Mirrors/stable-diffusion-webui-forge
1
0
Fork 0
mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2025-12-28 13:42:02 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add Chroma (#2925)

Browse Source
This commit is contained in:
Mathieu Croquelois 2025-06-23 23:35:06 +01:00 committed by GitHub
parent ae278f7940
commit 963e7643f0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
11 changed files with 131222 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
backend/diffusion_engine/chroma.py Normal file
View File

@ -0,0 +1,72 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend.modules.k_prediction import PredictionFlux
from backend import memory_management
class Chroma(ForgeDiffusionEngine):
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
't5xxl': huggingface_components['text_encoder']
},
tokenizer_dict={
't5xxl': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
k_predictor = PredictionFlux(
mu=1.0
)
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler=None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
min_length=1
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
def set_clip_skip(self, clip_skip):
pass
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
return self.text_processing_engine_t5(prompt)
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)

24
backend/huggingface/Chroma/model_index.json Normal file
View File

@ -0,0 +1,24 @@
{
"_class_name": "FluxPipeline",
"_diffusers_version": "0.30.0.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"ChromaTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

11
backend/huggingface/Chroma/scheduler/scheduler_config.json Normal file
View File

@ -0,0 +1,11 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.30.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"max_image_seq_len": 4096,
"max_shift": 1.15,
"num_train_timesteps": 1000,
"shift": 1.0,
"use_dynamic_shifting": false
}

22
backend/huggingface/Chroma/text_encoder/config.json Normal file
View File

@ -0,0 +1,22 @@
{
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "gelu_pytorch_tanh",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}

226
backend/huggingface/Chroma/text_encoder/model.safetensors.index.json Normal file
View File

@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 9524621312
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

125
backend/huggingface/Chroma/tokenizer/special_tokens_map.json Normal file
View File

@ -0,0 +1,125 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

129428
backend/huggingface/Chroma/tokenizer/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

939
backend/huggingface/Chroma/tokenizer/tokenizer_config.json Normal file
View File

@ -0,0 +1,939 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": false,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

