Update README.md

README.md

@@ -28,6 +28,189 @@ model-index:
 This model was converted to GGUF format from [`EVA-UNIT-01/EVA-Qwen2.5-1.5B-v0.0`](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-1.5B-v0.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-1.5B-v0.0) for more details on the model.
 
+---
+Model details:
+-
+
+  A small-scale RP/storywriting specialist model, full-parameter 
+finetune of Qwen2.5-1.5B on mixture of synthetic and natural data.
+
+  It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve 
+versatility, creativity and "flavor" of the resulting model.
+
+  Unlike EVA-D 1.5B v0.0, this model was created without using 
+DistillKit, and unlike other versions of EVA, Spectrum wasn't used 
+either, since layer freezing is inefficient at small scale.
+
+
+
+
+
+  
+
+  
+
+    Training data:
+  
+
+    
+Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model's card for details.
+Kalomaze's Opus_Instruct_25k dataset, filtered for refusals.
+A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe
+A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe
+Synthstruct and SynthRP datasets by Epiculous
+A subset from Dolphin-2.9.3, including filtered version of not_samantha and a small subset of systemchat.
+
+  
+
+     Training time and hardware:
+  
+
+      
+9 hours on 4x3090Ti
+
+  
+
+
+
+
+  
+Model was created by Kearm, Auri and Cahvay.
+
+  
+Special thanks:
+to Cahvay for his work on investigating and reprocessing the 
+corrupted dataset, removing the single biggest source of data poisoning.
+to Gryphe, Lemmy, Kalomaze, Nopm, Epiculous and CognitiveComputations for the data
+and to Allura-org for support, feedback, beta-testing and doing quality control of EVA models.
+
+
+
+
+
+See axolotl config
+
+
+axolotl version: 0.4.1
+
+
+base_model: /media/kearm/Disk_2/HF_FAST_MoE_Fodder/Qwen2.5-1.5B
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+# plugins:
+#   - axolotl.integrations.spectrum.SpectrumPlugin
+
+# spectrum_top_fraction: 0.5
+# # Optional if using a pre-scanned model as your base_model. Useful if using a model mirror
+# spectrum_model_name: Qwen/Qwen2.5-32B
+
+datasets:
+  - path: datasets/Celeste_Filtered_utf8fix.jsonl
+    type: sharegpt
+  - path: datasets/deduped_not_samantha_norefusals.jsonl
+    type: sharegpt
+  - path: datasets/deduped_SynthRP-Gens_processed_ShareGPT_converted_cleaned.jsonl
+    type: sharegpt
+  - path: datasets/deduped_Synthstruct-Gens_processed_sharegpt_converted_cleaned.jsonl
+    type: sharegpt
+  - path: datasets/Gryphe-4o-WP-filtered-sharegpt_utf8fix.jsonl
+    type: sharegpt
+  - path: datasets/Sonnet3-5-charcard-names-filtered-sharegpt_utf8fix.jsonl
+    type: sharegpt
+  - path: datasets/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
+    type: sharegpt
+  - path: datasets/S2.jsonl
+    type: sharegpt
+  - path: datasets/Turing.jsonl
+    type: sharegpt
+
+chat_template: chatml
+shuffle_merged_datasets: true
+val_set_size: 0.05
+output_dir: EVA-Qwen2.5-1.5B-FFT-v0.0
+
+sequence_len: 10240
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+# adapter: qlora
+# lora_model_dir:
+# lora_r: 64
+# lora_alpha: 128
+# lora_dropout: 0.05
+# lora_target_linear: true
+# peft_use_dora: true
+
+wandb_project: EVA-Qwen2.5-1.5B-FFT-v0.0
+wandb_entity:
+wandb_watch:
+wandb_name: Unit-00
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.000005
+max_grad_norm: 1.5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: "unsloth"
+gradient_checkpointing_kwargs:
+   use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 20
+evals_per_epoch: 4
+saves_per_epoch: 4
+save_safetensors: true
+save_total_limit: 8
+hub_model_id:
+hub_strategy:
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.15
+# fsdp:
+#   - full_shard
+#   - auto_wrap
+# fsdp_config:
+#   fsdp_limit_all_gathers: true
+#   fsdp_sync_module_states: false
+#   fsdp_offload_params: true
+#   fsdp_cpu_ram_efficient_loading: true
+#   fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+#   fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+#   fsdp_activation_checkpointing: true
+#   fsdp_state_dict_type: SHARDED_STATE_DICT  # Changed from FULL_STATE_DICT
+#   fsdp_sharding_strategy: FULL_SHARD
+#   fsdp_forward_prefetch: false  # Added
+#   fsdp_backward_prefetch: "BACKWARD_PRE"  # Added
+#   fsdp_backward_prefetch_limit: 1  # Added
+#   fsdp_mixed_precision: BF16  # Added
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)