Upload folder using huggingface_hub

README.md

@@ -0,0 +1,344 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: sail/Sailor-7B
+model-index:
+- name: Sailor-7B-toba
+  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: sail/Sailor-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+is_mistral_derived_model: false
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+#we used a small dataset to teach the model function calling abilities
+  - path: ./echonettobatrain.jsonl
+    ds_type: json
+    type: sharegpt
+
+dataset_prepared_path: last_run_function_call
+#0.05
+val_set_size: 0.02
+output_dir: ./Sailor-7B-toba
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 8192
+sample_packing: false
+eval_sample_packing: true
+pad_to_sequence_len: true
+
+# important, to get the same trainable parameters then for a qlora training with lora_r=32 and lora_alpha=16 you need to adjust the lora_r depending on the amount of filtered layers you want to use. With top_n=4 you would go for lora_r= 256
+
+lora_r: 64
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: false
+lora_fan_in_fan_out:
+lora_target_modules:
+- layers.0.self_attn.v_proj
+- layers.1.self_attn.v_proj
+- layers.2.self_attn.v_proj
+- layers.3.self_attn.v_proj
+- layers.4.self_attn.v_proj
+- layers.5.self_attn.v_proj
+- layers.6.self_attn.v_proj
+- layers.7.self_attn.v_proj
+- layers.8.self_attn.v_proj
+- layers.9.self_attn.v_proj
+- layers.10.self_attn.v_proj
+- layers.11.self_attn.v_proj
+- layers.12.self_attn.v_proj
+- layers.13.self_attn.v_proj
+- layers.14.self_attn.v_proj
+- layers.15.self_attn.v_proj
+- layers.16.self_attn.v_proj
+- layers.17.self_attn.v_proj
+- layers.18.self_attn.v_proj
+- layers.19.self_attn.v_proj
+- layers.20.self_attn.v_proj
+- layers.21.self_attn.v_proj
+- layers.22.self_attn.v_proj
+- layers.23.self_attn.v_proj
+- layers.24.self_attn.v_proj
+- layers.25.self_attn.v_proj
+- layers.26.self_attn.v_proj
+- layers.27.self_attn.v_proj
+- layers.28.self_attn.v_proj
+- layers.29.self_attn.v_proj
+- layers.30.self_attn.v_proj
+- layers.31.self_attn.v_proj
+- layers.0.self_attn.k_proj
+- layers.1.self_attn.k_proj
+- layers.2.self_attn.k_proj
+- layers.3.self_attn.k_proj
+- layers.4.self_attn.k_proj
+- layers.5.self_attn.k_proj
+- layers.6.self_attn.k_proj
+- layers.7.self_attn.k_proj
+- layers.8.self_attn.k_proj
+- layers.9.self_attn.k_proj
+- layers.10.self_attn.k_proj
+- layers.11.self_attn.k_proj
+- layers.12.self_attn.k_proj
+- layers.13.self_attn.k_proj
+- layers.14.self_attn.k_proj
+- layers.15.self_attn.k_proj
+- layers.16.self_attn.k_proj
+- layers.17.self_attn.k_proj
+- layers.18.self_attn.k_proj
+- layers.19.self_attn.k_proj
+- layers.20.self_attn.k_proj
+- layers.21.self_attn.k_proj
+- layers.22.self_attn.k_proj
+- layers.23.self_attn.k_proj
+- layers.24.self_attn.k_proj
+- layers.25.self_attn.k_proj
+- layers.26.self_attn.k_proj
+- layers.27.self_attn.k_proj
+- layers.28.self_attn.k_proj
+- layers.29.self_attn.k_proj
+- layers.30.self_attn.k_proj
+- layers.31.self_attn.k_proj
+- layers.0.self_attn.o_proj
+- layers.1.self_attn.o_proj
+- layers.2.self_attn.o_proj
+- layers.3.self_attn.o_proj
+- layers.4.self_attn.o_proj
+- layers.5.self_attn.o_proj
+- layers.6.self_attn.o_proj
+- layers.7.self_attn.o_proj
+- layers.8.self_attn.o_proj
+- layers.9.self_attn.o_proj
+- layers.10.self_attn.o_proj
+- layers.11.self_attn.o_proj
+- layers.12.self_attn.o_proj
+- layers.13.self_attn.o_proj
+- layers.14.self_attn.o_proj
+- layers.15.self_attn.o_proj
+- layers.16.self_attn.o_proj
+- layers.17.self_attn.o_proj
+- layers.18.self_attn.o_proj
+- layers.19.self_attn.o_proj
+- layers.20.self_attn.o_proj
+- layers.21.self_attn.o_proj
+- layers.22.self_attn.o_proj
+- layers.23.self_attn.o_proj
+- layers.24.self_attn.o_proj
+- layers.25.self_attn.o_proj
+- layers.26.self_attn.o_proj
+- layers.27.self_attn.o_proj
+- layers.28.self_attn.o_proj
+- layers.29.self_attn.o_proj
+- layers.30.self_attn.o_proj
+- layers.31.self_attn.o_proj
+- layers.0.self_attn.q_proj
+- layers.1.self_attn.q_proj
+- layers.2.self_attn.q_proj
+- layers.3.self_attn.q_proj
+- layers.4.self_attn.q_proj
+- layers.5.self_attn.q_proj
+- layers.6.self_attn.q_proj
+- layers.7.self_attn.q_proj
+- layers.8.self_attn.q_proj
+- layers.9.self_attn.q_proj
+- layers.10.self_attn.q_proj
+- layers.11.self_attn.q_proj
+- layers.12.self_attn.q_proj
+- layers.13.self_attn.q_proj
+- layers.14.self_attn.q_proj
+- layers.15.self_attn.q_proj
+- layers.16.self_attn.q_proj
+- layers.17.self_attn.q_proj
+- layers.18.self_attn.q_proj
+- layers.19.self_attn.q_proj
+- layers.20.self_attn.q_proj
+- layers.21.self_attn.q_proj
+- layers.22.self_attn.q_proj
+- layers.23.self_attn.q_proj
+- layers.24.self_attn.q_proj
