Instructions to use intel-ai/Z-Image-Turbo-MXFP8-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use intel-ai/Z-Image-Turbo-MXFP8-AutoRound with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("intel-ai/Z-Image-Turbo-MXFP8-AutoRound", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Replace RTN checkpoint with SignRound, 200 iterations
Browse files- README.md +42 -33
- aqa_export_repair.json +0 -6
- model_index.json +1 -1
- text_encoder/config.json +47 -6
- text_encoder/generation_config.json +0 -13
- text_encoder/model-00002-of-00003.safetensors +0 -3
- text_encoder/{model-00003-of-00003.safetensors → model.safetensors} +2 -2
- text_encoder/model.safetensors.index.json +0 -405
- tokenizer/tokenizer.json +2 -2
- transformer/config.json +3 -4
- transformer/{model-00001-of-00007.safetensors → model-00001-of-00002.safetensors} +2 -2
- text_encoder/model-00001-of-00003.safetensors → transformer/model-00002-of-00002.safetensors +2 -2
- transformer/model-00002-of-00007.safetensors +0 -3
- transformer/model-00003-of-00007.safetensors +0 -3
- transformer/model-00004-of-00007.safetensors +0 -3
- transformer/model-00005-of-00007.safetensors +0 -3
- transformer/model-00006-of-00007.safetensors +0 -3
- transformer/model-00007-of-00007.safetensors +0 -3
- transformer/model.safetensors.index.json +0 -0
- transformer/quantization_config.json +2 -3
- vae/config.json +1 -1
README.md
CHANGED
|
@@ -2,64 +2,73 @@
|
|
| 2 |
base_model:
|
| 3 |
- Tongyi-MAI/Z-Image-Turbo
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
-
license:
|
| 6 |
tags:
|
| 7 |
- quantized
|
| 8 |
- mxfp8
|
| 9 |
-
-
|
|
|
|
| 10 |
- diffusion
|
| 11 |
- text-to-image
|
| 12 |
-
- autoquant-agent
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# Z-Image-Turbo-MXFP8-
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
| 22 |
-
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
|
| 34 |
## Evaluation
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
-
|
|
| 39 |
-
|---|---|---|
|
| 40 |
-
|
|
| 41 |
-
|
|
| 42 |
-
| DrawBench ImageReward | 1.00 | 0.97 |
|
| 43 |
-
| GenEval | 0.757 | 0.760 |
|
| 44 |
|
| 45 |
-
|
|
|
|
|
|
|
| 46 |
|
| 47 |
## Usage
|
| 48 |
|
|
|
|
|
|
|
| 49 |
```python
|
| 50 |
from vllm_omni.entrypoints.omni import Omni
|
| 51 |
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
|
| 52 |
|
| 53 |
-
omni = Omni(model="INCModel3/Z-Image-Turbo-MXFP8-RTN-AutoRound"
|
| 54 |
params = OmniDiffusionSamplingParams(
|
| 55 |
-
height=1024,
|
| 56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
)
|
| 58 |
-
out = omni.generate("a red bench in a park", sampling_params_list=[params])
|
| 59 |
```
|
| 60 |
|
| 61 |
-
|
| 62 |
|
| 63 |
-
|
| 64 |
|
| 65 |
-
|
|
|
|
| 2 |
base_model:
|
| 3 |
- Tongyi-MAI/Z-Image-Turbo
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
+
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- quantized
|
| 8 |
- mxfp8
|
| 9 |
+
- auto-round
|
| 10 |
+
- signround
|
| 11 |
- diffusion
|
| 12 |
- text-to-image
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Z-Image-Turbo-MXFP8-AutoRound
|
| 16 |
|
| 17 |
+
An MXFP8 quantization of [Tongyi-MAI/Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo), made with [AutoRound](https://github.com/intel/auto-round) using SignRound with 200 optimization iterations.
