End of training

README.md

@@ -1,80 +1,53 @@
-# KUET CHATBOT
-Contributed by Jesiara Khatun and Sadia Islam (CSE 2K19, KUET)
-```
-!pip install peft -q
-!pip install transformers[sentencepiece] -q
-!pip install sentencepiece
-!pip install accelerate
-!pip install bitsandbytes
-```
-
-```
-import torch
-from peft import PeftModel
-import transformers
-import textwrap
-from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
-from transformers.generation.utils import GreedySearchDecoderOnlyOutput
-
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-DEVICE
-tokenizer = LlamaTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
-
-model = LlamaForCausalLM.from_pretrained(
-    "abhishek/llama-2-7b-hf-small-shards",
-    load_in_4bit=True,
-    device_map="auto",
-)
-
-model = PeftModel.from_pretrained(model, "shahidul034/kuet_chatbot", torch_dtype=torch.float16)
-model.config.pad_token_id = tokenizer.pad_token_id = 0  # unk
-model.config.bos_token_id = 1
-model.config.eos_token_id = 2
- 
-model = model.eval()
-model = torch.compile(model)
-PROMPT_TEMPLATE = f"""
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
- 
-### Instruction:
-[INSTRUCTION]
- 
-### Response:
-"""
-
-
-def create_prompt(instruction: str) -> str:
-    return PROMPT_TEMPLATE.replace("[INSTRUCTION]", instruction)
- 
-# print(create_prompt("What is (are) Glaucoma ?"))
-
-def generate_response(prompt: str, model: PeftModel) -> GreedySearchDecoderOnlyOutput:
-    encoding = tokenizer(prompt, return_tensors="pt")
-    input_ids = encoding["input_ids"].to(DEVICE)
- 
-    generation_config = GenerationConfig(
-        temperature=0.1,
-        top_p=0.75,
-        repetition_penalty=1.1,
-    )
-    with torch.inference_mode():
-        return model.generate(
-            input_ids=input_ids,
-            generation_config=generation_config,
-            return_dict_in_generate=True,
-            output_scores=True,
-            max_new_tokens=256,
-        )
-def format_response(response: GreedySearchDecoderOnlyOutput) -> str:
-    decoded_output = tokenizer.decode(response.sequences[0])
-    response = decoded_output.split("### Response:")[1].strip()
-    return "\n".join(textwrap.wrap(response))
-
-def ask_alpaca(prompt: str, model: PeftModel = model) -> str:
-    prompt = create_prompt(prompt)
-    response = generate_response(prompt, model)
-    print(format_response(response))
-
-ask_alpaca("where is kuet located?")
-
-```
+---
+license: apache-2.0
+base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
+tags:
+- generated_from_trainer
+model-index:
+- name: KUET_information_LLM
+  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. -->
+
+# KUET_information_LLM
+
+This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) 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: 0.0002
+- train_batch_size: 24
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 600
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0