+- layers.25.self_attn.q_proj
+- layers.26.self_attn.q_proj
+- layers.27.self_attn.q_proj
+- layers.28.self_attn.q_proj
+- layers.29.self_attn.q_proj
+- layers.30.self_attn.q_proj
+- layers.31.self_attn.q_proj
+- layers.0.mlp.down_proj
+- layers.1.mlp.down_proj
+- layers.2.mlp.down_proj
+- layers.3.mlp.down_proj
+- layers.4.mlp.down_proj
+- layers.5.mlp.down_proj
+- layers.6.mlp.down_proj
+- layers.7.mlp.down_proj
+- layers.8.mlp.down_proj
+- layers.9.mlp.down_proj
+- layers.10.mlp.down_proj
+- layers.11.mlp.down_proj
+- layers.12.mlp.down_proj
+- layers.13.mlp.down_proj
+- layers.14.mlp.down_proj
+- layers.15.mlp.down_proj
+- layers.16.mlp.down_proj
+- layers.17.mlp.down_proj
+- layers.18.mlp.down_proj
+- layers.19.mlp.down_proj
+- layers.20.mlp.down_proj
+- layers.21.mlp.down_proj
+- layers.22.mlp.down_proj
+- layers.23.mlp.down_proj
+- layers.24.mlp.down_proj
+- layers.25.mlp.down_proj
+- layers.26.mlp.down_proj
+- layers.27.mlp.down_proj
+- layers.28.mlp.down_proj
+- layers.29.mlp.down_proj
+- layers.30.mlp.down_proj
+- layers.31.mlp.down_proj
+- layers.0.mlp.up_proj
+- layers.1.mlp.up_proj
+- layers.2.mlp.up_proj
+- layers.3.mlp.up_proj
+- layers.4.mlp.up_proj
+- layers.5.mlp.up_proj
+- layers.6.mlp.up_proj
+- layers.7.mlp.up_proj
+- layers.8.mlp.up_proj
+- layers.9.mlp.up_proj
+- layers.10.mlp.up_proj
+- layers.11.mlp.up_proj
+- layers.12.mlp.up_proj
+- layers.13.mlp.up_proj
+- layers.14.mlp.up_proj
+- layers.15.mlp.up_proj
+- layers.16.mlp.up_proj
+- layers.17.mlp.up_proj
+- layers.18.mlp.up_proj
+- layers.19.mlp.up_proj
+- layers.20.mlp.up_proj
+- layers.21.mlp.up_proj
+- layers.22.mlp.up_proj
+- layers.23.mlp.up_proj
+- layers.24.mlp.up_proj
+- layers.25.mlp.up_proj
+- layers.26.mlp.up_proj
+- layers.27.mlp.up_proj
+- layers.28.mlp.up_proj
+- layers.29.mlp.up_proj
+- layers.30.mlp.up_proj
+- layers.31.mlp.up_proj
+  # important: you need to unfreeze the lm.head
+- lm.head
+
+wandb_project: axolotl-sailor7b-toba
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00025
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+eval_steps: 0.2
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+```
+
+</details><br>
+
+# Sailor-7B-toba
+
+This model is a fine-tuned version of [sail/Sailor-7B](https://huggingface.co/sail/Sailor-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3876
+
+## 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: 0.00025
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.0998        | 0.0   | 1    | 5.1501          |
+| 1.3477        | 0.6   | 622  | 1.6304          |
+| 1.268         | 1.2   | 1244 | 1.4755          |
+| 0.8714        | 1.8   | 1866 | 1.2799          |
+| 0.4408        | 2.4   | 2488 | 1.3876          |
+
+
+### Framework versions
+
+- PEFT 0.9.1.dev0
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,219 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sail/Sailor-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.3.self_attn.v_proj",
+    "layers.30.self_attn.k_proj",
+    "layers.12.self_attn.o_proj",
+    "layers.3.mlp.up_proj",
+    "layers.1.self_attn.k_proj",
+    "layers.10.self_attn.o_proj",
+    "layers.28.self_attn.o_proj",
+    "layers.4.self_attn.v_proj",
+    "layers.3.self_attn.o_proj",
+    "layers.10.mlp.down_proj",
+    "layers.6.self_attn.o_proj",
+    "layers.1.self_attn.q_proj",
+    "layers.15.self_attn.q_proj",
+    "layers.7.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.27.self_attn.k_proj",
+    "layers.31.self_attn.k_proj",
+    "layers.30.mlp.down_proj",
+    "layers.17.mlp.down_proj",
+    "layers.14.self_attn.v_proj",
+    "layers.28.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.31.mlp.down_proj",
+    "layers.5.self_attn.o_proj",
+    "layers.6.mlp.down_proj",
+    "layers.17.mlp.up_proj",
+    "layers.26.self_attn.v_proj",
+    "layers.2.self_attn.v_proj",
+    "layers.7.self_attn.o_proj",
+    "layers.2.mlp.down_proj",
+    "layers.6.self_attn.v_proj",
+    "layers.18.self_attn.v_proj",
+    "layers.18.mlp.up_proj",
+    "layers.25.self_attn.v_proj",
+    "layers.0.self_attn.k_proj",
+    "layers.13.self_attn.v_proj",
+    "layers.10.self_attn.k_proj",
+    "layers.27.self_attn.o_proj",
+    "layers.0.self_attn.v_proj",
+    "layers.23.mlp.down_proj",
+    "layers.11.self_attn.v_proj",
+    "layers.30.mlp.up_proj",
+    "layers.20.self_attn.o_proj",
+    "layers.15.mlp.up_proj",
+    "layers.4.self_attn.k_proj",
+    "layers.9.mlp.up_proj",
+    "layers.29.self_attn.o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.21.self_attn.q_proj",
+    "layers.16.self_attn.o_proj",
+    "layers.12.self_attn.v_proj",
+    "layers.14.self_attn.q_proj",
+    "layers.29.self_attn.v_proj",
