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 +1,197 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai_Mistral-Nemo-Instruct-2407
+model-index:
+- name: 12b-out-r3
+  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
+base_model: mistralai_Mistral-Nemo-Instruct-2407
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: NewEden/OpenCAI-ShareGPT
+    type: chat_template
+#    chat_template: mistralv3tekken
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: NewEden/vanilla-backrooms-claude-sharegpt
+    type: chat_template
+#    chat_template: mistralv3tekken
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn    
+  - path: anthracite-org/kalo_opus_misc_240827
+    type: chat_template
+#    chat_template: mistralv3tekken
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn    
+  - path: anthracite-org/kalo_misc_part2
+    type: chat_template
+#    chat_template: mistralv3tekken
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: NewEden/Roleplay-Logs-V2
+    type: chat_template
+#    chat_template: mistralv3tekken
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+dataset_prepared_path: dataset_prepared
+val_set_size: 0.0
+output_dir: 12b-out-r3
+
+sequence_len: 16384
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05 
+  #lora_target_linear:
+  #lora_fan_in_fan_out: true
+peft_use_rslora: true
+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: 12b-control
+wandb_entity:
+wandb_watch:
+wandb_name: 12b-control-r3
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+  #gradient_checkpointing_kwargs:
+  #  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 40
+evals_per_epoch: 
+eval_table_size:
+eval_max_new_tokens:
+saves_per_epoch: 1
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
+weight_decay: 0.03
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <pad>
+
+
+```
+
+</details><br>
+
+# 12b-out-r3
+
+This model was trained from scratch on the None dataset.
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 4
+
+### Training results
+
+
+
+### 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": "mistralai_Mistral-Nemo-Instruct-2407",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325447b46ec5a949650d6e31661f38563fcc13795bec1befe394d897e9d1c726
+size 2912497608

config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai_Mistral-Nemo-Instruct-2407",
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "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": "</s>",
+    "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:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a34494574e9f6fb5caa0e48edb41cb98af38d171ff118bd32731ba085811af8
+size 7992