Resolved merge conflicts and fixed LFS tracking

.gitattributes

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +34,7 @@ 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
+=======
+adapter_model.bin filter=lfs diff=lfs merge=lfs -text
+>>>>>>> master
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-chat-hf
+---
+
+# 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]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2120679768b581cb5fa5413ec2c270c7bdb0d67f4243843e2bc65a092ede24
+size 134262410

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

chat_cli.py

@@ -0,0 +1,39 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+def chat_with_model(model_path: str):
+    # Ensure CUDA is available and set the device to use the first GPU
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"Using device: {device}")
+
+    # Load the model and tokenizer
+    model = AutoModelForCausalLM.from_pretrained(model_path).to(device)
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+    # Wrap the model with DataParallel to use multiple GPUs
+    if torch.cuda.is_available() and torch.cuda.device_count() > 1:
+        print(f"Using {torch.cuda.device_count()} GPUs!")
+        model = torch.nn.DataParallel(model)
+
+    print("You're now chatting with the model. Type 'quit' to exit.")
+
+    while True:
+        # Get user input
+        input_text = input("You: ")
+        if input_text.lower() == 'quit':
+            break
+
+        # Encode the input text
+        input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
+        
+        # Generate a response
+        with torch.no_grad():
+            generated_text_samples = model.generate(input_ids, max_length=50, pad_token_id=tokenizer.eos_token_id)
+
+        # Decode and print the model's response
+        response_text = tokenizer.decode(generated_text_samples[0], skip_special_tokens=True)
+        print("AI:", response_text)
+
+if __name__ == "__main__":
+    model_path = '/home/energyxadmin/UI2/merge'
+    chat_with_model(model_path)

merge_script.py

@@ -0,0 +1,63 @@
+import torch
+from peft import PeftModel  # Ensure you have 'peft' library or modify according to your setup
+import os
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
+import argparse
+from utils import get_logger  # Ensure this is implemented in your environment
+import json
+
+logger = get_logger("merge", "info")
+
+def smart_tokenizer_and_embedding_resize(tokenizer, model, custom_tokens_path=None):
+    """Resize tokenizer and embedding to accommodate new tokens."""
+    special_tokens_dict = {
+        "pad_token": "[PAD]",
+        "eos_token": "</s>",
+        "bos_token": "<s>",
+        "unk_token": "<unk>"
+    }
+    
+    # Load custom tokens if specified
+    custom_tokens = []
+    if custom_tokens_path is not None:
+        with open(custom_tokens_path, 'r') as file:
+            custom_tokens = [line.strip() for line in file.readlines()]
+
+    num_added_toks = tokenizer.add_special_tokens(special_tokens_dict)
+    if custom_tokens:
+        num_added_toks += tokenizer.add_tokens(custom_tokens, special_tokens=True)
+    
+    model.resize_token_embeddings(len(tokenizer))
+    logger.info(f"Resized tokenizer and model embeddings. Added {num_added_toks} tokens.")
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-bm", "--base_model", type=str, default="meta-llama/Llama-2-7b-chat-hf", help="Base model name or path")
+    parser.add_argument("-lm", "--lora_model", type=str, required=True, help="Path to the Lora model directory")
+    parser.add_argument("-o", "--output", type=str, required=True, help="Output directory for the merged model")
+    parser.add_argument("--custom_tokens", type=str, default=None, help="Path to a file containing custom tokens")
+    args = parser.parse_args()
+
+    if not os.path.exists(args.lora_model):
+        raise FileNotFoundError(f"LoRA model directory {args.lora_model} not found.")
+    
+    os.makedirs(args.output, exist_ok=True)
+    
+    # Load the base model and tokenizer
+    model = AutoModelForCausalLM.from_pretrained(args.base_model)
+    tokenizer = AutoTokenizer.from_pretrained(args.base_model)
+
+    # Adjust tokenizer and model for any additional tokens
+    smart_tokenizer_and_embedding_resize(tokenizer, model, args.custom_tokens)
+
+    # Load and merge the LoRA model
+    logger.info("Loading and merging the LoRA model...")
+    lora_model = PeftModel.from_pretrained(model, args.lora_model, merge_with_base=True)
+    
+    # Save the merged model and tokenizer
+    lora_model.save_pretrained(args.output)
+    tokenizer.save_pretrained(args.output)
+    logger.info(f"Merged model saved to {args.output}")
+
+if __name__ == "__main__":
+    main()

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test.py

@@ -0,0 +1,12 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = '/home/energyxadmin/UI2/merge'
+
+model = AutoModelForCausalLM.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+# Example text generation
+input_ids = tokenizer.encode("What song did Eric Pask write or was a part of", return_tensors="pt")
+generated_text_samples = model.generate(input_ids, max_length=1000)
+
+print("Generated text:", tokenizer.decode(generated_text_samples[0], skip_special_tokens=True))

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

utils.py

@@ -0,0 +1,17 @@
+import logging
+from typing_extensions import Literal
+from rich.logging import RichHandler
+
+
+def get_logger(name: str, level: Literal["info", "warning", "debug"]) -> logging.Logger:
+    rich_handler = RichHandler(level=logging.INFO, rich_tracebacks=True, markup=True)
+
+    logger = logging.getLogger(name)
+    logger.setLevel(logging._nameToLevel[level.upper()])
+
+    if not logger.handlers:
+        logger.addHandler(rich_handler)
+
+    logger.propagate = False
+
+    return logger