+    "layers.16.self_attn.v_proj",
+    "layers.28.self_attn.k_proj",
+    "layers.13.self_attn.o_proj",
+    "layers.13.self_attn.k_proj",
+    "layers.5.self_attn.v_proj",
+    "layers.7.self_attn.q_proj",
+    "layers.13.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.19.self_attn.k_proj",
+    "layers.26.self_attn.o_proj",
+    "layers.14.mlp.up_proj",
+    "layers.6.self_attn.k_proj",
+    "layers.23.self_attn.v_proj",
+    "layers.3.self_attn.q_proj",
+    "layers.1.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.7.self_attn.k_proj",
+    "layers.26.mlp.up_proj",
+    "layers.12.self_attn.q_proj",
+    "layers.21.self_attn.v_proj",
+    "layers.11.mlp.down_proj",
+    "layers.14.self_attn.o_proj",
+    "layers.8.self_attn.k_proj",
+    "layers.19.self_attn.q_proj",
+    "layers.23.self_attn.o_proj",
+    "layers.8.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.25.self_attn.q_proj",
+    "layers.29.mlp.up_proj",
+    "layers.20.self_attn.v_proj",
+    "layers.18.self_attn.o_proj",
+    "layers.17.self_attn.k_proj",
+    "layers.0.self_attn.o_proj",
+    "layers.1.self_attn.v_proj",
+    "layers.7.mlp.down_proj",
+    "layers.5.self_attn.k_proj",
+    "layers.29.self_attn.k_proj",
+    "layers.21.self_attn.o_proj",
+    "layers.20.self_attn.q_proj",
+    "layers.24.mlp.up_proj",
+    "layers.4.self_attn.q_proj",
+    "layers.22.mlp.down_proj",
+    "layers.14.self_attn.k_proj",
+    "layers.0.mlp.up_proj",
+    "layers.15.self_attn.o_proj",
+    "layers.18.mlp.down_proj",
+    "layers.8.self_attn.o_proj",
+    "layers.2.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.6.self_attn.q_proj",
+    "layers.16.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.12.mlp.up_proj",
+    "layers.30.self_attn.v_proj",
+    "layers.5.self_attn.q_proj",
+    "layers.25.self_attn.k_proj",
+    "layers.4.self_attn.o_proj",
+    "layers.0.self_attn.q_proj",
+    "layers.11.self_attn.q_proj",
+    "layers.3.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.27.self_attn.q_proj",
+    "layers.15.mlp.down_proj",
+    "layers.12.self_attn.k_proj",
+    "layers.16.self_attn.k_proj",
+    "layers.13.mlp.down_proj",
+    "layers.9.self_attn.q_proj",
+    "layers.13.self_attn.q_proj",
+    "layers.12.mlp.down_proj",
+    "layers.22.self_attn.o_proj",
+    "layers.22.self_attn.q_proj",
+    "layers.1.self_attn.o_proj",
+    "layers.30.self_attn.q_proj",
+    "layers.24.self_attn.k_proj",
+    "layers.19.mlp.up_proj",
+    "layers.10.mlp.up_proj",
+    "layers.28.self_attn.v_proj",
+    "layers.31.self_attn.o_proj",
+    "layers.15.self_attn.v_proj",
+    "layers.22.self_attn.v_proj",
+    "layers.16.self_attn.q_proj",
+    "layers.27.mlp.up_proj",
+    "layers.20.self_attn.k_proj",
+    "layers.17.self_attn.o_proj",
+    "layers.29.self_attn.q_proj",
+    "layers.29.mlp.down_proj",
+    "layers.4.mlp.down_proj",
+    "layers.8.self_attn.q_proj",
+    "layers.25.mlp.down_proj",
+    "layers.11.self_attn.k_proj",
+    "layers.17.self_attn.q_proj",
+    "layers.2.self_attn.q_proj",
+    "layers.5.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.2.self_attn.o_proj",
+    "layers.16.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.27.self_attn.v_proj",
+    "layers.22.self_attn.k_proj",
+    "layers.26.self_attn.k_proj",
+    "layers.7.self_attn.v_proj",
+    "layers.9.self_attn.v_proj",
+    "layers.31.self_attn.v_proj",
+    "layers.3.self_attn.k_proj",
+    "layers.15.self_attn.k_proj",
+    "layers.19.self_attn.v_proj",
+    "layers.21.mlp.down_proj",
+    "layers.9.self_attn.k_proj",
+    "layers.19.self_attn.o_proj",
+    "layers.10.self_attn.v_proj",
+    "layers.9.self_attn.o_proj",
+    "layers.25.self_attn.o_proj",
+    "layers.24.mlp.down_proj",
+    "layers.31.self_attn.q_proj",
+    "layers.10.self_attn.q_proj",
+    "layers.18.self_attn.q_proj",
+    "layers.19.mlp.down_proj",
+    "layers.21.self_attn.k_proj",
+    "layers.20.mlp.down_proj",
+    "layers.24.self_attn.o_proj",
+    "layers.26.self_attn.q_proj",
+    "layers.11.self_attn.o_proj",
+    "layers.14.mlp.down_proj",
+    "layers.24.self_attn.q_proj",
+    "layers.28.mlp.up_proj",
+    "layers.23.self_attn.k_proj",
+    "layers.6.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.24.self_attn.v_proj",
+    "layers.30.self_attn.o_proj",
+    "layers.1.mlp.down_proj",
+    "layers.17.self_attn.v_proj",
+    "layers.18.self_attn.k_proj",
+    "layers.28.self_attn.q_proj",
+    "layers.21.mlp.up_proj",
+    "lm.head",
+    "layers.8.self_attn.v_proj",
+    "layers.23.self_attn.q_proj",
+    "layers.2.self_attn.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 sha256:58df9a56c186e2463bd3ed8be94206423219163cfe53ffff3f0a9777e6b51752
+size 516038346

