Subida automática de CaelisNeuralBase-3 (CNB-Gen) con nomenclatura oficial
Browse files- config.json +35 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- pytorch_model.pth +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"CaelisNeuralBase"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "cnb3",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1536,
|
| 17 |
+
"n_head": 24,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 32,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": null,
|
| 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 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"transformers_version": "5.17.0",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 50257
|
| 35 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"output_attentions": false,
|
| 5 |
+
"output_hidden_states": false,
|
| 6 |
+
"transformers_version": "5.17.0",
|
| 7 |
+
"use_cache": true
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cd3b9600c606e20db5e9e74dd4ddaeb2245d28f948c7240e8c5dec0b8441e32
|
| 3 |
+
size 3941557952
|
pytorch_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ef02dc2b19067c0f3e2f610c04897d3e8fde89511e4ebcb980df5c046c52ba
|
| 3 |
+
size 3941660083
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "<CLS>",
|
| 4 |
+
"is_local": true,
|
| 5 |
+
"local_files_only": false,
|
| 6 |
+
"mask_token": "<MASK>",
|
| 7 |
+
"max_length": 1024,
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"model_type": "caelis",
|
| 10 |
+
"organization": "Inserloft Research",
|
| 11 |
+
"pad_token": "<PAD>",
|
| 12 |
+
"padding_side": "right",
|
| 13 |
+
"project": "Caelis Neural Base",
|
| 14 |
+
"sep_token": "<SEP>",
|
| 15 |
+
"stride": 0,
|
| 16 |
+
"tokenizer_class": "TokenizersBackend",
|
| 17 |
+
"truncation_side": "right",
|
| 18 |
+
"truncation_strategy": "longest_first",
|
| 19 |
+
"unk_token": "<UNK>"
|
| 20 |
+
}
|