upload models
Browse files
tokenizer/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "CompressiveVQModel",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
128,
|
| 7 |
+
256,
|
| 8 |
+
512
|
| 9 |
+
],
|
| 10 |
+
"context_length": 2,
|
| 11 |
+
"down_block_types": [
|
| 12 |
+
"DownEncoderBlock2D",
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D"
|
| 15 |
+
],
|
| 16 |
+
"force_upcast": true,
|
| 17 |
+
"in_channels": 3,
|
| 18 |
+
"latent_channels": 64,
|
| 19 |
+
"layers_per_block": 2,
|
| 20 |
+
"lookup_from_codebook": true,
|
| 21 |
+
"max_att_resolution": 16,
|
| 22 |
+
"mid_block_add_attention": false,
|
| 23 |
+
"norm_num_groups": 32,
|
| 24 |
+
"norm_type": "group",
|
| 25 |
+
"num_dyn_embeddings": 8192,
|
| 26 |
+
"num_vq_embeddings": 8192,
|
| 27 |
+
"out_channels": 3,
|
| 28 |
+
"patch_size": 4,
|
| 29 |
+
"resolution": 64,
|
| 30 |
+
"sample_size": 32,
|
| 31 |
+
"scaling_factor": 0.18215,
|
| 32 |
+
"up_block_types": [
|
| 33 |
+
"UpDecoderBlock2D",
|
| 34 |
+
"UpDecoderBlock2D",
|
| 35 |
+
"UpDecoderBlock2D"
|
| 36 |
+
],
|
| 37 |
+
"vq_embed_dim": null
|
| 38 |
+
}
|
tokenizer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0350b9f6b34dbdd0f387c31eb10493cb9aa1d3b2c224f3e2a2fa037f19319f4d
|
| 3 |
+
size 456684880
|
transformer/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"eos_token_id": 50256,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"max_position_embeddings": 1024,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"num_key_value_heads": 12,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.38.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 16386
|
| 27 |
+
}
|
transformer/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a325113a9993369408bc5e2df28875bc3da6179105f8d6e0adb05bde1d470fc
|
| 3 |
+
size 553749536
|