|
| 18 |
|
| 19 |
+
## Quantization
|
| 20 |
|
| 21 |
+
| Setting | Value |
|
| 22 |
+
|---|---|
|
| 23 |
+
| Method | AutoRound SignRound |
|
| 24 |
+
| Iterations | 200 |
|
| 25 |
+
| Format | MXFP8 W8A8, group size 32 |
|
| 26 |
+
| Quantized component | Diffusion transformer |
|
| 27 |
+
| Excluded layers | `adaLN_modulation` |
|
| 28 |
+
| Text encoder and VAE | BF16, not quantized |
|
| 29 |
+
| Calibration data | 128 prompts from OpenS2V |
|
| 30 |
+
| Calibration steps | 8 |
|
| 31 |
+
| Calibration guidance scale | 7.5 |
|
| 32 |
+
| AutoRound version recorded in export | 0.17.0 |
|
| 33 |
|
| 34 |
## Evaluation
|
| 35 |
|
| 36 |
+
DrawBench, 200 prompts, one image per prompt. Images were generated with official vLLM 0.32.0 and vLLM-Omni 0.32.0 on an NVIDIA B200: 1024×1024, 8 steps, guidance scale 0.0, seed `42 + prompt_id`.
|
| 37 |
|
| 38 |
+
| Model | CLIP ↑ | CLIP-IQA ↑ | ImageReward ↑ |
|
| 39 |
+
|---|---:|---:|---:|
|
| 40 |
+
| BF16 | 31.7831 | 70.6414 | 1.0073 |
|
| 41 |
+
| MXFP8 SignRound, 200 iterations | 31.7907 | 70.3976 | 0.9916 |
|
|
|
|
|
|
|
| 42 |
|
| 43 |
+
CLIP uses `openai/clip-vit-base-patch32`. CLIP-IQA averages three positive/negative prompt pairs. Both are reported on a 0–100 scale. ImageReward uses ImageReward-v1.0.
|
| 44 |
+
|
| 45 |
+
These results cover this DrawBench run, not all prompts or benchmarks. GenEval has not been evaluated for this checkpoint.
|
| 46 |
|
| 47 |
## Usage
|
| 48 |
|
| 49 |
+
Tested with vLLM 0.32.0 and vLLM-Omni 0.32.0.
|
| 50 |
+
|
| 51 |
```python
|
| 52 |
from vllm_omni.entrypoints.omni import Omni
|
| 53 |
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
|
| 54 |
|
| 55 |
+
omni = Omni(model="INCModel3/Z-Image-Turbo-MXFP8-RTN-AutoRound")
|
| 56 |
params = OmniDiffusionSamplingParams(
|
| 57 |
+
height=1024,
|
| 58 |
+
width=1024,
|
| 59 |
+
seed=42,
|
| 60 |
+
guidance_scale=0.0,
|
| 61 |
+
num_inference_steps=8,
|
| 62 |
+
num_outputs_per_prompt=1,
|
| 63 |
+
)
|
| 64 |
+
outputs = omni.generate(
|
| 65 |
+
{"prompt": "A red bench in a park", "modalities": ["image"]},
|
| 66 |
+
sampling_params_list=[params],
|
| 67 |
)
|
|
|
|
| 68 |
```
|
| 69 |
|
| 70 |
+
Quantization settings are stored in the transformer checkpoint. Do not pass a global MXFP8 override for the whole pipeline: the text encoder and VAE remain BF16.
|
| 71 |
|
| 72 |
+
## License
|
| 73 |
|
| 74 |
+
Apache 2.0, following the [base model](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).
