Training Basic Model for Mistral MidiTok Transformer Single Instrument Small
Browse files- config.json +28 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/wombat/Documents/projects/music/midiTok/data/HuggingFace_Mistral_Transformer_Single_Instrument/run/model.safetensors",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 64,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 512,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 2048,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 8,
|
17 |
+
"num_hidden_layers": 8,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"sliding_window": 256,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.46.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.46.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a36a5a2deaeaccf3c60fea79860b75fedca40b881d9a46f0133565023849741
|
3 |
+
size 256944240
|