer_norm_epsilon": 1e-05,
|
| 15 |
+
"model_type": "gpt2",
|
| 16 |
+
"n_embd": 512,
|
| 17 |
+
"n_head": 8,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 8,
|
| 20 |
+
"n_positions": 128,
|
| 21 |
+
"pad_token_id": 50257,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.49.0",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 50258
|
| 35 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50257,
|
| 8 |
+
"transformers_version": "4.49.0"
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10eafd3b85f0d19c70c3dcb9a0786476e31b2f827c08896b81e4301b00ee2fb2
|
| 3 |
+
size 204300051
|
onnx/model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a87e5f5376dc611cc4e672fe043eca0507a6cb324ae3b70cd6b35700f21dd978
|
| 3 |
+
size 204300070
|
onnx/model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a1469f30287c23af1afbd583718a6394eb819fe6b709290e3c7c521331461f8
|
| 3 |
+
size 102268734
|
onnx/model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d6e0036284696051b08b867f2321740cde9064076b706a1ad7a43cfc4d365e
|
| 3 |
+
size 154386871
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a87e5f5376dc611cc4e672fe043eca0507a6cb324ae3b70cd6b35700f21dd978
|
| 3 |
+
size 204300070
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fc6cc0be4a48914c872cb6c0fb881d22168b82a8a439ef2bd1fef07720d2938
|
| 3 |
+
size 102268753
|
onnx/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d6e0036284696051b08b867f2321740cde9064076b706a1ad7a43cfc4d365e
|
| 3 |
+
size 154386871
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11de49aefd51e3383a13c92f7145054c3142bef048ea5258edf3e5a31c406680
|
| 3 |
+
size 154386885
|
quantize_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modes": [
|
| 3 |
+
"fp16",
|
| 4 |
+
"q8",
|
| 5 |
+
"int8",
|
| 6 |
+
"uint8",
|
| 7 |
+
"q4",
|
| 8 |
+
"q4f16",
|
| 9 |
+
"bnb4"
|
| 10 |
+
],
|
| 11 |
+
"per_channel": false,
|
| 12 |
+
"reduce_range": false,
|
| 13 |
+
"block_size": null,
|
| 14 |
+
"is_symmetric": true,
|
| 15 |
+
"accuracy_level": null,
|
| 16 |
+
"quant_type": 1,
|
| 17 |
+
"op_block_list": null
|
| 18 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": "[PAD]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|endoftext|>",
|
| 22 |
+
"chat_template": "{%- for message in messages -%}\n {{ '### Instruction:\\n' + message.content + '\\n\\n' }}\n{%- endfor -%}\n{{ '### Response:\\n' }}",
|
| 23 |
+
"clean_up_tokenization_spaces": false,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"extra_special_tokens": {},
|
| 26 |
+
"max_length": 128,
|
| 27 |
+
"model_max_length": 1024,
|
| 28 |
+
"pad_to_multiple_of": null,
|
| 29 |
+
"pad_token": "[PAD]",
|
| 30 |
+
"pad_token_type_id": 0,
|
| 31 |
+
"padding_side": "right",
|
| 32 |
+
"stride": 0,
|
| 33 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 34 |
+
"truncation_side": "right",
|
| 35 |
+
"truncation_strategy": "longest_first",
|
| 36 |
+
"unk_token": "<|endoftext|>"
|
| 37 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|