|
aqa_export_repair.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"repaired_components": [
|
| 3 |
-
"text_encoder"
|
| 4 |
-
],
|
| 5 |
-
"source": "/models/Z-Image-Turbo"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model_index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "ZImagePipeline",
|
| 3 |
"_diffusers_version": "0.40.0",
|
| 4 |
-
"_name_or_path": "/
|
| 5 |
"scheduler": [
|
| 6 |
"diffusers",
|
| 7 |
"FlowMatchEulerDiscreteScheduler"
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "ZImagePipeline",
|
| 3 |
"_diffusers_version": "0.40.0",
|
| 4 |
+
"_name_or_path": "/home/changwa1/Z-Image-Turbo",
|
| 5 |
"scheduler": [
|
| 6 |
"diffusers",
|
| 7 |
"FlowMatchEulerDiscreteScheduler"
|
text_encoder/config.json
CHANGED
|
@@ -1,30 +1,71 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
|
|
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 2560,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 9728,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"max_position_embeddings": 40960,
|
| 15 |
"max_window_layers": 36,
|
| 16 |
"model_type": "qwen3",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
"num_hidden_layers": 36,
|
| 19 |
"num_key_value_heads": 8,
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
-
"
|
| 22 |
-
|
|
|
|
|
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": true,
|
| 25 |
-
"
|
| 26 |
-
"transformers_version": "4.51.0",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 151936
|
| 30 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen3Model"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 2560,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
"max_position_embeddings": 40960,
|
| 54 |
"max_window_layers": 36,
|
| 55 |
"model_type": "qwen3",
|
| 56 |
"num_attention_heads": 32,
|
| 57 |
"num_hidden_layers": 36,
|
| 58 |
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": null,
|
| 60 |
"rms_norm_eps": 1e-06,
|
| 61 |
+
"rope_parameters": {
|
| 62 |
+
"rope_theta": 1000000,
|
| 63 |
+
"rope_type": "default"
|
| 64 |
+
},
|
| 65 |
"sliding_window": null,
|
| 66 |
"tie_word_embeddings": true,
|
| 67 |
+
"transformers_version": "5.14.1",
|
|
|
|
| 68 |
"use_cache": true,
|
| 69 |
"use_sliding_window": false,
|
| 70 |
"vocab_size": 151936
|
| 71 |
+
}
|
text_encoder/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 151643,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
151645,
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 151643,
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_k": 20,
|
| 11 |
-
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.51.0"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
text_encoder/model-00002-of-00003.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6cd087b316306a68c562436b5492edbcf6e16c6dba3a1308279caa5a58e21ca5
|
| 3 |
-
size 3987450520
|
|
|
|
|
|
|
|
|
|
|
|
text_encoder/{model-00003-of-00003.safetensors → model.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3096dd368271973428bd24fcc773b8a57fe3b3bb5ea2b7320caa7f375113d79
|
| 3 |
+
size 8044982080
|
text_encoder/model.safetensors.index.json
DELETED
|
@@ -1,405 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_size": 8044936192
|
| 4 |
-
},
|
| 5 |
-
"weight_map": {
|
| 6 |
-
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 7 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 8 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 9 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 12 |
-
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
-
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 16 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 19 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
-
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 24 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
-
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
-
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 30 |
-
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
-
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
-
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 35 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
-
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 39 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
-
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 41 |
-
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 42 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
-
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 44 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 45 |
-
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
-
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 49 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 50 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 51 |
-
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 52 |
-
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 54 |
-
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 56 |
-
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 57 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 58 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 59 |
-
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 60 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 61 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 62 |
-
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 63 |
-
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
-
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 66 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 67 |
-
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 68 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 70 |
-
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 71 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 72 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 73 |
-
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 74 |
-
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 75 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 76 |
-
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 77 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 78 |
-
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 79 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 80 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 81 |
-
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 82 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 83 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 84 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 87 |
-
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 88 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 89 |
-
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 90 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 91 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 92 |
-
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 93 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 94 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 95 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 96 |
-
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
-
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 100 |
-
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 101 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
-
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 104 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 107 |
-
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
-
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 111 |
-
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
-
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 115 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
-
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
-
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
-
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
-
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 123 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
-
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
-
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 129 |
-
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 133 |
-
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 135 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
-
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 137 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 140 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 141 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 142 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 143 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 144 |
-
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 145 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 146 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 147 |
-
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 148 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 149 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 150 |
-
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 151 |
-
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
-
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 154 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 155 |
-
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 156 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 157 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
-
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 159 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
-
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 162 |
-
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
-
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 165 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
-
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 167 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
-
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 171 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
-
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 173 |
-
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 174 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
-
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 176 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 177 |
-
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
-
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 181 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 182 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 183 |
-
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 184 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 186 |
-
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 188 |
-
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 189 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 190 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
-
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 192 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
-
