updated

README.md

@@ -0,0 +1,219 @@
+---
+license: apache-2.0
+language:
+- en
+datasets:
+- togethercomputer/RedPajama-Data-1T
+- OpenAssistant/oasst1
+- databricks/databricks-dolly-15k
+widget:
+- text: "<human>: Write an email to my friends inviting them to come to my home on Friday for a dinner party, bring their own food to share.\n<bot>:"
+  example_title: "Email Writing"
+- text: "<human>: Create a list of things to do in San Francisco\n<bot>:"
+  example_title: "Brainstorming"
+inference:
+  parameters:
+    temperature: 0.7
+    top_p: 0.7
+    top_k: 50
+    max_new_tokens: 128
+---
+
+# RedPajama-INCITE-Chat-3B-v1
+
+RedPajama-INCITE-Chat-3B-v1 was developed by Together and leaders from the open-source AI community including Ontocord.ai, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. 
+
+It is fine-tuned on OASST1 and Dolly2 to enhance chatting ability.
+
+  - Base Model: [RedPajama-INCITE-Base-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1)
+  - Instruction-tuned Version: [RedPajama-INCITE-Instruct-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1)
+  - Chat Version: [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1)
+
+
+## Model Details
+- **Developed by**: Together Computer.
+- **Model type**: Language Model
+- **Language(s)**: English
+- **License**: Apache 2.0
+- **Model Description**: A 2.8B parameter pretrained language model.
+
+# Quick Start
+
+Please note that the model requires `transformers` version >= 4.25.1.
+
+To prompt the chat model, use the following format:
+```
+<human>: [Instruction]
+<bot>:
+```
+
+## GPU Inference
+
+This requires a GPU with 8GB memory.
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+# infer
+prompt = "<human>: Who is Alan Turing?\n<bot>:"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+Alan Turing was a British mathematician, logician, cryptologist, and computer scientist. He is widely regarded as the father of computer science and artificial intelligence.
+"""
+```
+
+## GPU Inference in Int8
+
+This requires a GPU with 6GB memory.
+
+To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:
+
+```bash
+pip install accelerate
+pip install bitsandbytes
+```
+
+Then you can run inference with int8 as follows:
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", device_map='auto', torch_dtype=torch.float16, load_in_8bit=True)
+
+# infer
+prompt = "<human>: Who is Alan Turing?\n<bot>:"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+Alan Turing was a British mathematician and computer scientist who made important contributions to computer science and mathematical logic. He is widely regarded as the father of computer science and artificial intelligence for his work on the Turing machine and Turing test.
+"""
+```
+
+## CPU Inference
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MIN_TRANSFORMERS_VERSION = '4.25.1'
+
+# check transformers version
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+
+# init
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.bfloat16)
+# infer
+prompt = "<human>: Who is Alan Turing?\n<bot>:"
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+input_length = inputs.input_ids.shape[1]
+outputs = model.generate(
+    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+)
+token = outputs.sequences[0, input_length:]
+output_str = tokenizer.decode(token)
+print(output_str)
+"""
+Alan Turing was a British mathematician and computer scientist who made important contributions to the fields of mathematics, cryptography, and computer science. He is widely regarded as the father of computer science and artificial intelligence.
+"""
+```
+
+Please note that since `LayerNormKernelImpl` is not implemented in fp16 for CPU, we use `bfloat16` for CPU inference.
+
+
+# Uses
+
+Excluded uses are described below.
+
+### Misuse, Malicious Use, and Out-of-Scope Use
+
+It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.
+
+#### Out-of-Scope Use
+
+`RedPajama-INCITE-Chat-3B-v1` is a language model and may not perform well for other use cases outside of its intended scope. 
+For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. 
+It is important to consider the limitations of the model and to only use it for its intended purpose.
+
+#### Misuse and Malicious Use
+
+`RedPajama-INCITE-Chat-3B-v1` is designed for language modeling.
+Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.
+
+Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
+
+- Generating fake news, misinformation, or propaganda
+- Promoting hate speech, discrimination, or violence against individuals or groups
+- Impersonating individuals or organizations without their consent
+- Engaging in cyberbullying or harassment
+- Defamatory content
+- Spamming or scamming
+- Sharing confidential or sensitive information without proper authorization
+- Violating the terms of use of the model or the data used to train it
+- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming
+
+## Limitations
+
+`RedPajama-INCITE-Chat-3B-v1`, like other language models, has limitations that should be taken into consideration. 
+For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. 
+We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.
+
+## Training
+
+**Training Data**
+
+Please refer to [togethercomputer/RedPajama-Data-1T](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)
+
+**Training Procedure**
+
+- **Hardware:** 8 A100
+- **Optimizer:** Adam
+- **Gradient Accumulations**: 1
+- **Num of Tokens:** 131M tokens
+- **Learning rate:** 1e-5
+
+## Community
+
+Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
+
+## Model Download
+
+The model weights (`pytorch_model.bin`) are stored on Google Drive due to file size limitations. Download the model file from the link below:
+
+[Download Model Weights](https://drive.google.com/uc?id=YOUR_FILE_ID)
+
+After downloading, place the file in the appropriate directory before running the scripts.

app.py

@@ -0,0 +1,71 @@
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import logging
+import os
+
+# Logging setup
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Hugging Face Model Hub Repository
+MODEL_REPO = "./"  # Replace with your Hugging Face model repo name
+
+# Load tokenizer and model from Hugging Face Model Hub
+try:
+    logging.info("Loading model and tokenizer from Hugging Face Model Hub...")
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
+    dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
+    model = AutoModelForCausalLM.from_pretrained(MODEL_REPO, torch_dtype=dtype).to(
+        "cuda" if torch.cuda.is_available() else "cpu"
+    )
+    logging.info("Model loaded successfully.")
+except Exception as e:
+    logging.error("Failed to load the model or tokenizer.", exc_info=True)
+    raise e
+
+# Flask app initialization
+app = Flask(__name__)
+CORS(app)  # Enable CORS
+
+def generate_response(prompt):
+    """Generate a response from the model given a prompt."""
+    try:
+        logging.debug(f"Generating response for prompt: {prompt}")
+        inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+        input_length = inputs.input_ids.shape[1]
+        outputs = model.generate(
+            **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+        )
+        token = outputs.sequences[0, input_length:]
+        output_str = tokenizer.decode(token, skip_special_tokens=True)
+        logging.debug(f"Generated response: {output_str}")
+        return output_str
+    except Exception as e:
+        logging.error("Error during response generation", exc_info=True)
+        return "Sorry, I encountered an error while generating the response."
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    """Endpoint to handle chat requests."""
+    try:
+        logging.debug("Received a POST request to /chat")
+        data = request.json
+        logging.debug(f"Request data: {data}")
+
+        if not data or "message" not in data:
+            return jsonify({"error": "Invalid request. 'message' field is required."}), 400
+
+        user_input = data.get("message", "")
+        prompt = f"<human>: {user_input}\n<bot>:"
+        response = generate_response(prompt)
+        return jsonify({"response": response}), 200
+    except Exception as e:
+        logging.error("Error in /chat endpoint", exc_info=True)
+        return jsonify({"error": "Internal server error", "message": str(e)}), 500
+
+if __name__ == "__main__":
+    # Get the port from environment variable or default to 5000
+    port = int(os.getenv("PORT", 5000))
+    logging.info(f"Starting Flask app on port {port}")
+    app.run(debug=True, host="0.0.0.0", port=port)

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/fm/models/rp_3b_800b_real_fp16",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8207c48c9830f6a0298f67bed916c78c9c27147006ed1f66ee122dcb1fdfd9c4
+size 5686106713

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}