Delta-Vector
/

SD-prompter-4B-V0.2

Safetensors

llama

tool

stable-diffusion

Model card Files Files and versions Community

Delta-Vector commited on 11 days ago

Commit

e1f8d1d

verified ·

1 Parent(s): 0eae1e1

Upload README.md

Browse files

Files changed (1) hide show

README.md +172 -0

README.md ADDED Viewed

	@@ -0,0 +1,172 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Model README</title>
+    <style>
+        body {
+            background: linear-gradient(-45deg, #0a0a0a, #121212, #1a1a1a);
+            color: #E0E0E0;
+            font-family: 'Segoe UI', system-ui;
+            margin: 0;
+            padding: 20px;
+            min-height: 100vh;
+            animation: gradient 15s ease infinite;
+            background-size: 400% 400%;
+            text-align: center;
+        }
+        @keyframes gradient {
+            0% { background-position: 0% 50%; }
+            50% { background-position: 100% 50%; }
+            100% { background-position: 0% 50%; }
+        }
+        .container {
+            max-width: 800px;
+            margin: auto;
+        }
+        .model-image {
+            width: 100%;
+            border-radius: 12px;
+            filter: drop-shadow(0 0 10px rgba(255, 255, 255, 0.1));
+            animation: float 6s ease-in-out infinite;
+        }
+        @keyframes float {
+            0%, 100% { transform: translateY(0); }
+            50% { transform: translateY(-20px); }
+        }
+        .box {
+            background: rgba(30, 30, 30, 0.9);
+            border-radius: 12px;
+            padding: 20px;
+            margin: 25px 0;
+            backdrop-filter: blur(10px);
+            border: 1px solid rgba(255, 255, 255, 0.1);
+            text-align: left;
+        }
+        h2 {
+            border-left: 4px solid #0ff;
+            padding-left: 15px;
+            margin: 0 0 15px 0;
+            background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.1));
+            text-transform: uppercase;
+            letter-spacing: 2px;
+            color: #fff;
+        }
+        .yaml-content {
+            background: #191919;
+            border-radius: 8px;
+            padding: 10px;
+            margin-top: 10px;
+            font-family: monospace;
+            white-space: pre-wrap;
+            color: #E0E0E0;
+            border-left: 4px solid #0ff;
+        }
+        /* Custom Scrollbar */
+        ::-webkit-scrollbar { width: 8px; }
+        ::-webkit-scrollbar-track { background: #121212; }
+        ::-webkit-scrollbar-thumb {
+            background: #333;
+            border-radius: 4px;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/tqI2XfovbkA_0ss6IKlPq.png" class="model-image" alt="Model Visualization">
+        <div class="box">
+            <h2>🔍 Overview</h2>
+            <p>This is the second in a line of models dedicated to creating Stable-Diffusion prompts when given a character appearance. Made for the CharGen Project, This has been finetuned ontop of Delta-Vector/Holland-4B-V1</>
+        </div>
+        <div class="box">
+            <h2>⚖️ Quants</h2>
+            <p>Available quantization formats:</p>
+            <ul>
+                <li>GGUF: https://huggingface.co/mradermacher/SDPrompter4b-GGUF</li>
+                <li>EXL2: https://huggingface.co/</li>
+            </ul>
+        </div>
+        <div class="box">
+            <h2>💬 Prompting</h2>
+            <p><strong>Recommended format: ChatML, Use the following system prompt for the model. I'd advise against setting a high amount of output tokens as the model loops, use 0.1 min-p and temp-1 to keep it coherent.</strong></p>
+            <code>Create a prompt for Stable Diffusion based on the information below.</code>
+        </div>
+        <div class="box">
+            <h2>🌟 Credits</h2>
+            <p>Finetuned on 1xRTX6000 provided by Kubernetes_bad, All credits goes to Kubernetes_bad, LucyKnada and the rest of Anthracite.</p>
+        </div>
+        <div class="box">
+            <h2>🛠️ Axolotl Config)</h2>
+                <pre>
+base_model: Delta-Vector/Holland-4B-V1
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+datasets:
+  - path: NewEden/CivitAI-SD-Prompts
+datasets:
+  - path: NewEden/CivitAI-Prompts-Sharegpt
+    type: chat_template
+    chat_template: chatml
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+dataset_prepared_path:
+val_set_size: 0.02
+output_dir: ./outputs/out2
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+wandb_project: SDprompter-final
+wandb_entity:
+wandb_watch:
+wandb_name: SDprompter-final
+wandb_log_model:
+gradient_accumulation_steps: 16
+micro_batch_size: 1
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+warmup_ratio: 0.05
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+weight_decay: 0.01
+special_tokens:
+  pad_token: <|finetune_right_pad_id|>
+  eos_token: <|eot_id|>
+auto_resume_from_checkpoints: true
+                </pre>
+            </div>
+        </div>
+    </div>
+</body>
+</html>