Upload folder using huggingface_hub

README.md

@@ -0,0 +1,143 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.3
+model-index:
+- name: outputs/axolotl-qlora-out-line
+  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/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: `0.4.0`
+```yaml
+base_model: mistralai/Mistral-7B-v0.3
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: vdaita/editpackft_inst_line
+    type: oasst
+dataset_prepared_path: 
+val_set_size: 0.05
+output_dir: ./outputs/axolotl-qlora-out-line
+
+adapter: lora
+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: huggingface
+wandb_log_model: axolotl-qlora-line-mistral
+
+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
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+
+```
+
+</details><br>
+
+# outputs/axolotl-qlora-out-line
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2883
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.847         | 0.01  | 1    | 0.9975          |
+| 0.3533        | 0.26  | 20   | 0.2772          |
+| 0.299         | 0.52  | 40   | 0.2501          |
+| 0.2288        | 0.77  | 60   | 0.2439          |
+| 0.334         | 1.01  | 80   | 0.2394          |
+| 0.3017        | 1.27  | 100  | 0.2399          |
+| 0.2394        | 1.53  | 120  | 0.2416          |
+| 0.2261        | 1.78  | 140  | 0.2400          |
+| 0.177         | 2.02  | 160  | 0.2388          |
+| 0.1911        | 2.28  | 180  | 0.2557          |
+| 0.1884        | 2.54  | 200  | 0.2601          |
+| 0.1516        | 2.79  | 220  | 0.2627          |
+| 0.1545        | 3.03  | 240  | 0.2628          |
+| 0.092         | 3.29  | 260  | 0.2915          |
+| 0.1251        | 3.55  | 280  | 0.2892          |
+| 0.109         | 3.8   | 300  | 0.2883          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "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": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af535014beb0051f4700a29e704b44e49328a08b621eaf0ab98d5d17d3a40b0a
+size 335706186

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404