Upload 8 files

README.md

@@ -1,3 +1,45 @@
----
-license: unknown
----
+---
+license: apache-2.0
+language:
+- en
+---
+<div align="center">
+
+# KobbleTinyV2-1.1B
+</div>
+
+This is a finetune of https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T trained on a small 50mb subset of the Kobble Dataset. 
+Training was done in under 2 hours on a single Nvidia RTX 2060 Mobile GPU with qLora (LR 1.5e-4, rank 8, alpha 16, batch size 2, gradient acc. 4, 2048 ctx). 
+
+You can obtain the GGUF quantization of this model here: https://huggingface.co/concedo/KobbleTinyV2-1.1B-GGUF
+
+Update: KobbleTiny has been upgraded to V2! The old V1 is [still available at this link](https://huggingface.co/concedo/KobbleTiny/tree/eb0c96864bfecfd6ac9ece1a42c4654b4997eb72).
+
+<video width="320" controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63cd4b6d1c8a5d1d7d76a778/zjHfohCnEu2Y9CWSWgf0n.mp4"></video>
+
+Try it live now: https://concedo-koboldcpp-kobbletiny.hf.space/
+
+## Dataset and Objectives
+
+The Kobble Dataset is a semi-private aggregated dataset made from multiple online sources and web scrapes. 
+It contains content chosen and formatted specifically to work with KoboldAI software and Kobold Lite.
+
+#### Dataset Categories:
+- Instruct: Single turn instruct examples presented in the Alpaca format, with an emphasis on uncensored and unrestricted responses.
+- Chat: Two participant roleplay conversation logs in a multi-turn raw chat format that KoboldAI uses.
+- Story: Unstructured fiction excerpts, including literature containing various erotic and provocative content.
+
+<!-- prompt-template start -->
+## Prompt template: Alpaca
+
+```
+### Instruction:
+{prompt}
+
+### Response:
+```
+
+<!-- prompt-template end -->
+
+**Note:** *No assurances will be provided about the **origins, safety, or copyright status** of this model, or of **any content** within the Kobble dataset.*  
+*If you belong to a country or organization that has strict AI laws or restrictions against unlabelled or unrestricted content, you are advised not to use this model.* 

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "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": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dd8a25c23133b308eff29d17bccd9a282bdb9c7e692f2b2a3a0f9102ab8408
+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": "<unk>",
+    "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 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}