Upload 9 files

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+widget:
+ - messages:
+ - role: user
+ content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+ model_path,
+ device_map="auto",
+ torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+ {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,29 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.6-mistral-7b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "q_proj",
+ "v_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "<|im_start|>": 32000
+}

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": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fa86fecf7687a2e3344d244af624fbcdf98948cc95179ba5cb5a62da099974
+size 4920

training_params.json

@@ -0,0 +1,48 @@
+{
+ "model": "cognitivecomputations/dolphin-2.6-mistral-7b",
+ "project_name": "Atorinv01",
+ "data_path": "C:\\AI\\training\\datasets",
+ "train_split": "train",
+ "valid_split": null,
+ "add_eos_token": false,
+ "block_size": 256,
+ "model_max_length": 1024,
+ "padding": null,
+ "trainer": "sft",
+ "use_flash_attention_2": false,
+ "log": "none",
+ "disable_gradient_checkpointing": false,
+ "logging_steps": -1,
+ "evaluation_strategy": "epoch",
+ "save_total_limit": 1,
+ "save_strategy": "epoch",
+ "auto_find_batch_size": false,
+ "mixed_precision": null,
+ "lr": 0.0002,
+ "epochs": 2,
+ "batch_size": 6,
+ "warmup_ratio": 0.1,
+ "gradient_accumulation": 1,
+ "optimizer": "adamw_torch",
+ "scheduler": "linear",
+ "weight_decay": 0.0,
+ "max_grad_norm": 1.0,
+ "seed": 42,
+ "chat_template": null,
+ "quantization": "int4",
+ "target_modules": null,
+ "merge_adapter": false,
+ "peft": true,
+ "lora_r": 16,
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "model_ref": null,
+ "dpo_beta": 0.1,
+ "prompt_text_column": "prompt",
+ "text_column": "text",
+ "rejected_text_column": "rejected",
+ "push_to_hub": false,
+ "repo_id": null,
+ "username": null,
+ "token": null
+}