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-1036/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: sail/Sailor-7B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.1.dev0

checkpoint-1036/adapter_config.json

@@ -0,0 +1,219 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sail/Sailor-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.3.self_attn.v_proj",
+    "layers.30.self_attn.k_proj",
+    "layers.12.self_attn.o_proj",
+    "layers.3.mlp.up_proj",
+    "layers.1.self_attn.k_proj",
+    "layers.10.self_attn.o_proj",
+    "layers.28.self_attn.o_proj",
+    "layers.4.self_attn.v_proj",
+    "layers.3.self_attn.o_proj",
+    "layers.10.mlp.down_proj",
+    "layers.6.self_attn.o_proj",
+    "layers.1.self_attn.q_proj",
+    "layers.15.self_attn.q_proj",
+    "layers.7.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.27.self_attn.k_proj",
+    "layers.31.self_attn.k_proj",
+    "layers.30.mlp.down_proj",
+    "layers.17.mlp.down_proj",
+    "layers.14.self_attn.v_proj",
+    "layers.28.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.31.mlp.down_proj",
+    "layers.5.self_attn.o_proj",
+    "layers.6.mlp.down_proj",
+    "layers.17.mlp.up_proj",
+    "layers.26.self_attn.v_proj",
+    "layers.2.self_attn.v_proj",
+    "layers.7.self_attn.o_proj",
+    "layers.2.mlp.down_proj",
+    "layers.6.self_attn.v_proj",
+    "layers.18.self_attn.v_proj",
+    "layers.18.mlp.up_proj",
+    "layers.25.self_attn.v_proj",
+    "layers.0.self_attn.k_proj",
+    "layers.13.self_attn.v_proj",
+    "layers.10.self_attn.k_proj",
+    "layers.27.self_attn.o_proj",
+    "layers.0.self_attn.v_proj",
+    "layers.23.mlp.down_proj",
+    "layers.11.self_attn.v_proj",
+    "layers.30.mlp.up_proj",
+    "layers.20.self_attn.o_proj",
+    "layers.15.mlp.up_proj",
+    "layers.4.self_attn.k_proj",
+    "layers.9.mlp.up_proj",
+    "layers.29.self_attn.o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.21.self_attn.q_proj",
+    "layers.16.self_attn.o_proj",
+    "layers.12.self_attn.v_proj",
+    "layers.14.self_attn.q_proj",
+    "layers.29.self_attn.v_proj",
+    "layers.16.self_attn.v_proj",
+    "layers.28.self_attn.k_proj",
+    "layers.13.self_attn.o_proj",
+    "layers.13.self_attn.k_proj",
+    "layers.5.self_attn.v_proj",
+    "layers.7.self_attn.q_proj",
+    "layers.13.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.19.self_attn.k_proj",
+    "layers.26.self_attn.o_proj",
+    "layers.14.mlp.up_proj",
+    "layers.6.self_attn.k_proj",
+    "layers.23.self_attn.v_proj",
+    "layers.3.self_attn.q_proj",
+    "layers.1.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.7.self_attn.k_proj",
+    "layers.26.mlp.up_proj",
+    "layers.12.self_attn.q_proj",
+    "layers.21.self_attn.v_proj",
+    "layers.11.mlp.down_proj",
+    "layers.14.self_attn.o_proj",
+    "layers.8.self_attn.k_proj",
+    "layers.19.self_attn.q_proj",
+    "layers.23.self_attn.o_proj",
+    "layers.8.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.25.self_attn.q_proj",
+    "layers.29.mlp.up_proj",
+    "layers.20.self_attn.v_proj",
+    "layers.18.self_attn.o_proj",
+    "layers.17.self_attn.k_proj",
+    "layers.0.self_attn.o_proj",
+    "layers.1.self_attn.v_proj",
+    "layers.7.mlp.down_proj",
+    "layers.5.self_attn.k_proj",
+    "layers.29.self_attn.k_proj",
+    "layers.21.self_attn.o_proj",
+    "layers.20.self_attn.q_proj",
+    "layers.24.mlp.up_proj",
+    "layers.4.self_attn.q_proj",
+    "layers.22.mlp.down_proj",
+    "layers.14.self_attn.k_proj",
+    "layers.0.mlp.up_proj",
+    "layers.15.self_attn.o_proj",
+    "layers.18.mlp.down_proj",
+    "layers.8.self_attn.o_proj",
+    "layers.2.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.6.self_attn.q_proj",
+    "layers.16.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.12.mlp.up_proj",
+    "layers.30.self_attn.v_proj",
+    "layers.5.self_attn.q_proj",
+    "layers.25.self_attn.k_proj",
+    "layers.4.self_attn.o_proj",
+    "layers.0.self_attn.q_proj",
+    "layers.11.self_attn.q_proj",
+    "layers.3.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.27.self_attn.q_proj",
+    "layers.15.mlp.down_proj",
+    "layers.12.self_attn.k_proj",
+    "layers.16.self_attn.k_proj",
+    "layers.13.mlp.down_proj",
+    "layers.9.self_attn.q_proj",
+    "layers.13.self_attn.q_proj",
+    "layers.12.mlp.down_proj",
+    "layers.22.self_attn.o_proj",
+    "layers.22.self_attn.q_proj",
+    "layers.1.self_attn.o_proj",
+    "layers.30.self_attn.q_proj",
+    "layers.24.self_attn.k_proj",
+    "layers.19.mlp.up_proj",
+    "layers.10.mlp.up_proj",
+    "layers.28.self_attn.v_proj",
+    "layers.31.self_attn.o_proj",
+    "layers.15.self_attn.v_proj",
+    "layers.22.self_attn.v_proj",
+    "layers.16.self_attn.q_proj",
+    "layers.27.mlp.up_proj",
+    "layers.20.self_attn.k_proj",
+    "layers.17.self_attn.o_proj",
+    "layers.29.self_attn.q_proj",
+    "layers.29.mlp.down_proj",
+    "layers.4.mlp.down_proj",
+    "layers.8.self_attn.q_proj",
+    "layers.25.mlp.down_proj",
+    "layers.11.self_attn.k_proj",
+    "layers.17.self_attn.q_proj",
+    "layers.2.self_attn.q_proj",
+    "layers.5.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.2.self_attn.o_proj",
+    "layers.16.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.27.self_attn.v_proj",
+    "layers.22.self_attn.k_proj",
+    "layers.26.self_attn.k_proj",
+    "layers.7.self_attn.v_proj",
+    "layers.9.self_attn.v_proj",
+    "layers.31.self_attn.v_proj",
+    "layers.3.self_attn.k_proj",
+    "layers.15.self_attn.k_proj",
+    "layers.19.self_attn.v_proj",
+    "layers.21.mlp.down_proj",
+    "layers.9.self_attn.k_proj",
+    "layers.19.self_attn.o_proj",
+    "layers.10.self_attn.v_proj",
+    "layers.9.self_attn.o_proj",
+    "layers.25.self_attn.o_proj",
+    "layers.24.mlp.down_proj",
+    "layers.31.self_attn.q_proj",
+    "layers.10.self_attn.q_proj",
+    "layers.18.self_attn.q_proj",
+    "layers.19.mlp.down_proj",
+    "layers.21.self_attn.k_proj",
+    "layers.20.mlp.down_proj",
+    "layers.24.self_attn.o_proj",
+    "layers.26.self_attn.q_proj",
+    "layers.11.self_attn.o_proj",
+    "layers.14.mlp.down_proj",
+    "layers.24.self_attn.q_proj",
+    "layers.28.mlp.up_proj",
+    "layers.23.self_attn.k_proj",
+    "layers.6.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.24.self_attn.v_proj",
+    "layers.30.self_attn.o_proj",
+    "layers.1.mlp.down_proj",
+    "layers.17.self_attn.v_proj",
+    "layers.18.self_attn.k_proj",
+    "layers.28.self_attn.q_proj",
+    "layers.21.mlp.up_proj",
+    "lm.head",
+    "layers.8.self_attn.v_proj",
+    "layers.23.self_attn.q_proj",
+    "layers.2.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1036/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b05dc849debef9d2fa3d53eb605c9ef6717dc69515f123150e532319ffcc78
+size 515951312

