Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,198 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: NewEden_nemo-chatml
+model-index:
+- name: 12b-out-rslora-SE
+  results: []
+---
+
+<!-- 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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.0`
+```yaml
+## model
+base_model: NewEden_nemo-chatml
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+## qlora COPE
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+## data 
+datasets:
+  - path: AquaV/c2-sharegpt-advanced-prefills-filtered
+    type: danchat-advanced
+  - path: AquaV/c1-sharegpt-advanced-prefills-filtered
+    type: danchat-advanced
+  - path: AquaV/rainy-sharegpt-advanced-prefills-filtered 
+    type: danchat-advanced
+  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
+    type: danchat-advanced
+  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
+    type: danchat-advanced
+  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
+    type: danchat-advanced
+  - path: anthracite-org/nopm_claude_writing_fixed
+    type: danchat-advanced
+  - path: anthracite-org/kalo_opus_misc_240827
+    type: danchat-advanced
+  - path: anthracite-org/kalo_misc_part2
+    type: danchat-advanced
+  - path: NewEden/Claude-Instruct-2.7K
+    type: danchat-advanced
+  - path: NewEden/Claude-Instruct-5K
+    type: danchat-advanced
+shuffle_merged_datasets: true
+dataset_prepared_path: dataset_prepared
+val_set_size: 0.02
+output_dir: 12b-out-rslora-SE
+
+## LIGGER
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+
+## CTX settings
+sequence_len: 16384
+sample_packing: true
+eval_sample_packing: true
+pad_to_sequence_len: true
+
+## Lora 
+adapter: lora
+lora_model_dir:
+lora_r: 128
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+peft_use_rslora: true
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+## WandB
+wandb_project: SE-mag-12B
+wandb_entity:
+wandb_watch:
+wandb_name: daring-mango
+wandb_log_model:
+
+## evals
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+
+## hoe params
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 2
+optimizer: paged_ademamix_8bit
+# optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 2.83e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+s2_attention:
+
+warmup_steps: 40
+saves_per_epoch: 2
+debug:
+## for ademiamix 
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
+## for adamw
+# deepspeed: ./deepspeed_configs/zero3_bf16.json
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+special_tokens:
+   pad_token: <pad>
+
+```
+
+</details><br>
+
+# 12b-out-rslora-SE
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0001
+
+## 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: 2.83e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.PAGED_ADEMAMIX_8BIT and the args are:
+No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 5.6935        | 0.0015 | 1    | 1.3433          |
+| 4.2418        | 0.2498 | 166  | 1.0758          |
+| 4.3565        | 0.4996 | 332  | 1.0486          |
+| 4.0471        | 0.7494 | 498  | 1.0297          |
+| 4.4088        | 0.9992 | 664  | 1.0146          |
+| 3.596         | 1.2494 | 830  | 1.0110          |
+| 3.4738        | 1.4992 | 996  | 1.0045          |
+| 3.6522        | 1.7491 | 1162 | 1.0010          |
+| 3.2321        | 1.9989 | 1328 | 1.0001          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.1
+- Pytorch 2.3.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden_nemo-chatml",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee433af6db7f81b8716ebd0136fa0d23d388608489362156483aa99f5510a67f
+size 1342339794

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c79293fe0c25ad6b774bf71f094c3e51898d14ece9967a763f4bb3561385584
+size 3596694008

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NewEden_nemo-chatml",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131072
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07f4f61632a89d8248b43f25649d6cc45200f8709e9d9bcd0414b00a4064e2
+size 17078342

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56987bc6a032478e9e6f911fa1232e42da921ed7e17c8e44fb271971fcfed7c7
+size 8184