Upload folder using huggingface_hub
Browse files- config.json +32 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- sft_config.json +28 -0
- tokenizer.json +0 -0
- tokenizer_meta.json +13 -0
- training_state.pt +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1376,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 8,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": true,
|
| 29 |
+
"transformers_version": "5.14.1",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 48000
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "5.14.1",
|
| 9 |
+
"use_cache": false
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c390f58a024851467b72bd72966b8b955baaa4bbc5d6dd6e7fd6ad6709929cba
|
| 3 |
+
size 191146000
|
sft_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "dmt-multilingual-50m-translation-sft",
|
| 3 |
+
"base_model_dir": "outputs/dmt-multilingual-50m/final",
|
| 4 |
+
"data_dir": "data/sft_tokenized",
|
| 5 |
+
"tokenizer_path": "tokenizer/tokenizer.json",
|
| 6 |
+
"output_dir": "outputs/dmt-multilingual-50m-translation-sft",
|
| 7 |
+
"training": {
|
| 8 |
+
"micro_batch_size": 64,
|
| 9 |
+
"eval_micro_batch_size": 64,
|
| 10 |
+
"gradient_accumulation_steps": 2,
|
| 11 |
+
"epochs": 1,
|
| 12 |
+
"max_steps": 0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"min_learning_rate": 5e-06,
|
| 15 |
+
"weight_decay": 0.01,
|
| 16 |
+
"warmup_ratio": 0.03,
|
| 17 |
+
"gradient_clip": 1.0,
|
| 18 |
+
"num_workers": 8,
|
| 19 |
+
"pad_to_multiple_of": 8,
|
| 20 |
+
"log_interval": 20,
|
| 21 |
+
"eval_interval": 500,
|
| 22 |
+
"eval_batches": 100,
|
| 23 |
+
"save_interval": 2000,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"compile": false,
|
| 26 |
+
"gradient_checkpointing": false
|
| 27 |
+
}
|
| 28 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_meta.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"algorithm": "ByteLevel BPE",
|
| 3 |
+
"requested_vocab_size": 48000,
|
| 4 |
+
"actual_vocab_size": 48000,
|
| 5 |
+
"special_tokens": {
|
| 6 |
+
"<pad>": 0,
|
| 7 |
+
"<s>": 1,
|
| 8 |
+
"</s>": 2,
|
| 9 |
+
"<unk>": 3,
|
| 10 |
+
"<ko>": 4,
|
| 11 |
+
"<en>": 5
|
| 12 |
+
}
|
| 13 |
+
}
|
training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7cf704c271600ba570d5eee0644f451d61e47a32ddd3600d09c69252a412444
|
| 3 |
+
size 382340799
|