Upload README.md

README.md

@@ -1,3 +1,148 @@
----
-license: apache-2.0
----
+---
+base_model:
+- concedo/KobbleTinyV2-1.1B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Tinyllama-2B
+
+This is a merge and a finetune to create a small, but very useable Model, and i have to say, its very good.
+
+## Basic Question:
+
+<img src="https://huggingface.co/Aculi/Tinyllama-2B/resolve/main/.huggingface/Screenshot%202024-07-29%20073647.jpg" alt="download.png" width="800" />
+
+
+## Prompt Template
+
+Tinyllama-2B uses Alpaca:
+
+```
+### Instruction:
+{prompt}
+
+### Response:
+```
+
+### Merge Info:
+
+This is a frankenmerge of: [concedo/KobbleTinyV2-1.1B](https://huggingface.co/concedo/KobbleTinyV2-1.1B)
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 16]
+    model: concedo/KobbleTinyV2-1.1B
+- sources:
+  - layer_range: [5, 16] 
+    model: concedo/KobbleTinyV2-1.1B
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+- sources:
+  - layer_range: [5, 16] 
+    model: concedo/KobbleTinyV2-1.1B
+    parameters:
+      scale:
+      - filter: o_proj
+        value: 0.0
+      - filter: down_proj
+        value: 0.0
+      - value: 1.0
+- sources:
+  - layer_range: [16, 22] 
+    model: concedo/KobbleTinyV2-1.1B
+```
+
+## Finetune Info:
+
+The following YAML configuration was used to finetune this model:
+
+```yaml
+base_model: Fischerboot/2b-tiny-llama-alpaca-instr
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: Fischerboot/freedom-rp-alpaca-shortend
+    type: alpaca
+  - path: diffnamehard/toxic-dpo-v0.1-NoWarning-alpaca
+    type: alpaca
+  - path: Fischerboot/alpaca-undensored-fixed-50k
+    type: alpaca
+  - path: Fischerboot/DAN-alpaca
+    type: alpaca
+  - path: Fischerboot/rp-alpaca-next-oone
+    type: alpaca
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/24r
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 4
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention: true
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 2
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+```