checkpoint-1036/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9740c97011df0478673668cd53ef61cc4884abb165f3a2681fa62d43f6b063c7
+size 258900244

checkpoint-1036/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d767e07218851864a3e29461588b6dfafd7c9c108116d6d6a78ac0df4990f92c
+size 14244

checkpoint-1036/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4e9e65b91e22f9fcd460c806a30334c2b2d47322a24d41e33a5bca2987066e
+size 1064

checkpoint-1036/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa70061cdbb7600b8f24d24febb8ee89ee01acb653af286c3ad5a4afa0f96e6
+size 5560

checkpoint-2072/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: sail/Sailor-7B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.1.dev0

checkpoint-2072/adapter_config.json

@@ -0,0 +1,219 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sail/Sailor-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.3.self_attn.v_proj",
+    "layers.30.self_attn.k_proj",
+    "layers.12.self_attn.o_proj",
+    "layers.3.mlp.up_proj",
+    "layers.1.self_attn.k_proj",
+    "layers.10.self_attn.o_proj",
+    "layers.28.self_attn.o_proj",
+    "layers.4.self_attn.v_proj",
+    "layers.3.self_attn.o_proj",
+    "layers.10.mlp.down_proj",
+    "layers.6.self_attn.o_proj",
+    "layers.1.self_attn.q_proj",
+    "layers.15.self_attn.q_proj",
+    "layers.7.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.27.self_attn.k_proj",
+    "layers.31.self_attn.k_proj",
+    "layers.30.mlp.down_proj",
+    "layers.17.mlp.down_proj",
+    "layers.14.self_attn.v_proj",
+    "layers.28.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.31.mlp.down_proj",
+    "layers.5.self_attn.o_proj",
+    "layers.6.mlp.down_proj",
+    "layers.17.mlp.up_proj",
+    "layers.26.self_attn.v_proj",
+    "layers.2.self_attn.v_proj",
+    "layers.7.self_attn.o_proj",
+    "layers.2.mlp.down_proj",
+    "layers.6.self_attn.v_proj",
+    "layers.18.self_attn.v_proj",
+    "layers.18.mlp.up_proj",
+    "layers.25.self_attn.v_proj",
+    "layers.0.self_attn.k_proj",
+    "layers.13.self_attn.v_proj",
+    "layers.10.self_attn.k_proj",
+    "layers.27.self_attn.o_proj",
+    "layers.0.self_attn.v_proj",
+    "layers.23.mlp.down_proj",
+    "layers.11.self_attn.v_proj",
+    "layers.30.mlp.up_proj",
+    "layers.20.self_attn.o_proj",
+    "layers.15.mlp.up_proj",
+    "layers.4.self_attn.k_proj",
+    "layers.9.mlp.up_proj",
+    "layers.29.self_attn.o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.21.self_attn.q_proj",
+    "layers.16.self_attn.o_proj",
+    "layers.12.self_attn.v_proj",
+    "layers.14.self_attn.q_proj",
+    "layers.29.self_attn.v_proj",
+    "layers.16.self_attn.v_proj",
+    "layers.28.self_attn.k_proj",
+    "layers.13.self_attn.o_proj",
+    "layers.13.self_attn.k_proj",
+    "layers.5.self_attn.v_proj",
+    "layers.7.self_attn.q_proj",
+    "layers.13.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.19.self_attn.k_proj",
+    "layers.26.self_attn.o_proj",
+    "layers.14.mlp.up_proj",
+    "layers.6.self_attn.k_proj",
+    "layers.23.self_attn.v_proj",
+    "layers.3.self_attn.q_proj",
+    "layers.1.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.7.self_attn.k_proj",
+    "layers.26.mlp.up_proj",
+    "layers.12.self_attn.q_proj",
+    "layers.21.self_attn.v_proj",
+    "layers.11.mlp.down_proj",
+    "layers.14.self_attn.o_proj",
+    "layers.8.self_attn.k_proj",
+    "layers.19.self_attn.q_proj",
+    "layers.23.self_attn.o_proj",
+    "layers.8.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.25.self_attn.q_proj",
+    "layers.29.mlp.up_proj",
+    "layers.20.self_attn.v_proj",
+    "layers.18.self_attn.o_proj",
+    "layers.17.self_attn.k_proj",