38
backend/huggingface/Chroma/vae/config.json Normal file
View File

@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

32
backend/loader.py
View File

@ -22,9 +22,10 @@ from backend.diffusion_engine.sd20 import StableDiffusion2
from backend.diffusion_engine.sdxl import StableDiffusionXL, StableDiffusionXLRefiner
from backend.diffusion_engine.sd35 import StableDiffusion3
from backend.diffusion_engine.flux import Flux
from backend.diffusion_engine.chroma import Chroma
possible_models = [StableDiffusion, StableDiffusion2, StableDiffusionXLRefiner, StableDiffusionXL, StableDiffusion3, Flux]
possible_models = [StableDiffusion, StableDiffusion2, StableDiffusionXLRefiner, StableDiffusionXL, StableDiffusion3, Chroma, Flux]
logging.getLogger("diffusers").setLevel(logging.ERROR)
@ -108,7 +109,7 @@ def load_huggingface_component(guess, component_name, lib_name, cls_name, repo_p
load_state_dict(model, state_dict, log_name=cls_name, ignore_errors=['transformer.encoder.embed_tokens.weight', 'logit_scale'])
return model
if cls_name in ['UNet2DConditionModel', 'FluxTransformer2DModel', 'SD3Transformer2DModel']:
if cls_name in ['UNet2DConditionModel', 'FluxTransformer2DModel', 'SD3Transformer2DModel', 'ChromaTransformer2DModel']:
assert isinstance(state_dict, dict) and len(state_dict) > 16, 'You do not have model state dict!'
model_loader = None
@ -117,6 +118,9 @@ def load_huggingface_component(guess, component_name, lib_name, cls_name, repo_p
elif cls_name == 'FluxTransformer2DModel':
from backend.nn.flux import IntegratedFluxTransformer2DModel
model_loader = lambda c: IntegratedFluxTransformer2DModel(**c)
elif cls_name == 'ChromaTransformer2DModel':
from backend.nn.chroma import IntegratedChromaTransformer2DModel
model_loader = lambda c: IntegratedChromaTransformer2DModel(**c)
elif cls_name == 'SD3Transformer2DModel':
from backend.nn.mmditx import MMDiTX
model_loader = lambda c: MMDiTX(**c)
@ -478,7 +482,18 @@ def split_state_dict(sd, additional_state_dicts: list = None):
return state_dict, guess
# To be removed once PR merged on huggingface_guess
chroma_is_in_huggingface_guess = hasattr(huggingface_guess.model_list, "Chroma")
if not chroma_is_in_huggingface_guess:
class GuessChroma:
huggingface_repo = 'Chroma'
unet_extra_config = {
'guidance_out_dim': 3072,
'guidance_hidden_dim': 5120,
'guidance_n_layers': 5
}
unet_remove_config = ['guidance_embed']
@torch.inference_mode()
def forge_loader(sd, additional_state_dicts=None):
try:
@ -486,6 +501,17 @@ def forge_loader(sd, additional_state_dicts=None):
except:
raise ValueError('Failed to recognize model type!')
if not chroma_is_in_huggingface_guess \
and estimated_config.huggingface_repo == "black-forest-labs/FLUX.1-schnell" \
and "transformer" in state_dicts \
and "distilled_guidance_layer.layers.0.in_layer.bias" in state_dicts["transformer"]:
estimated_config.huggingface_repo = GuessChroma.huggingface_repo
for x in GuessChroma.unet_extra_config:
estimated_config.unet_config[x] = GuessChroma.unet_extra_config[x]
for x in GuessChroma.unet_remove_config:
del estimated_config.unet_config[x]
state_dicts['text_encoder'] = state_dicts['text_encoder_2']
del state_dicts['text_encoder_2']
repo_name = estimated_config.huggingface_repo
local_path = os.path.join(dir_path, 'huggingface', repo_name)
@ -540,6 +566,8 @@ def forge_loader(sd, additional_state_dicts=None):
else:
huggingface_components['scheduler'].config.prediction_type = prediction_types.get(estimated_config.model_type.name, huggingface_components['scheduler'].config.prediction_type)
if not chroma_is_in_huggingface_guess and estimated_config.huggingface_repo == "Chroma":
return Chroma(estimated_config=estimated_config, huggingface_components=huggingface_components)
for M in possible_models:
if any(isinstance(estimated_config, x) for x in M.matched_guesses):
return M(estimated_config=estimated_config, huggingface_components=huggingface_components)

