Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Newton-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Newton-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ecdf14b5e233dce50b3fa2eea042562f9c4c76db7232ee368abe9d17239956
+size 3822034912

Newton-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d726b3a8f8422bc3544454ac512147593bdb0e655f70a056c9898c499cb86b5
+size 3518996448

Newton-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f864eee84ca185c7347de9706d23a82a015d097961811a87c1a38539851994
+size 3164577760

Newton-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c0bb8034d9006a41e7e860df92d6fa152e21b86f4131eea0e773c6af9eec7d
+size 4368450592

Newton-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d234e6d9ce140be4907bb6253f7320a3732893004cb83ec0e59298b9e7666aa6
+size 4140385312

Newton-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce10cc4991aa3cadb19c059c95b51dadc61ee37fb55a12e8869491172ff1ee1
+size 5131421728

Newton-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bac35480ac47fc1f96544585df7b658c2d30c9a40e514bca161ac37f36df0a3
+size 4997728288

Newton-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247963c15775d5eefc853919475c2262d0a5f46cb5ea5f8f0a52f084f7e10225
+size 5942078560

Newton-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50397058db6873deeeb12e1501af102c35976b8f8cefd971238810bfe5b8525
+size 7695875040

README.md

@@ -0,0 +1,235 @@
+---
+license: other
+tags:
+- axolotl
+- finetune
+- qlora
+base_model: openchat/openchat-3.5-0106
+datasets:
+- hendrycks/competition_math
+- allenai/ai2_arc
+- camel-ai/physics
+- camel-ai/chemistry
+- camel-ai/biology
+- camel-ai/math
+- STEM-AI-mtl/Electrical-engineering
+- openbookqa
+- piqa
+- metaeval/reclor
+- mandyyyyii/scibench
+- derek-thomas/ScienceQA
+- sciq
+- TIGER-Lab/ScienceEval
+---
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/aimTTdmut59aZxOWQlkcC.jpeg)
+
+# 🔬👩‍🔬 Newton-7B
+
+This model is a fine-tuned version of [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) on datasets related to science.
+
+This model is fine-tuned using [QLoRa](https://arxiv.org/abs/2305.14314) and [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
+
+This model's training was sponsored by [sablo.ai](https://sablo.ai).
+
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.3.0`
+```yaml
+base_model: openchat/openchat-3.5-0106
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+
+datasets:
+  - path: merged_all.json
+    type:
+      field_instruction: instruction
+      field_output: output
+
+      format: "GPT4 Correct User: {instruction}<|end_of_turn|>GPT4 Correct Assistant:"
+      no_input_format: "GPT4 Correct User: {instruction}<|end_of_turn|>GPT4 Correct Assistant:"
+
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01 # not sure
+output_dir: ./newton
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 128
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+wandb_project: huggingface
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+hub_model_id: Weyaxi/newton-lora
+save_safetensors: true
+
+# change #
+gradient_accumulation_steps: 12
+micro_batch_size: 6
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+# change #
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10 # not sure
+
+saves_per_epoch: 2
+
+evals_per_epoch: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+
+debug:
+deepspeed:
+weight_decay: 0.1 # not sure
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+tokens:
+  - "<|end_of_turn|>"
+  - "<|pad_0|>"
+```
+
+</details><br>
+
+# 📊 Datasets
+
+You can find the dataset I used and the work I am doing with this datasets here:
+
+https://huggingface.co/datasets/Weyaxi/sci-datasets
+
+Following datasets were used in this model:
+
+- 📐 [MATH](https://huggingface.co/datasets/hendrycks/competition_math)