+    "layers.0.self_attn.o_proj",
+    "layers.1.self_attn.v_proj",
+    "layers.7.mlp.down_proj",
+    "layers.5.self_attn.k_proj",
+    "layers.29.self_attn.k_proj",
+    "layers.21.self_attn.o_proj",
+    "layers.20.self_attn.q_proj",
+    "layers.24.mlp.up_proj",
+    "layers.4.self_attn.q_proj",
+    "layers.22.mlp.down_proj",
+    "layers.14.self_attn.k_proj",
+    "layers.0.mlp.up_proj",
+    "layers.15.self_attn.o_proj",
+    "layers.18.mlp.down_proj",
+    "layers.8.self_attn.o_proj",
+    "layers.2.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.6.self_attn.q_proj",
+    "layers.16.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.12.mlp.up_proj",
+    "layers.30.self_attn.v_proj",
+    "layers.5.self_attn.q_proj",
+    "layers.25.self_attn.k_proj",
+    "layers.4.self_attn.o_proj",
+    "layers.0.self_attn.q_proj",
+    "layers.11.self_attn.q_proj",
+    "layers.3.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.27.self_attn.q_proj",
+    "layers.15.mlp.down_proj",
+    "layers.12.self_attn.k_proj",
+    "layers.16.self_attn.k_proj",
+    "layers.13.mlp.down_proj",
+    "layers.9.self_attn.q_proj",
+    "layers.13.self_attn.q_proj",
+    "layers.12.mlp.down_proj",
+    "layers.22.self_attn.o_proj",
+    "layers.22.self_attn.q_proj",
+    "layers.1.self_attn.o_proj",
+    "layers.30.self_attn.q_proj",
+    "layers.24.self_attn.k_proj",
+    "layers.19.mlp.up_proj",
+    "layers.10.mlp.up_proj",
+    "layers.28.self_attn.v_proj",
+    "layers.31.self_attn.o_proj",
+    "layers.15.self_attn.v_proj",
+    "layers.22.self_attn.v_proj",
+    "layers.16.self_attn.q_proj",
+    "layers.27.mlp.up_proj",
+    "layers.20.self_attn.k_proj",
+    "layers.17.self_attn.o_proj",
+    "layers.29.self_attn.q_proj",
+    "layers.29.mlp.down_proj",
+    "layers.4.mlp.down_proj",
+    "layers.8.self_attn.q_proj",
+    "layers.25.mlp.down_proj",
+    "layers.11.self_attn.k_proj",
+    "layers.17.self_attn.q_proj",
+    "layers.2.self_attn.q_proj",
+    "layers.5.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.2.self_attn.o_proj",
+    "layers.16.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.27.self_attn.v_proj",
+    "layers.22.self_attn.k_proj",
+    "layers.26.self_attn.k_proj",
+    "layers.7.self_attn.v_proj",
+    "layers.9.self_attn.v_proj",
+    "layers.31.self_attn.v_proj",
+    "layers.3.self_attn.k_proj",
+    "layers.15.self_attn.k_proj",
+    "layers.19.self_attn.v_proj",
+    "layers.21.mlp.down_proj",
+    "layers.9.self_attn.k_proj",
+    "layers.19.self_attn.o_proj",
+    "layers.10.self_attn.v_proj",
+    "layers.9.self_attn.o_proj",
+    "layers.25.self_attn.o_proj",
+    "layers.24.mlp.down_proj",
+    "layers.31.self_attn.q_proj",
+    "layers.10.self_attn.q_proj",
+    "layers.18.self_attn.q_proj",
+    "layers.19.mlp.down_proj",
+    "layers.21.self_attn.k_proj",
+    "layers.20.mlp.down_proj",
+    "layers.24.self_attn.o_proj",
+    "layers.26.self_attn.q_proj",
+    "layers.11.self_attn.o_proj",
+    "layers.14.mlp.down_proj",
+    "layers.24.self_attn.q_proj",
+    "layers.28.mlp.up_proj",
+    "layers.23.self_attn.k_proj",
+    "layers.6.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.24.self_attn.v_proj",
+    "layers.30.self_attn.o_proj",
+    "layers.1.mlp.down_proj",
+    "layers.17.self_attn.v_proj",
+    "layers.18.self_attn.k_proj",
+    "layers.28.self_attn.q_proj",
+    "layers.21.mlp.up_proj",
+    "lm.head",
+    "layers.8.self_attn.v_proj",
+    "layers.23.self_attn.q_proj",
+    "layers.2.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2072/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5249e878d0457fb9d6911b5154a443b832af001fb934d6e32d01b69390c81d4f
+size 515951312

