Update tiny models for JetMoeForSequenceClassification
Browse files- config.json +33 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "silu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"JetMoeForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"aux_loss_coef": 0.01,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_size": 32,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 37,
|
| 14 |
+
"kv_channels": 8,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "jetmoe",
|
| 17 |
+
"num_attention_heads": 4,
|
| 18 |
+
"num_experts_per_tok": 2,
|
| 19 |
+
"num_hidden_layers": 2,
|
| 20 |
+
"num_key_value_heads": 2,
|
| 21 |
+
"num_local_experts": 4,
|
| 22 |
+
"output_router_logits": false,
|
| 23 |
+
"pad_token_id": 2,
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_parameters": {
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"rope_type": "default"
|
| 28 |
+
},
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"transformers_version": "5.16.0.dev0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f8d81fc1bcb9c01e0ac99b0708f241fbbff9642d95127817fe994f4902e74aa
|
| 3 |
+
size 4256816
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"extra_special_tokens": [],
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"pad_token": "</s>",
|
| 12 |
+
"padding_side": "left",
|
| 13 |
+
"sp_model_kwargs": {},
|
| 14 |
+
"spaces_between_special_tokens": false,
|
| 15 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 16 |
+
"unk_token": "<unk>",
|
| 17 |
+
"use_default_system_prompt": false
|
| 18 |
+
}
|