Upload Qwen2AudioForConditionalGeneration
Browse files- config.json +102 -0
- generation_config.json +14 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2AudioForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"activation_dropout": 0.0,
|
| 7 |
+
"activation_function": "gelu",
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"d_model": 1280,
|
| 10 |
+
"dropout": 0.0,
|
| 11 |
+
"encoder_attention_heads": 20,
|
| 12 |
+
"encoder_ffn_dim": 5120,
|
| 13 |
+
"encoder_layerdrop": 0.0,
|
| 14 |
+
"encoder_layers": 32,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"max_source_positions": 1500,
|
| 17 |
+
"model_type": "qwen2_audio_encoder",
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_mel_bins": 128,
|
| 20 |
+
"scale_embedding": false,
|
| 21 |
+
"torch_dtype": "float16"
|
| 22 |
+
},
|
| 23 |
+
"audio_token_index": 151646,
|
| 24 |
+
"ignore_index": -100,
|
| 25 |
+
"model_type": "qwen2_audio",
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"_load_in_4bit": true,
|
| 28 |
+
"_load_in_8bit": false,
|
| 29 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 30 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 31 |
+
"bnb_4bit_quant_type": "nf4",
|
| 32 |
+
"bnb_4bit_use_double_quant": true,
|
| 33 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 34 |
+
"llm_int8_has_fp16_weight": false,
|
| 35 |
+
"llm_int8_skip_modules": null,
|
| 36 |
+
"llm_int8_threshold": 6.0,
|
| 37 |
+
"load_in_4bit": true,
|
| 38 |
+
"load_in_8bit": false,
|
| 39 |
+
"quant_method": "bitsandbytes"
|
| 40 |
+
},
|
| 41 |
+
"text_config": {
|
| 42 |
+
"attention_dropout": 0.0,
|
| 43 |
+
"bos_token_id": 151643,
|
| 44 |
+
"eos_token_id": 151645,
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 4096,
|
| 47 |
+
"initializer_range": 0.02,
|
| 48 |
+
"intermediate_size": 11008,
|
| 49 |
+
"layer_types": [
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"full_attention",
|
| 81 |
+
"full_attention"
|
| 82 |
+
],
|
| 83 |
+
"max_position_embeddings": 8192,
|
| 84 |
+
"max_window_layers": 28,
|
| 85 |
+
"model_type": "qwen2",
|
| 86 |
+
"num_attention_heads": 32,
|
| 87 |
+
"num_hidden_layers": 32,
|
| 88 |
+
"num_key_value_heads": 32,
|
| 89 |
+
"rms_norm_eps": 1e-05,
|
| 90 |
+
"rope_scaling": null,
|
| 91 |
+
"rope_theta": 10000,
|
| 92 |
+
"sliding_window": null,
|
| 93 |
+
"torch_dtype": "float16",
|
| 94 |
+
"use_cache": true,
|
| 95 |
+
"use_mrope": false,
|
| 96 |
+
"use_sliding_window": false,
|
| 97 |
+
"vocab_size": 156032
|
| 98 |
+
},
|
| 99 |
+
"torch_dtype": "float16",
|
| 100 |
+
"transformers_version": "4.53.0.dev0",
|
| 101 |
+
"vocab_size": 156032
|
| 102 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_format": "chatml",
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151643,
|
| 6 |
+
151645
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.5,
|
| 13 |
+
"transformers_version": "4.53.0.dev0"
|
| 14 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bd7901aed2659a0fa9b041fabb29d7af11d29a75b0a247ff1fba1b9dea16374
|
| 3 |
+
size 4964121579
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d264ec26836e039c675faa9be628bfcc99cfbf31ad2b253d1f121c489744874
|
| 3 |
+
size 1278214288
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|