checkpoint-2072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fa210ffd7d345400f86fb2df26418e676f25786299f937c1db3eb5692034ee
+size 258900244

checkpoint-2072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd0d6adc5021f17a6d77ac6b68fb70ca1d9fd5ead58ce37c1721ea2ef66aa83
+size 14244

checkpoint-2072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898d015d6b4cc63de52c6917a769d45a319b1d8b3784c078d7dfd8535a874791
+size 1064

checkpoint-2072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa70061cdbb7600b8f24d24febb8ee89ee01acb653af286c3ad5a4afa0f96e6
+size 5560

checkpoint-3108/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: sail/Sailor-7B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.1.dev0

checkpoint-3108/adapter_config.json

@@ -0,0 +1,219 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sail/Sailor-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.3.self_attn.v_proj",
+    "layers.30.self_attn.k_proj",
+    "layers.12.self_attn.o_proj",
+    "layers.3.mlp.up_proj",
+    "layers.1.self_attn.k_proj",
+    "layers.10.self_attn.o_proj",
+    "layers.28.self_attn.o_proj",
+    "layers.4.self_attn.v_proj",
+    "layers.3.self_attn.o_proj",
+    "layers.10.mlp.down_proj",
+    "layers.6.self_attn.o_proj",
+    "layers.1.self_attn.q_proj",
+    "layers.15.self_attn.q_proj",
+    "layers.7.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.27.self_attn.k_proj",
+    "layers.31.self_attn.k_proj",
+    "layers.30.mlp.down_proj",
+    "layers.17.mlp.down_proj",
+    "layers.14.self_attn.v_proj",
+    "layers.28.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.31.mlp.down_proj",
+    "layers.5.self_attn.o_proj",
+    "layers.6.mlp.down_proj",
+    "layers.17.mlp.up_proj",
+    "layers.26.self_attn.v_proj",
+    "layers.2.self_attn.v_proj",
+    "layers.7.self_attn.o_proj",
+    "layers.2.mlp.down_proj",
+    "layers.6.self_attn.v_proj",
+    "layers.18.self_attn.v_proj",
+    "layers.18.mlp.up_proj",
+    "layers.25.self_attn.v_proj",
+    "layers.0.self_attn.k_proj",
+    "layers.13.self_attn.v_proj",
+    "layers.10.self_attn.k_proj",
+    "layers.27.self_attn.o_proj",
+    "layers.0.self_attn.v_proj",
+    "layers.23.mlp.down_proj",
+    "layers.11.self_attn.v_proj",
+    "layers.30.mlp.up_proj",
+    "layers.20.self_attn.o_proj",
+    "layers.15.mlp.up_proj",
+    "layers.4.self_attn.k_proj",
+    "layers.9.mlp.up_proj",
+    "layers.29.self_attn.o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.21.self_attn.q_proj",
+    "layers.16.self_attn.o_proj",
+    "layers.12.self_attn.v_proj",
+    "layers.14.self_attn.q_proj",
+    "layers.29.self_attn.v_proj",
+    "layers.16.self_attn.v_proj",
+    "layers.28.self_attn.k_proj",
+    "layers.13.self_attn.o_proj",
+    "layers.13.self_attn.k_proj",
+    "layers.5.self_attn.v_proj",
+    "layers.7.self_attn.q_proj",
+    "layers.13.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.19.self_attn.k_proj",
+    "layers.26.self_attn.o_proj",
+    "layers.14.mlp.up_proj",
+    "layers.6.self_attn.k_proj",
+    "layers.23.self_attn.v_proj",
+    "layers.3.self_attn.q_proj",
+    "layers.1.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.7.self_attn.k_proj",
+    "layers.26.mlp.up_proj",
+    "layers.12.self_attn.q_proj",
+    "layers.21.self_attn.v_proj",
+    "layers.11.mlp.down_proj",
+    "layers.14.self_attn.o_proj",
+    "layers.8.self_attn.k_proj",
+    "layers.19.self_attn.q_proj",
+    "layers.23.self_attn.o_proj",
+    "layers.8.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.25.self_attn.q_proj",
+    "layers.29.mlp.up_proj",
+    "layers.20.self_attn.v_proj",
+    "layers.18.self_attn.o_proj",
+    "layers.17.self_attn.k_proj",
+    "layers.0.self_attn.o_proj",
+    "layers.1.self_attn.v_proj",
+    "layers.7.mlp.down_proj",
+    "layers.5.self_attn.k_proj",
+    "layers.29.self_attn.k_proj",
+    "layers.21.self_attn.o_proj",
+    "layers.20.self_attn.q_proj",
+    "layers.24.mlp.up_proj",
+    "layers.4.self_attn.q_proj",
+    "layers.22.mlp.down_proj",
+    "layers.14.self_attn.k_proj",