307
backend/nn/chroma.py Normal file
View File

@ -0,0 +1,307 @@
# implementation of Chroma for Forge, inspired by https://github.com/lodestone-rock/ComfyUI_FluxMod
from dataclasses import dataclass
import math
import torch
from torch import nn
from einops import rearrange, repeat
from backend.attention import attention_function
from backend.utils import fp16_fix, tensor2parameter
from backend.nn.flux import attention, rope, timestep_embedding, EmbedND, MLPEmbedder, RMSNorm, QKNorm, SelfAttention
class Approximator(nn.Module):
def __init__(self, in_dim: int, out_dim: int, hidden_dim: int, n_layers = 4):
super().__init__()
self.in_proj = nn.Linear(in_dim, hidden_dim, bias=True)
self.layers = nn.ModuleList([MLPEmbedder(hidden_dim, hidden_dim) for x in range( n_layers)])
self.norms = nn.ModuleList([RMSNorm( hidden_dim) for x in range( n_layers)])
self.out_proj = nn.Linear(hidden_dim, out_dim)
def forward(self, x):
x = self.in_proj(x)
for layer, norms in zip(self.layers, self.norms):
x = x + layer(norms(x))
x = self.out_proj(x)
return x
@dataclass
class ModulationOut:
shift: torch.Tensor
scale: torch.Tensor
gate: torch.Tensor
class DoubleStreamBlock(nn.Module):
def __init__(self, hidden_size, num_heads, mlp_ratio, qkv_bias=False):
super().__init__()
mlp_hidden_dim = int(hidden_size * mlp_ratio)
self.num_heads = num_heads
self.hidden_size = hidden_size
self.img_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.img_attn = SelfAttention(dim=hidden_size, num_heads=num_heads, qkv_bias=qkv_bias)
self.img_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.img_mlp = nn.Sequential(
nn.Linear(hidden_size, mlp_hidden_dim, bias=True),
nn.GELU(approximate="tanh"),
nn.Linear(mlp_hidden_dim, hidden_size, bias=True),
)
self.txt_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.txt_attn = SelfAttention(dim=hidden_size, num_heads=num_heads, qkv_bias=qkv_bias)
self.txt_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.txt_mlp = nn.Sequential(
nn.Linear(hidden_size, mlp_hidden_dim, bias=True),
nn.GELU(approximate="tanh"),
nn.Linear(mlp_hidden_dim, hidden_size, bias=True),
)
def forward(self, img, txt, mod, pe):
(img_mod1, img_mod2), (txt_mod1, txt_mod2) = mod
img_modulated = self.img_norm1(img)
img_modulated = (1 + img_mod1.scale) * img_modulated + img_mod1.shift
img_qkv = self.img_attn.qkv(img_modulated)
B, L, _ = img_qkv.shape
H = self.num_heads
D = img_qkv.shape[-1] // (3 * H)
img_q, img_k, img_v = img_qkv.view(B, L, 3, H, D).permute(2, 0, 3, 1, 4)
img_q, img_k = self.img_attn.norm(img_q, img_k, img_v)
txt_modulated = self.txt_norm1(txt)
txt_modulated = (1 + txt_mod1.scale) * txt_modulated + txt_mod1.shift
txt_qkv = self.txt_attn.qkv(txt_modulated)
B, L, _ = txt_qkv.shape
txt_q, txt_k, txt_v = txt_qkv.view(B, L, 3, H, D).permute(2, 0, 3, 1, 4)
txt_q, txt_k = self.txt_attn.norm(txt_q, txt_k, txt_v)
q = torch.cat((txt_q, img_q), dim=2)
k = torch.cat((txt_k, img_k), dim=2)
v = torch.cat((txt_v, img_v), dim=2)
attn = attention(q, k, v, pe=pe)
txt_attn, img_attn = attn[:, :txt.shape[1]], attn[:, txt.shape[1]:]
img = img + img_mod1.gate * self.img_attn.proj(img_attn)
img = img + img_mod2.gate * self.img_mlp((1 + img_mod2.scale) * self.img_norm2(img) + img_mod2.shift)
txt = txt + txt_mod1.gate * self.txt_attn.proj(txt_attn)
txt = txt + txt_mod2.gate * self.txt_mlp((1 + txt_mod2.scale) * self.txt_norm2(txt) + txt_mod2.shift)
txt = fp16_fix(txt)
return img, txt
class SingleStreamBlock(nn.Module):
def __init__(self, hidden_size, num_heads, mlp_ratio=4.0, qk_scale=None):
super().__init__()
self.hidden_dim = hidden_size
self.num_heads = num_heads
head_dim = hidden_size // num_heads
self.scale = qk_scale or head_dim ** -0.5
self.mlp_hidden_dim = int(hidden_size * mlp_ratio)
self.linear1 = nn.Linear(hidden_size, hidden_size * 3 + self.mlp_hidden_dim)
self.linear2 = nn.Linear(hidden_size + self.mlp_hidden_dim, hidden_size)
