Upload folder using huggingface_hub

README.md

@@ -0,0 +1,125 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: peft
+pipeline_tag: text-generation
+language: en
+license: apache-2.0
+tags:
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+- fine-tuned
+datasets:
+- theprint/Zeth
+---
+# Zeth-Gemma3-4B
+
+A fine-tuned Gemma3 4B model, specialized in pragmatic empathy, or perhaps it is empathic pragmatism?
+
+## Model Details
+
+This model is a fine-tuned version of google/gemma-3-4b-it using the Unsloth framework with LoRA (Low-Rank Adaptation) for efficient training.
+
+- **Developed by:** theprint
+- **Model type:** Causal Language Model (Fine-tuned with LoRA)
+- **Language:** en
+- **License:** apache-2.0
+- **Base model:** google/gemma-3-4b-it
+- **Fine-tuning method:** LoRA with rank 128
+
+## Intended Use
+
+Conversation, brainstorming, and general instruction following
+
+## Training Details
+
+### Training Data
+
+The Zeth data set was specifically created for finetuning models on empathic explanation. This was done by taking premade data sets and rewording the replies to be in line with the style for Zeth.
+
+- **Dataset:** theprint/Zeth
+- **Format:** alpaca
+
+### Training Procedure
+
+- **Training epochs:** 3
+- **LoRA rank:** 128
+- **Learning rate:** 0.0002
+- **Batch size:** 4
+- **Framework:** Unsloth + transformers + PEFT
+- **Hardware:** NVIDIA RTX 5090
+
+## Usage
+
+```python
+from unsloth import FastLanguageModel
+import torch
+
+# Load model and tokenizer
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="theprint/Zeth-Gemma3-4B",
+    max_seq_length=4096,
+    dtype=None,
+    load_in_4bit=True,
+)
+
+# Enable inference mode
+FastLanguageModel.for_inference(model)
+
+# Example usage
+inputs = tokenizer(["Your prompt here"], return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+### Alternative Usage (Standard Transformers)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "theprint/Zeth-Gemma3-4B",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("theprint/Zeth-Gemma3-4B")
+
+# Example usage
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Your question here"}
+]
+
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
+outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7, do_sample=True)
+response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
+print(response)
+```
+## Limitations
+
+May hallucinate or provide incorrect information.
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{zeth_gemma3_4b,
+  title={Zeth-Gemma3-4B: Fine-tuned google/gemma-3-4b-it},
+  author={theprint},
+  year={2025},
+  publisher={Hugging Face},
+  url={https://huggingface.co/theprint/Zeth-Gemma3-4B}
+}
+```
+
+## Acknowledgments
+
+- Base model: [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
+- Training dataset: [theprint/Zeth](https://huggingface.co/datasets/theprint/Zeth)
+- Fine-tuning framework: [Unsloth](https://github.com/unslothai/unsloth)
+- Quantization: [llama.cpp](https://github.com/ggerganov/llama.cpp)

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.2",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "float16",
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.53.2"
+}