Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- dnd
+- dungeons-and-dragons
+- rpg
+- text-generation
+- qlora
+- tinyllama
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+pipeline_tag: text-generation
+---
+
+# DM-LLM-Tiny
+
+A tiny (1.1B parameter) language model fine-tuned for **Dungeons & Dragons** content generation.
+
+## What it does
+
+Generates creative D&D content including:
+- **NPCs** — memorable characters with backstories, motivations, and quirks
+- **Quests** — hooks, outlines, and full quest arcs
+- **Dialog** — in-character conversations, monologues, and banter
+- **Locations** — vivid descriptions of dungeons, towns, and wilderness
+- **Encounters** — combat, social, and puzzle encounters
+
+## Usage
+
+### With Ollama (easiest)
+```bash
+ollama run JBHarris/dm-llm-tiny
+```
+
+### With Transformers
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="JBHarris/dm-llm-tiny")
+messages = [
+    {"role": "system", "content": "You are a creative D&D dungeon master's assistant."},
+    {"role": "user", "content": "Create a mysterious NPC for a tavern scene."},
+]
+result = pipe(messages, max_new_tokens=512)
+print(result[0]["generated_text"][-1]["content"])
+```
+
+## Training
+
+- **Base model:** TinyLlama-1.1B-Chat-v1.0
+- **Method:** QLoRA (4-bit NF4 quantization + LoRA r=64)
+- **Data:** ~500 synthetic D&D instruction/response pairs generated with Claude
+- **Hardware:** NVIDIA RTX 4080 16GB
+
+## Limitations
+
+This is a 1.1B parameter model. It's creative and fun for brainstorming but will not match
+the quality of larger models (7B+). Best used as a quick idea generator, not a replacement
+for a human DM's judgment.
+
+## License
+
+Apache 2.0 (same as base model)

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d8b73a5513e8baaba6654eabdb4365a9ddde0db42797ec78fbdbab97249c4a
+size 2200119664

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}