Upload model
Browse files- config.json +45 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/media/khalid/HDD2/Huggingface_models/mt5_large",
|
3 |
+
"architectures": [
|
4 |
+
"MT5Model"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"quantization_config": {
|
26 |
+
"bnb_4bit_compute_dtype": "float32",
|
27 |
+
"bnb_4bit_quant_type": "fp4",
|
28 |
+
"bnb_4bit_use_double_quant": false,
|
29 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
+
"llm_int8_has_fp16_weight": false,
|
31 |
+
"llm_int8_skip_modules": null,
|
32 |
+
"llm_int8_threshold": 6.0,
|
33 |
+
"load_in_4bit": false,
|
34 |
+
"load_in_8bit": true,
|
35 |
+
"quant_method": "bitsandbytes"
|
36 |
+
},
|
37 |
+
"relative_attention_max_distance": 128,
|
38 |
+
"relative_attention_num_buckets": 32,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"tokenizer_class": "T5Tokenizer",
|
41 |
+
"torch_dtype": "float16",
|
42 |
+
"transformers_version": "4.33.0.dev0",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 250112
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c980de8bc9416c6d290efd681be33ce88ee2f8ec23d786720e0e967b1c05513f
|
3 |
+
size 1647527617
|