+    "layers.0.mlp.up_proj",
+    "layers.15.self_attn.o_proj",
+    "layers.18.mlp.down_proj",
+    "layers.8.self_attn.o_proj",
+    "layers.2.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.6.self_attn.q_proj",
+    "layers.16.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.12.mlp.up_proj",
+    "layers.30.self_attn.v_proj",
+    "layers.5.self_attn.q_proj",
+    "layers.25.self_attn.k_proj",
+    "layers.4.self_attn.o_proj",
+    "layers.0.self_attn.q_proj",
+    "layers.11.self_attn.q_proj",
+    "layers.3.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.27.self_attn.q_proj",
+    "layers.15.mlp.down_proj",
+    "layers.12.self_attn.k_proj",
+    "layers.16.self_attn.k_proj",
+    "layers.13.mlp.down_proj",
+    "layers.9.self_attn.q_proj",
+    "layers.13.self_attn.q_proj",
+    "layers.12.mlp.down_proj",
+    "layers.22.self_attn.o_proj",
+    "layers.22.self_attn.q_proj",
+    "layers.1.self_attn.o_proj",
+    "layers.30.self_attn.q_proj",
+    "layers.24.self_attn.k_proj",
+    "layers.19.mlp.up_proj",
+    "layers.10.mlp.up_proj",
+    "layers.28.self_attn.v_proj",
+    "layers.31.self_attn.o_proj",
+    "layers.15.self_attn.v_proj",
+    "layers.22.self_attn.v_proj",
+    "layers.16.self_attn.q_proj",
+    "layers.27.mlp.up_proj",
+    "layers.20.self_attn.k_proj",
+    "layers.17.self_attn.o_proj",
+    "layers.29.self_attn.q_proj",
+    "layers.29.mlp.down_proj",
+    "layers.4.mlp.down_proj",
+    "layers.8.self_attn.q_proj",
+    "layers.25.mlp.down_proj",
+    "layers.11.self_attn.k_proj",
+    "layers.17.self_attn.q_proj",
+    "layers.2.self_attn.q_proj",
+    "layers.5.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.2.self_attn.o_proj",
+    "layers.16.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.27.self_attn.v_proj",
+    "layers.22.self_attn.k_proj",
+    "layers.26.self_attn.k_proj",
+    "layers.7.self_attn.v_proj",
+    "layers.9.self_attn.v_proj",
+    "layers.31.self_attn.v_proj",
+    "layers.3.self_attn.k_proj",
+    "layers.15.self_attn.k_proj",
+    "layers.19.self_attn.v_proj",
+    "layers.21.mlp.down_proj",
+    "layers.9.self_attn.k_proj",
+    "layers.19.self_attn.o_proj",
+    "layers.10.self_attn.v_proj",
+    "layers.9.self_attn.o_proj",
+    "layers.25.self_attn.o_proj",
+    "layers.24.mlp.down_proj",
+    "layers.31.self_attn.q_proj",
+    "layers.10.self_attn.q_proj",
+    "layers.18.self_attn.q_proj",
+    "layers.19.mlp.down_proj",
+    "layers.21.self_attn.k_proj",
+    "layers.20.mlp.down_proj",
+    "layers.24.self_attn.o_proj",
+    "layers.26.self_attn.q_proj",
+    "layers.11.self_attn.o_proj",
+    "layers.14.mlp.down_proj",
+    "layers.24.self_attn.q_proj",
+    "layers.28.mlp.up_proj",
+    "layers.23.self_attn.k_proj",
+    "layers.6.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.24.self_attn.v_proj",
+    "layers.30.self_attn.o_proj",
+    "layers.1.mlp.down_proj",
+    "layers.17.self_attn.v_proj",
+    "layers.18.self_attn.k_proj",
+    "layers.28.self_attn.q_proj",
+    "layers.21.mlp.up_proj",
+    "lm.head",
+    "layers.8.self_attn.v_proj",
+    "layers.23.self_attn.q_proj",
+    "layers.2.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3108/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647d7c7ea41254629468f756b800db8c8b990cbd387cb76ab944a056c8449dbe
+size 515951312

checkpoint-3108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3048c513a709a3326e5ddcd2e903784e7957f5ab54aea44536cf7e823a4d4676
+size 258900244

checkpoint-3108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa9fec4ce6d77cc70ba336c0db662fb1d386591699c634fa7636fcbb2bc84ad
+size 14244

checkpoint-3108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece357ba5008202c6875696f25f985008223cc82e98ab7fc6c1e42dea66cd7dd
+size 1064

checkpoint-3108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa70061cdbb7600b8f24d24febb8ee89ee01acb653af286c3ad5a4afa0f96e6
+size 5560

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "sail/Sailor-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}