Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- PATIENT_FILE.md +16 -0
- ct2/config.json +55 -0
- ct2/generation_config.json +16 -0
- ct2/model.safetensors +3 -0
- ct2/source.spm +3 -0
- ct2/special_tokens_map.json +5 -0
- ct2/target.spm +3 -0
- ct2/tokenizer_config.json +38 -0
- ct2/vocab.json +0 -0
- herm0-ct2/config.json +10 -0
- herm0-ct2/model.bin +3 -0
- herm0-ct2/shared_vocabulary.json +0 -0
.gitattributes
CHANGED
|
@@ -39,3 +39,5 @@ lora/source.spm filter=lfs diff=lfs merge=lfs -text
|
|
| 39 |
lora/target.spm filter=lfs diff=lfs merge=lfs -text
|
| 40 |
herm0/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 41 |
herm0/target.spm filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 39 |
lora/target.spm filter=lfs diff=lfs merge=lfs -text
|
| 40 |
herm0/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 41 |
herm0/target.spm filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
ct2/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
ct2/target.spm filter=lfs diff=lfs merge=lfs -text
|
PATIENT_FILE.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Patient File: windy-pair-eo-cs
|
| 2 |
+
**Created:** 2026-03-28T00:07:51.392638+00:00
|
| 3 |
+
**Fleet:** Windy Pro Translation Models
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
## INT8 Quantization — 2026-03-28T00:07:51.392638+00:00
|
| 7 |
+
**Doctor:** Dr. B (Herm Zero)
|
| 8 |
+
**Procedure:** CTranslate2 INT8 quantization of GOATIA/Herm0 improved model
|
| 9 |
+
**Source:** herm0/ (improved model)
|
| 10 |
+
**Output:** herm0-ct2/ (INT8 quantized)
|
| 11 |
+
**Status:** SUCCESS
|
| 12 |
+
**Original size:** 183.6 MB
|
| 13 |
+
**INT8 size:** 47.4 MB
|
| 14 |
+
**Compression:** 3.87x
|
| 15 |
+
**Load test:** passed
|
| 16 |
+
**Recommendation:** INT8 variant ready for production deployment
|
ct2/config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "swish",
|
| 4 |
+
"add_bias_logits": false,
|
| 5 |
+
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MarianMTModel"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"classif_dropout": 0.0,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 512,
|
| 14 |
+
"decoder_attention_heads": 8,
|
| 15 |
+
"decoder_ffn_dim": 2048,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 6,
|
| 18 |
+
"decoder_start_token_id": 7396,
|
| 19 |
+
"decoder_vocab_size": 7397,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"dtype": "float32",
|
| 22 |
+
"encoder_attention_heads": 8,
|
| 23 |
+
"encoder_ffn_dim": 2048,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 0,
|
| 27 |
+
"extra_pos_embeddings": 7397,
|
| 28 |
+
"forced_eos_token_id": 0,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_length": null,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "marian",
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": false,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 7396,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"share_encoder_decoder_embeddings": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"transformers_version": "4.57.3",
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"vocab_size": 7397
|
| 55 |
+
}
|
ct2/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
7396
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 7396,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 7396,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.57.3"
|
| 16 |
+
}
|
ct2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8b0d01617295d10b347843c07b9c09c90a300c4136de6a1d0e66a9212bd53b2
|
| 3 |
+
size 191761676
|
ct2/source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684b51586a682af089d7cd54d315571d885f969753763a7fc652b093d22449ff
|
| 3 |
+
size 303125
|
ct2/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
ct2/target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99dee0635b959e0761d3d02a0e5e5a357f4af24ae15288c6515b95f76e09b730
|
| 3 |
+
size 304201
|
ct2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"7396": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": false,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "epo",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"target_lang": "ces",
|
| 36 |
+
"tokenizer_class": "MarianTokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
ct2/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
herm0-ct2/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_source_bos": false,
|
| 3 |
+
"add_source_eos": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"decoder_start_token": "</s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"layer_norm_epsilon": null,
|
| 8 |
+
"multi_query_attention": false,
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
herm0-ct2/model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67600f2840fc3569a23ffa0299f53480c20deb9f2e42bc3d3c0b73ea75b048c2
|
| 3 |
+
size 49613555
|
herm0-ct2/shared_vocabulary.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|