+
+- 🧠 [ARC](https://huggingface.co/datasets/allenai/ai2_arc) (Note: Only **train** part)
+
+- 🧲 [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics)
+
+- ⚗️ [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry)
+
+- 🦠 [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology)
+
+- 📊 [camel-ai/math](https://huggingface.co/datasets/camel-ai/math)
+
+- ⚡ [STEM-AI-mtl/Electrical-engineering](https://huggingface.co/datasets/STEM-AI-mtl/Electrical-engineering)
+
+- 📚 [openbookqa](https://huggingface.co/datasets/openbookqa)
+
+- 🧠 [piqa](https://huggingface.co/datasets/piqa)
+
+- 🎨 [reclor](https://huggingface.co/datasets/metaeval/reclor)
+
+- 🔬 [scibench](https://github.com/mandyyyyii/scibench)
+
+- 🧪 [ScienceQA](https://huggingface.co/datasets/derek-thomas/ScienceQA)
+
+- 🧬 [sciq](https://huggingface.co/datasets/sciq)
+
+- 📝 [ScienceEval](https://huggingface.co/datasets/TIGER-Lab/ScienceEval)
+
+## 🛠️ Multiple Choice Question & Answer Datasets Conversion Progress
+
+I used [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) to generate a reasonable and logical answer by providing it with the question and the answer key.
+
+I used the [Together AI](https://www.together.ai) API for this task.
+
+The following datasets are converted using this method:
+
+- 🧠 [ARC](https://huggingface.co/datasets/allenai/ai2_arc) (Note: Only **train** part)
+
+- 📚 [openbookqa](https://huggingface.co/datasets/openbookqa)
+
+- 🎨 [reclor](https://huggingface.co/datasets/metaeval/reclor)
+
+- 🧬 [sciq](https://huggingface.co/datasets/sciq)
+
+# 💬 Prompt Template
+
+You can use this prompt template while using the model:
+
+### GPT4 Correct [(Openchat)](https://huggingface.co/openchat/openchat-3.5-0106#conversation-templates)
+
+```
+GPT4 Correct User: {user}<|end_of_turn|>GPT4 Correct Assistant: {asistant}<|end_of_turn|>GPT4 Correct User: {user}<|end_of_turn|>GPT4 Correct Assistant:
+```
+
+You can also utilize the chat template method from the tokenizer config like here:
+
+```python
+messages = [
+    {"role": "user", "content": "Hello"},
+    {"role": "assistant", "content": "Hi"},
+    {"role": "user", "content": "How are you today?"}
+]
+tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+```
+
+# 🤝 Acknowledgments
+
+Thanks to [openchat](https://huggingface.co/openchat) team for fine-tuning an excellent model that I used as a base model.
+
+Thanks to [@jondurbin](https://huggingface.co/jondurbin) for reformatting codes for some datasets: [bagel/data_sources](https://github.com/jondurbin/bagel/tree/main/bagel/data_sources)
+
+Thanks to [Together AI](https://www.together.ai) for providing everyone with free credits, which I used to generate a dataset in multiple choice to explanations format.
+
+Thanks to [Tim Dettmers](https://huggingface.co/timdettmers) for his excellent [QLoRA](https://arxiv.org/abs/2305.14314) work.
+
+Thanks to all the dataset authors mentioned in the datasets section.
+
+Thanks to [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for making the repository I used to make this model.
+
+Overall, thanks to all of the open soure AI community! 🚀
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+
+If you would like to support me:
+
+[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)

huggingface-metadata.txt

@@ -0,0 +1,8 @@
+url: https://huggingface.co/Weyaxi/Newton-7B
+branch: main
+download date: 2024-02-01 00:42:51
+sha256sum:
+    008cd7cdcec4904aec424162611fbd7831f55c4a58cde3039707f956b735233e model-00001-of-00003.safetensors
+    ba7aa65e46edd121ff5eb051467ba684a7d5b69efb3eac967fbb7122e34d7dd0 model-00002-of-00003.safetensors
+    2d2709fc008ce04e9fb9619a2e88901f21af2f060bf57ea4d5c2565fd75e3df3 model-00003-of-00003.safetensors
+    dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 tokenizer.model