Update README.md

README.md

@@ -3,184 +3,51 @@ license: apache-2.0
 base_model: Qwen/Qwen2-1.5B
 tags:
 - generated_from_trainer
-model-index:
-- name: 1.5b-out
-  results: []
+- axolotl
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-[<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)
-<details><summary>See axolotl config</summary>
-
-axolotl version: `0.4.1`
-```yaml
-base_model: Qwen/Qwen2-1.5B
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-# load_in_4bit: true
+# Dolphin 2.9.3 Qwen2 1.5B 🐬
 
-chat_template: chatml
-datasets:
-  - path: /workspace/datasets/dolphin201-sharegpt2.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /workspace/datasets/SystemChat_sharegpt.jsonl
-    type: sharegpt
-    conversation: chatml
-  # - path: /workspace/datasets/SystemChat_multilingual_sharegpt.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/SystemChat-2.0-Arabic/SystemChatArabic_sharegpt.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/dolphin-coder-translate-sharegpt2.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/dolphin-coder-codegen-sharegpt2.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
-  #   type: sharegpt
-    # conversation: chatml
-  - path: /workspace/datasets/not_samantha_norefusals.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /workspace/datasets/Orca-Math-resort-unfiltered.jsonl
-    type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/agent_instruct_react_unfiltered.jsonl
-  #   type: sharegpt  
-  #   conversation: chatml
-  # - path: /workspace/datasets/toolbench_instruct_j1s1_3k_unfiltered.jsonl
-  #   type: sharegpt  
-  #   conversation: chatml
-  # - path: /workspace/datasets/toolbench_negative_unfiltered.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/toolbench_react_10p_unfiltered.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  # - path: /workspace/datasets/toolbench_tflan_cot_30p_unfiltered.jsonl
-  #   type: sharegpt
-  #   conversation: chatml
-  - path: /workspace/datasets/openhermes200k_unfiltered.jsonl
-    type: sharegpt 
-    conversation: chatml
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.03
-output_dir: 1.5b-out
+Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
 
-sequence_len: 16384
-sample_packing: true
-pad_to_sequence_len: true
+[![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations)
+Discord: https://discord.gg/cognitivecomputations
 
-# adapter: qlora
-# lora_r: 16
-# lora_alpha: 32
-# lora_dropout: 0.05
-# lora_target_modules:
-#   - q_proj
-#   - k_proj
-#   - v_proj
-#   - o_proj
-#   - gate_proj
-#   - up_proj
-#   - down_proj
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
 
-wandb_project: 2.9.3-qwen-2.9.3-qwen2-1.5b
-# wandb_entity: oaaic
-# wandb_watch:
-# wandb_name:
-# wandb_log_model:
+Our appreciation for the sponsors of Dolphin 2.9.3:
+- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
 
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-num_epochs: 3
-optimizer: adamw_8bit
-lr_scheduler: constant
-learning_rate: 3e-4
-# max_grad_norm: 1.0
+This model is based on Qwen2-1.5b, and is governed by the Apache-2.0
 
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: false
+The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.
 
-gradient_checkpointing: true
-gradient_checkpointing_kwargs:
-  use_reentrant: true
-logging_steps: 1
-flash_attention: true
-deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
-warmup_steps: 10
-# evals_per_epoch: 2
-saves_per_epoch: 2
-save_total_limit: 2
-weight_decay: 0.1
-special_tokens:
-  eos_token: <|im_end|>
 
+example:
 
 ```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
 
-</details><br>
-
-# 1.5b-out
-
-This model is a fine-tuned version of [Qwen/Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.9568
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
-- total_eval_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 10
-- num_epochs: 3
-
-### Training results
+```
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.9653        | 1.0111 | 933  | 0.9733          |
-| 0.9254        | 2.0116 | 1867 | 0.9613          |
-| 0.8312        | 2.9743 | 2766 | 0.9568          |
+Dolphin-2.9.3 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
 
+Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
 
-### Framework versions
+Dolphin is licensed according to Apache-2.0  We grant permission for any use, including commercial, that falls within accordance with said license. Dolphin was trained on data generated from GPT4, among other models.
 
-- Transformers 4.41.1
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+Evals:
+<img src="https://i.ibb.co/JpNLRYG/file-9-Fs-Qpm4-LKPz-CZy08-Bu-MZj-Xi-V.png" width="600" />