AdoCleanCode commited on
Commit
e49d04f
·
verified ·
1 Parent(s): 323d4d1

Step 300, eval_loss=N/A

Browse files
llasa/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/aasonitis/train_vc_1705453/hf_cache/models--AdoCleanCode--LAVCO-v1/snapshots/b14f8174f4e01bd71710f344067872ba3b029720/llasa",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 193800
40
+ }
llasa/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.2"
12
+ }
llasa/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45849ffa793ab907d8000d457243cd99f95ef78587913de5933c32c85764b9b4
3
+ size 2740113872
llasa_vc_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "whisper_model": "openai/whisper-small",
3
+ "xcodec_model": "HKUSTAudio/xcodec2",
4
+ "whisper_dim": 768,
5
+ "hidden_size": 2048,
6
+ "u_start_id": 128262,
7
+ "u_end_id": 128263,
8
+ "g_start_id": 128260,
9
+ "g_end_id": 128261,
10
+ "pad_id": 128009,
11
+ "instruction_prefix": "Convert ",
12
+ "instruction_middle": " into speech using this speaker: "
13
+ }
projection.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0aa89a964efe6f48894eae34fc4632ae9e4bf49f25825ec24d69b1bfd8af8c
3
+ size 6301162