First model version

.gitattributes

@@ -33,3 +33,6 @@ 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
+data/alpaca_synth_queries_healed.jsonl filter=lfs diff=lfs merge=lfs -text
+adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
+*.psd filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1 @@
----
-title: Shit
-emoji: ⚡
-colorFrom: red
-colorTo: green
-sdk: streamlit
-sdk_version: 1.35.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This directory contains the jsonl data used to train this model

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+# Load the model and tokenizer
+model = AutoModelForSequenceClassification.from_pretrained("./", local_files_only=True)
+tokenizer = AutoTokenizer.from_pretrained("gpt2")
+
+def classify_text(text):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_id = logits.argmax().item()
+    return "Proper Naming Notfcn" if predicted_class_id == 1 else "Wrong Naming Notificn"
+
+iface = gr.Interface(fn=classify_text, inputs="text", outputs="text", title="Classification Naming", description="Classify naming notifications as proper or wrong.")
+iface.launch()

data/README.md

@@ -0,0 +1 @@
+This directory contains the jsonl data used to train this model

data/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

data/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151496a8692deab90e4393beefaf341e8f67bdda2df9d2c62e2cf913122aeba5
+size 335604696

data/configs_hc.yml

@@ -0,0 +1,91 @@
+base_model: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+lora_fan_in_fan_out: false
+data_seed: 49
+seed: 49
+
+datasets:
+  - path: /teamspace/studios/this_studio/axolotl/finetune_maven/hc-mistral-alpaca/data/alpaca_synth_queries_healed.jsonl
+    type: sharegpt
+    conversation: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./qlora-alpaca-out
+hub_model_id: valLabsz/clssfcn-naming
+#hub_model_id: hamel/hc-mistral-alpaca
+
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 896
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+#wandb_project: hc-axolotl-mistral
+#wandb_entity: hamelsmu
+
+gradient_accumulation_steps: 4
+micro_batch_size: 16
+eval_batch_size: 16
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+max_grad_norm: 1.0
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+save_total_limit: 12
+
+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
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 20
+evals_per_epoch: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 6
+debug:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+save_safetensors: true

data/notfcn_B17.jsonl

@@ -0,0 +1,2 @@
+{"text": "No"}
+{"text": "Yes"}