self.norm = QKNorm(head_dim)
self.hidden_size = hidden_size
self.pre_norm = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.mlp_act = nn.GELU(approximate="tanh")
def forward(self, x, mod, pe):
x_mod = (1 + mod.scale) * self.pre_norm(x) + mod.shift
qkv, mlp = torch.split(self.linear1(x_mod), [3 * self.hidden_size, self.mlp_hidden_dim], dim=-1)
del x_mod
# q, k, v = rearrange(qkv, "B L (K H D) -> K B H L D", K=3, H=self.num_heads)
qkv = qkv.view(qkv.size(0), qkv.size(1), 3, self.num_heads, self.hidden_size // self.num_heads)
q, k, v = qkv.permute(2, 0, 3, 1, 4)
del qkv
q, k = self.norm(q, k, v)
attn = attention(q, k, v, pe=pe)
del q, k, v, pe
output = self.linear2(torch.cat((attn, self.mlp_act(mlp)), dim=2))
del attn, mlp
x = x + mod.gate * output
x = fp16_fix(x)
return x
class LastLayer(nn.Module):
def __init__(self, hidden_size, patch_size, out_channels):
super().__init__()
self.norm_final = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
self.linear = nn.Linear(hidden_size, patch_size * patch_size * out_channels, bias=True)
def forward(self, x, mod):
shift, scale = mod
shift = shift.squeeze(1)
scale = scale.squeeze(1)
x = (1 + scale[:, None, :]) * self.norm_final(x) + shift[:, None, :]
x = self.linear(x)
return x
class IntegratedChromaTransformer2DModel(nn.Module):
def __init__(self, in_channels: int, vec_in_dim: int, context_in_dim: int, hidden_size: int, mlp_ratio: float, num_heads: int, depth: int, depth_single_blocks: int, axes_dim: list[int], theta: int, qkv_bias: bool, guidance_out_dim: int, guidance_hidden_dim: int, guidance_n_layers: int):
super().__init__()
self.in_channels = in_channels * 4
self.out_channels = self.in_channels
if hidden_size % num_heads != 0:
raise ValueError(f"Hidden size {hidden_size} must be divisible by num_heads {num_heads}")
pe_dim = hidden_size // num_heads
if sum(axes_dim) != pe_dim:
raise ValueError(f"Got {axes_dim} but expected positional dim {pe_dim}")
self.hidden_size = hidden_size
self.num_heads = num_heads
self.pe_embedder = EmbedND(dim=pe_dim, theta=theta, axes_dim=axes_dim)
self.img_in = nn.Linear(self.in_channels, self.hidden_size, bias=True)
self.distilled_guidance_layer = Approximator(64, guidance_out_dim, guidance_hidden_dim, guidance_n_layers)
self.txt_in = nn.Linear(context_in_dim, self.hidden_size)
self.double_blocks = nn.ModuleList(
[
DoubleStreamBlock(
self.hidden_size,
self.num_heads,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
)
for _ in range(depth)
]
)
self.single_blocks = nn.ModuleList(
[
SingleStreamBlock(self.hidden_size, self.num_heads, mlp_ratio=mlp_ratio)
for _ in range(depth_single_blocks)
]
)
self.final_layer = LastLayer(self.hidden_size, 1, self.out_channels)
@staticmethod
def distribute_modulations(tensor, single_block_count: int = 38, double_blocks_count: int = 19):
"""
Distributes slices of the tensor into the block_dict as ModulationOut objects.
Args:
tensor (torch.Tensor): Input tensor with shape [batch_size, vectors, dim].
"""
batch_size, vectors, dim = tensor.shape
block_dict = {}
for i in range(single_block_count):
key = f"single_blocks.{i}.modulation.lin"
block_dict[key] = None
for i in range(double_blocks_count):
key = f"double_blocks.{i}.img_mod.lin"
block_dict[key] = None
for i in range(double_blocks_count):
key = f"double_blocks.{i}.txt_mod.lin"
block_dict[key] = None
block_dict["final_layer.adaLN_modulation.1"] = None
idx = 0 # Index to keep track of the vector slices
for key in block_dict.keys():
if "single_blocks" in key:
# Single block: 1 ModulationOut
block_dict[key] = ModulationOut(
shift=tensor[:, idx:idx+1, :],
scale=tensor[:, idx+1:idx+2, :],
gate=tensor[:, idx+2:idx+3, :]
)
idx += 3 # Advance by 3 vectors
elif "img_mod" in key:
# Double block: List of 2 ModulationOut
double_block = []
for _ in range(2): # Create 2 ModulationOut objects
double_block.append(