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 195 |
-
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
-
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 198 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 199 |
-
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 200 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 202 |
-
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 203 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
-
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 207 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
-
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 210 |
-
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 211 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 212 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
-
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
-
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 217 |
-
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 218 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 219 |
-
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 221 |
-
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 222 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 224 |
-
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 225 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 226 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
-
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 228 |
-
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 230 |
-
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 231 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 232 |
-
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 233 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 234 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
-
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 236 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 238 |
-
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 239 |
-
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
-
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
-
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 242 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 243 |
-
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 244 |
-
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 246 |
-
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 247 |
-
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 248 |
-
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
-
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
-
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
-
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
-
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
-
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 255 |
-
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
-
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 258 |
-
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
-
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 260 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
-
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 266 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
-
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 269 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 270 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
-
"model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 272 |
-
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
-
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 274 |
-
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 275 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 276 |
-
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 277 |
-
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 278 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 279 |
-
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 280 |
-
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 281 |
-
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 282 |
-
"model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 283 |
-
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 284 |
-
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 285 |
-
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 286 |
-
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 287 |
-
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 288 |
-
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 289 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 290 |
-
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 291 |
-
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 292 |
-
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 293 |
-
"model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 294 |
-
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 295 |
-
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 296 |
-
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 297 |
-
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 298 |
-
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 299 |
-
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 300 |
-
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 301 |
-
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 302 |
-
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 303 |
-
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 304 |
-
"model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 305 |
-
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 306 |
-
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 307 |
-
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 308 |
-
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 309 |
-
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 310 |
-
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 311 |
-
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 312 |
-
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 313 |
-
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 314 |
-
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 315 |
-
"model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 316 |
-
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 317 |
-
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 318 |
-
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 319 |
-
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 320 |
-
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 321 |
-
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
-
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 323 |
-
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 324 |
-
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 325 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
-
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 327 |
-
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
-
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 329 |
-
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 330 |
-
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 331 |
-
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 332 |
-
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 333 |
-
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 334 |
-
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 335 |
-
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 336 |
-
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 337 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 338 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 339 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 340 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 341 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 342 |
-
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 343 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 344 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 345 |
-
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 346 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 347 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 348 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 349 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 350 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 351 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 352 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 353 |
-
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 354 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 355 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 356 |
-
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 357 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 358 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 359 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 360 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 361 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 362 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 363 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 364 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 365 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 366 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 367 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 368 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 369 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 370 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 371 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 374 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 375 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 376 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 378 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 379 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 380 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 387 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 390 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 392 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 393 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 394 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 397 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 399 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 401 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 402 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
-
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 404 |
-
}
|
| 405 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7029094cd70eca33e2f5d6837051bd1b63789ebde3c05bcce93b0fb31c094a85
|
| 3 |
+
size 11422928
|
transformer/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "ZImageTransformer2DModel",
|
| 3 |
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
-
"_name_or_path": "/
|
| 5 |
"_use_default_values": [
|
| 6 |
"siglip_feat_dim"
|
| 7 |
],
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"act_dynamic": true,
|
| 37 |
"act_group_size": 32,
|
| 38 |
"act_sym": true,
|
| 39 |
-
"autoround_version": "0.
