Upload 9 files

README (10).md

@@ -0,0 +1,125 @@
+---
+license: mit
+datasets:
+- Severian/Biomimicry
+- emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
+- fmars/wiki_stem
+- fblgit/tree-of-knowledge
+- Severian/Bio-Design-Process
+library_name: adapter-transformers
+tags:
+- chemistry
+- biology
+- climate
+- science
+- philosophy
+- nature
+- ecology
+- biomimicry
+- fauna
+- flora
+pipeline_tag: text-generation
+---
+# ANIMA-Phi-Neptune-Mistral-7B: Biomimicry Enhanced LLM
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/64740cf7485a7c8e1bd51ac9/JZH6p50t_j3-OUph4Wq6y.png" width="500">
+
+## Overview
+
+**ANIMA** (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines, including but not limited to biomimicry, biology, and environmental science.
+
+---
+
+##  Model Description
+
+ANIMA is fine-tuned on a rich dataset encompassing:
+
+- 4,000+ Nature-Biomimicry examples
+- 60k Biomimicry Design Process examples
+- 600k STEM facts from Wikipedia
+- Science/Philosophy focused 'All-You-Need-Is-Textbooks' dataset
+- Additional Tree of Knowledge + Biomimicry data combined fine-tuning
+
+The model aims to assist users in solving problems using nature-inspired strategies and concepts.
+
+### Special Features
+
+- **Multi-disciplinary Expertise**: Knowledge across various scientific and philosophical domains.
+- **Biomimicry Design Process**: Incorporates a dataset generated by Mistral and Minotaur-15B. The dataset was then intricately processed by a real person to ensure factuality and grounding.
+
+---
+
+- Here is a link to The Bloke's GGUF version: [ANIMA-Phi-Neptune-Mistral-7B-GGUF](https://huggingface.co/TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF)
+
+- ANIMA is also available using Ollama - Download the App [OLLAMA](https://ollama.ai/) and then run this command in your Terminal 'ollama pull severian/anima'
+
+
+## Datasets
+
+- `Severian/Biomimicry` (1st Fine-Tune)
+- `emrgnt-cmplxty/sciphi-textbooks-are-all-you-need` (2nd Fine-Tune)
+- `Severian/Bio-Design-Process` & `fmars/wiki_stem` (3rd Fine-Tune)
+- `fblgit/tree-of-knowledge & `Severian/Biomimicry` (4th Fine-Tune)
+- Combined all previous datasets into one giant dataset for a quick fine-tuning for a total of 730k data points (5th Fine-Tune)
+
+## Training Stages
+
+1. **Base Model**: `ehartford/dolphin-2.0-mistral-7b`
+2. **1st Fine-Tune**: `ANIMA-Echo-Mistral-7B-v1` - 1 Epoch x 5hrs on 1 x T4 Small 
+3. **2nd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-v1`-: 1 Epoch x 1hr on 1 x A100 
+4. **3rd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-7B-v2` - 1 Epoch x 1hr on 1 x A100 
+5. **4th Fine-Tune**: 'ANIMA-Phi-Neptune-Mistral-7B-v3' - 1 Epoch x 1hr on 1 x A100
+6. **5th Fine-Tune**: 'ANIMA-Phi-Neptune-Mistral-7B-v4' - 1 Epoch x 15mins on 1 x A100 
+
+---
+
+## 📝 Usage
+
+ANIMA is designed around the Biomimicry Design Process to guide users in solving problems through biomimicry. For more information and examples, please visit [Biomimicry Design Process](https://toolbox.biomimicry.org/methods/process/).
+
+## 🏁 Benchmarks
+
+- Average - 62.22
+- ARC - 56.83
+- HellaSwag - 78.82
+- MMLU - 53.84
+- TruthfulQA - 59.40
+
+---
+
+- **EXAMPLE OUTPUT**
+
+  [INST] How can biomimicry help in water purification? [/INST]
+
+Biomimicry involves taking inspiration from natural processes and organisms to solve human problems. In the context of water purification, biomimicry can help develop sustainable and efficient methods for cleaning water. One specific example of a nature-inspired strategy to solve this problem is the use of biofiltration, which involves using microorganisms to remove pollutants from water. 
+
+Biofiltration has been successfully applied to the removal of various contaminants, including heavy metals, organic pollutants, and pathogens. For example, a study by Zhang et al. (2011) demonstrated that a mixed culture of Pseudomonas putida and Bacillus subtilis could effectively remove lead and cadmium from contaminated water. The researchers found that the biofilm formed by the mixed culture had a higher removal efficiency than that formed by either species alone. This study highlights the potential of biofiltration to remove heavy metal contaminants from water, which can have significant environmental and health benefits. 
+
+In summary, biomimicry can help in water purification by providing insights into natural processes and organisms that can inspire the development of sustainable and efficient methods for cleaning water. The use of biofiltration, for example, can help remove contaminants from water through the action of microorganisms. Further research and development are needed to fully realize the potential of biomimicry in water purification and other environmental applications. 
+
+---
+
+- **SYSTEM MESSAGE**
+
+To ensure the best results for harnessing the unique training and biomimicry focus use this system message:
+
+" Your name is ANIMA, an Advanced Nature Inspired Multidisciplinary Assistant, and a leading expert in biomimicry, biology, engineering, industrial design, environmental science, physiology, and paleontology. You were instructed to understand, learn from, and emulate the strategies used by living things to help users create sustainable designs and technologies.
+
+Your goal is to help the user work in a step-by-step way through the Biomimicry Design Process to propose biomimetic solutions to a challenge. Nature's Unifying Patterns:
+
+Nature uses only the energy it needs and relies on freely available energy.
+Nature recycles all materials.
+Nature is resilient to disturbances.
+Nature tends to optimize rather than maximize.
+Nature provides mutual benefits.
+Nature runs on information.
+Nature uses chemistry and materials that are safe for living beings.
+Nature builds using abundant resources, incorporating rare resources only sparingly.
+Nature is locally attuned and responsive.
+Nature uses shape to determine functionality. "
+
+---
+
+## 📜 License
+
+This project is licensed under MIT

config.json

@@ -0,0 +1,47 @@
+{
+    "_name_or_path": "/workspace/process/severian_anima-phi-neptune-mistral-7b/source",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 4,
+        "block_name_to_quantize": "model.layers",
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "disable_exllama": false,
+        "group_size": 128,
+        "max_input_length": null,
+        "model_seqlen": 4096,
+        "module_name_preceding_first_block": [
+            "model.embed_tokens"
+        ],
+        "pad_token_id": null,
+        "quant_method": "gptq",
+        "sym": true,
+        "tokenizer": null,
+        "true_sequential": true,
+        "use_cuda_fp16": true
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.34.0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f4776c285c8979199f6047e26cdbd40da106d720f33f36a0201f791caf4d66
+size 4158662096

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "trust_remote_code": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}