ModulationOut(
shift=tensor[:, idx:idx+1, :],
scale=tensor[:, idx+1:idx+2, :],
gate=tensor[:, idx+2:idx+3, :]
)
)
idx += 3 # Advance by 3 vectors per ModulationOut
block_dict[key] = double_block
elif "txt_mod" in key:
# Double block: List of 2 ModulationOut
double_block = []
for _ in range(2): # Create 2 ModulationOut objects
double_block.append(
ModulationOut(
shift=tensor[:, idx:idx+1, :],
scale=tensor[:, idx+1:idx+2, :],
gate=tensor[:, idx+2:idx+3, :]
)
)
idx += 3 # Advance by 3 vectors per ModulationOut
block_dict[key] = double_block
elif "final_layer" in key:
# Final layer: 1 ModulationOut
block_dict[key] = [
tensor[:, idx:idx+1, :],
tensor[:, idx+1:idx+2, :],
]
idx += 2 # Advance by 2 vectors
return block_dict
def inner_forward(self, img, img_ids, txt, txt_ids, timesteps):
if img.ndim != 3 or txt.ndim != 3:
raise ValueError("Input img and txt tensors must have 3 dimensions.")
img = self.img_in(img)
device = img.device
dtype = img.dtype # torch.bfloat16
nb_double_block = len(self.double_blocks)
nb_single_block = len(self.single_blocks)
mod_index_length = nb_double_block*12 + nb_single_block*3 + 2
distill_timestep = timestep_embedding(timesteps.detach().clone(), 16).to(device=device, dtype=dtype)
distil_guidance = timestep_embedding(torch.zeros_like(timesteps), 16).to(device=device, dtype=dtype)
modulation_index = timestep_embedding(torch.arange(mod_index_length), 32).to(device=device, dtype=dtype)
modulation_index = modulation_index.unsqueeze(0).repeat(img.shape[0], 1, 1)
timestep_guidance = torch.cat([distill_timestep, distil_guidance], dim=1).unsqueeze(1).repeat(1, mod_index_length, 1)
input_vec = torch.cat([timestep_guidance, modulation_index], dim=-1)
mod_vectors = self.distilled_guidance_layer(input_vec)
mod_vectors_dict = self.distribute_modulations(mod_vectors, nb_single_block, nb_double_block)
txt = self.txt_in(txt)
ids = torch.cat((txt_ids, img_ids), dim=1)
del txt_ids, img_ids
pe = self.pe_embedder(ids)
del ids
for i, block in enumerate(self.double_blocks):
img_mod = mod_vectors_dict[f"double_blocks.{i}.img_mod.lin"]
txt_mod = mod_vectors_dict[f"double_blocks.{i}.txt_mod.lin"]
double_mod = [img_mod, txt_mod]
img, txt = block(img=img, txt=txt, mod=double_mod, pe=pe)
img = torch.cat((txt, img), 1)
for i, block in enumerate(self.single_blocks):
single_mod = mod_vectors_dict[f"single_blocks.{i}.modulation.lin"]
img = block(img, mod=single_mod, pe=pe)
del pe
img = img[:, txt.shape[1]:, ...]
final_mod = mod_vectors_dict["final_layer.adaLN_modulation.1"]
img = self.final_layer(img, final_mod)
return img
def forward(self, x, timestep, context, **kwargs):
bs, c, h, w = x.shape
input_device = x.device
input_dtype = x.dtype
patch_size = 2
pad_h = (patch_size - x.shape[-2] % patch_size) % patch_size
pad_w = (patch_size - x.shape[-1] % patch_size) % patch_size
x = torch.nn.functional.pad(x, (0, pad_w, 0, pad_h), mode="circular")
img = rearrange(x, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=patch_size, pw=patch_size)
del x, pad_h, pad_w
h_len = ((h + (patch_size // 2)) // patch_size)
w_len = ((w + (patch_size // 2)) // patch_size)
img_ids = torch.zeros((h_len, w_len, 3), device=input_device, dtype=input_dtype)
img_ids[..., 1] = img_ids[..., 1] + torch.linspace(0, h_len - 1, steps=h_len, device=input_device, dtype=input_dtype)[:, None]
img_ids[..., 2] = img_ids[..., 2] + torch.linspace(0, w_len - 1, steps=w_len, device=input_device, dtype=input_dtype)[None, :]
img_ids = repeat(img_ids, "h w c -> b (h w) c", b=bs)
txt_ids = torch.zeros((bs, context.shape[1], 3), device=input_device, dtype=input_dtype)
del input_device, input_dtype
out = self.inner_forward(img, img_ids, context, txt_ids, timestep)
del img, img_ids, txt_ids, timestep, context
out = rearrange(out, "b (h w) (c ph pw) -> b c (h ph) (w pw)", h=h_len, w=w_len, ph=2, pw=2)[:, :, :h, :w]
del h_len, w_len, bs
return out