commit initial model artifacts

.gitattributes

@@ -33,3 +33,5 @@ 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
+finetuned_conversations.pth filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,254 @@
 ---
 license: other
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- falcon
+- falcon-40b
+- prompt answering
+- peft
 ---
+
+## Model Card for Model ID
+
+This repository contains further fine-tuned falcon-40b model on conversations and question answering prompts.
+
+**I used falcon-40b (https://huggingface.co/tiiuae/falcon-40b) as a base model, so this model has the same license with falcon-40b model (Apache-2.0)**
+
+
+## Model Details
+
+Anyone can use (ask prompts) and play with the model using the pre-existing Jupyter Notebook in the **noteboooks** folder. The Jupyter Notebook contains example code to load the model and ask prompts to it as well as example prompts to get you started.
+
+### Model Description
+
+The tiiuae/falcon-40b model was finetuned on conversations and question answering prompts.
+
+**Developed by:** [More Information Needed]
+
+**Shared by:** [More Information Needed]
+
+**Model type:** Causal LM
+
+**Language(s) (NLP):** English, multilingual
+
+**License:** Apache-2.0
+
+**Finetuned from model:** tiiuae/falcon-40b
+
+
+## Model Sources [optional]
+
+**Repository:** [More Information Needed]
+**Paper:** [More Information Needed]
+**Demo:** [More Information Needed]
+
+## Uses
+
+The model can be used for prompt answering
+
+
+### Direct Use
+
+The model can be used for prompt answering
+
+
+### Downstream Use
+
+Generating text and prompt answering
+
+
+## Recommendations
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+
+# Usage
+
+## Creating prompt
+
+The model was trained on the following kind of prompt:
+
+```python
+def generate_prompt(prompt: str) -> str:
+    return f"""
+    <human>: {prompt}
+    <assistant>: 
+    """.strip()
+```
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+1. You can git clone the repo, which contains also the artifacts for the base model for simplicity and completeness, and run the following code snippet to load the mode:
+
+```python
+import torch
+from peft import PeftConfig, PeftModel
+from transformers import GenerationConfig, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
+MODEL_NAME = "."
+
+config = PeftConfig.from_pretrained(MODEL_NAME)
+
+compute_dtype = getattr(torch, "float16")
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=compute_dtype,
+    bnb_4bit_use_double_quant=True,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path,
+    quantization_config=bnb_config,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+model = PeftModel.from_pretrained(model, MODEL_NAME)
+
+generation_config = model.generation_config
+generation_config.top_p = 0.7
+generation_config.num_return_sequences = 1
+generation_config.max_new_tokens = 32
+generation_config.use_cache = False
+generation_config.pad_token_id = tokenizer.eos_token_id
+generation_config.eos_token_id = tokenizer.eos_token_id
+
+model.eval()
+if torch.__version__ >= "2":
+    model = torch.compile(model)
+```
+
+### Example of Usage
+```python
+prompt = "What is the capital city of Greece and with which countries does Greece border?"
+
+prompt = generate_prompt(prompt)
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+input_ids = input_ids.to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        input_ids=input_ids,
+        generation_config=generation_config,
+        return_dict_in_generate=True,
+        output_scores=True,
+    )
+
+response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+print(response)
+
+>>> The capital city of Greece is Athens and it borders Albania, Bulgaria, Macedonia, and Turkey.
+```
+
+2. You can also directly call the model from HuggingFace using the following code snippet:
+
+```python
+import torch
+from peft import PeftConfig, PeftModel
+from transformers import GenerationConfig, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
+MODEL_NAME = "Sandiago21/falcon-40b-prompt-answering"
+BASE_MODEL = "tiiuae/falcon-40b"
+
+compute_dtype = getattr(torch, "float16")
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=compute_dtype,
+    bnb_4bit_use_double_quant=True,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    quantization_config=bnb_config,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+model = PeftModel.from_pretrained(model, MODEL_NAME)
+
+generation_config = model.generation_config
+generation_config.top_p = 0.7
+generation_config.num_return_sequences = 1
+generation_config.max_new_tokens = 32
+generation_config.use_cache = False
+generation_config.pad_token_id = tokenizer.eos_token_id
+generation_config.eos_token_id = tokenizer.eos_token_id
+
+model.eval()
+if torch.__version__ >= "2":
+    model = torch.compile(model)
+```
+
+### Example of Usage
+
+```python
+prompt = "What is the capital city of Greece and with which countries does Greece border?"
+
+prompt = generate_prompt(prompt)
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+input_ids = input_ids.to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        input_ids=input_ids,
+        generation_config=generation_config,
+        return_dict_in_generate=True,
+        output_scores=True,
+    )
+
+response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+print(response)
+
+>>> The capital city of Greece is Athens and it borders Albania, Bulgaria, Macedonia, and Turkey.
+```
+
+## Training Details
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.12.0
+- Tokenizers 0.12.1
+
+### Training Data
+
+The tiiuae/falcon-40b was finetuned on conversations and question answering data
+
+### Training Procedure
+
+The tiiuae/falcon-40b model was further trained and finetuned on question answering and prompts data for 1 epoch (approximately 10 hours of training on a single GPU)
+
+## Model Architecture and Objective
+
+The model is based on tiiuae/falcon-40b model and finetuned adapters on top of the main model on conversations and question answering data.

adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-40b",
+  "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,
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17eb2eb3871449a810505692bcd9d51ed01938e9125d74e627a93104de3cc676
+size 267431853

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "tiiuae/falcon-40b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-40b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-40b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-40b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-40b--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWeb",
+  "n_head": 128,
+  "n_head_kv": 8,
+  "n_layer": 60,
+  "parallel_attn": true,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": false,
+  "vocab_size": 65024
+}

finetuned_conversations.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1a352d4f1ab628ee67132bea9332505baab31553d204dcd8fd9f5e10af73a1
+size 22790689091

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948fcb4cb227f09823443ff3813dd14daa7d033268d72bea3a4ff38989b28bf0
+size 22790664801

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e639b3ce4423bde112dbf3ebf2ac94b3cc7aee6acc1ecfbb17baeb71c95be1
+size 3963