|
| 40 |
"bits": 8,
|
| 41 |
"block_name_to_quantize": "noise_refiner,context_refiner,layers",
|
| 42 |
"data_type": "mx_fp",
|
|
@@ -247,11 +247,10 @@
|
|
| 247 |
"data_type": "float"
|
| 248 |
}
|
| 249 |
},
|
|
|
|
| 250 |
"group_size": 32,
|
| 251 |
"packing_format": "auto_round:llm_compressor",
|
| 252 |
"quant_method": "auto-round",
|
| 253 |
-
"static_attention_granularity": "tensor",
|
| 254 |
-
"static_kv_granularity": "tensor",
|
| 255 |
"sym": true
|
| 256 |
},
|
| 257 |
"rope_theta": 256.0,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "ZImageTransformer2DModel",
|
| 3 |
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"_name_or_path": "/home/changwa1/Z-Image-Turbo/transformer",
|
| 5 |
"_use_default_values": [
|
| 6 |
"siglip_feat_dim"
|
| 7 |
],
|
|
|
|
| 36 |
"act_dynamic": true,
|
| 37 |
"act_group_size": 32,
|
| 38 |
"act_sym": true,
|
| 39 |
+
"autoround_version": "0.17.0",
|
| 40 |
"bits": 8,
|
| 41 |
"block_name_to_quantize": "noise_refiner,context_refiner,layers",
|
| 42 |
"data_type": "mx_fp",
|
|
|
|
| 247 |
"data_type": "float"
|
| 248 |
}
|
| 249 |
},
|
| 250 |
+
"gradient_accumulate_steps": 8,
|
| 251 |
"group_size": 32,
|
| 252 |
"packing_format": "auto_round:llm_compressor",
|
| 253 |
"quant_method": "auto-round",
|
|
|
|
|
|
|
| 254 |
"sym": true
|
| 255 |
},
|
| 256 |
"rope_theta": 256.0,
|
transformer/{model-00001-of-00007.safetensors → model-00001-of-00002.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f75ec0161c7bd9842ad051d44b7f146bc7a8f665af6dbdef4959087138cd15
|
| 3 |
+
size 5361184144
|
text_encoder/model-00001-of-00003.safetensors → transformer/model-00002-of-00002.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db7852fa2bad76541b312470455dc0f9e24bb0e94520f3db519ef869a3a0a6b5
|
| 3 |
+
size 1120518384
|
transformer/model-00002-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a7f0a65ac384a2285e38e49da97e9f10828894c55c3d78ca2f9cfc1c0f25cbd1
|
| 3 |
-
size 1071468816
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model-00003-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:21cd403f404aa3399b9f9cb126a1a001b9b83c28dc5dd83c563af997efc1c6b1
|
| 3 |
-
size 1063541800
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model-00004-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d1e2ba177fd9a91c528246b048074aa071b2f1dcf5623f0582d9c359f6080ecd
|
| 3 |
-
size 1061331568
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model-00005-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:28b5739fe454635f00d8f2ea6e657e7b5c37d83a67c0035e5ebefa490337f546
|
| 3 |
-
size 1073711064
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model-00006-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d2a086a3bb9d48da20c987385039caa5b3e05a4a73060e6bc5e984f811709b72
|
| 3 |
-
size 1061299744
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model-00007-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5c58f1b6c8bf15e5b99630650f0a54c6974f37ea3a04c4cd3f133a945ff8b463
|
| 3 |
-
size 104807384
|
|
|
|
|
|
|
|
|
|
|
|
transformer/model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/quantization_config.json
CHANGED
|
@@ -9,9 +9,8 @@
|
|
| 9 |
"act_sym": true,
|
| 10 |
"act_dynamic": true,
|
| 11 |
"enable_quanted_input": false,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"autoround_version": "0.15.0",
|
| 15 |
"block_name_to_quantize": "noise_refiner,context_refiner,layers",
|
| 16 |
"quant_method": "auto-round",
|
| 17 |
"packing_format": "auto_round:llm_compressor",
|
|
|
|
| 9 |
"act_sym": true,
|
| 10 |
"act_dynamic": true,
|
| 11 |
"enable_quanted_input": false,
|
| 12 |
+
"gradient_accumulate_steps": 8,
|
| 13 |
+
"autoround_version": "0.17.0",
|
|
|
|
| 14 |
"block_name_to_quantize": "noise_refiner,context_refiner,layers",
|
| 15 |
"quant_method": "auto-round",
|
| 16 |
"packing_format": "auto_round:llm_compressor",
|
vae/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
"_diffusers_version": "0.40.0",
|
| 4 |
-
"_name_or_path": "/
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
"_diffusers_version": "0.40.0",
|
| 4 |
+
"_name_or_path": "/home/changwa1/Z-Image-Turbo/vae",
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|