Rename lumaticai_BongLlama-1.1B-Chat-alpha-v0_model_card.md to Readme.md

lumaticai_BongLlama-1.1B-Chat-alpha-v0_model_card.md → Readme.md

@@ -1,69 +1,18 @@
 ---
 
 ---
+# lumaticai/BongLlama-1.1B-Chat-alpha-v0
 
+Introducing BongLlama by LumaticAI. A finetuned version of TinyLlama 1.1B Chat on Bengali Dataset.
 
 
-
-
-
-# Model Card for lumaticai/BongLlama-1.1B-Chat-alpha-v0
-
-<!-- Provide a quick summary of what the model is/does. [Optional] -->
-Bongllama is a sub-part of our company&#39;s initiative for developing Indic and Regional Large Language Models. We are LumaticAI continuously working on helping our clients build Custom AI Solutions for their organization. 
-We have taken an initiative to launch open source models specific to regions and languages.
-
-Bongllama is a LLM built for West Bengal on Bengali dataset. It&#39;s a 1.1B parameters model. We have used a Bengali dataset of 10k data i.e lumatic-ai/BongChat-10k-v0 and finetuned on TinyLlama/TinyLlama-1.1B-Chat-v1.0 model to get our BongLlama 1.1B Chat Alpha v0 model. 
-
-We are continuously working on training and developing this model and improve it. We are also going to launch this model with various sizes of different LLM&#39;s and Datasets.
-
-
-
-
-#  Table of Contents
-
-- [Model Card for lumaticai/BongLlama-1.1B-Chat-alpha-v0](#model-card-for--model_id-)
-- [Table of Contents](#table-of-contents)
-- [Table of Contents](#table-of-contents-1)
-- [Model Details](#model-details)
-  - [Model Description](#model-description)
-- [Uses](#uses)
-  - [Direct Use](#direct-use)
-  - [Downstream Use [Optional]](#downstream-use-optional)
-  - [Out-of-Scope Use](#out-of-scope-use)
-- [Bias, Risks, and Limitations](#bias-risks-and-limitations)
-  - [Recommendations](#recommendations)
-- [Training Details](#training-details)
-  - [Training Data](#training-data)
-  - [Training Procedure](#training-procedure)
-    - [Preprocessing](#preprocessing)
-    - [Speeds, Sizes, Times](#speeds-sizes-times)
-- [Evaluation](#evaluation)
-  - [Testing Data, Factors & Metrics](#testing-data-factors--metrics)
-    - [Testing Data](#testing-data)
-    - [Factors](#factors)
-    - [Metrics](#metrics)
-  - [Results](#results)
-- [Model Examination](#model-examination)
-- [Environmental Impact](#environmental-impact)
-- [Technical Specifications [optional]](#technical-specifications-optional)
-  - [Model Architecture and Objective](#model-architecture-and-objective)
-  - [Compute Infrastructure](#compute-infrastructure)
-    - [Hardware](#hardware)
-    - [Software](#software)
-- [Citation](#citation)
-- [Glossary [optional]](#glossary-optional)
-- [More Information [optional]](#more-information-optional)
-- [Model Card Authors [optional]](#model-card-authors-optional)
-- [Model Card Contact](#model-card-contact)
-- [How to Get Started with the Model](#how-to-get-started-with-the-model)
+<img class="custom-image" src="llama.png" alt="BongLlama">
 
 
 # Model Details
 
 ## Model Description
 
-<!-- Provide a longer summary of what this model is/does. -->
 Bongllama is a sub-part of our company&#39;s initiative for developing Indic and Regional Large Language Models. We are LumaticAI continuously working on helping our clients build Custom AI Solutions for their organization. 
 We have taken an initiative to launch open source models specific to regions and languages.
 
@@ -71,34 +20,24 @@ Bongllama is a LLM built for West Bengal on Bengali dataset. It&#39;s a 1.1B par
 
 We are continuously working on training and developing this model and improve it. We are also going to launch this model with various sizes of different LLM&#39;s and Datasets.
 
-- **Developed by:** L, u, m, a, t, i, c, A, I
-- **Shared by [Optional]:** L, u, m, a, t, i, c, A, I
+- **Developed by:** LumaticAI
+- **Shared by [Optional]:** LumaticAI
 - **Model type:** Language model
 - **Language(s) (NLP):** en, bn
 - **License:** apache-2.0
-- **Parent Model:** More information needed
-- **Resources for more information:** More information needed
-
+- **Parent Model:** TinyLlama/TinyLlama-1.1B-Chat-v1.0
 
 
 # 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. -->
-<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
-
 - base model for further finetuning
 - get an overview of how indic LLM work on specific language
 - for fun
 
 
 ## Downstream Use [Optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
  
 - can be deployed with api
 - used to create webapp or app to show demo
@@ -106,51 +45,33 @@ We are continuously working on training and developing this model and improve it
 
 ## Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
-
 - cannot be used for production purpose
 - cannot be used to generate text for research or academic purposes
 
 
 # Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
 Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
 
 
-## Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-
-
-
-
 # Training Details
 
 ## Training Data
 
-<!-- This should link to a Data 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. -->
+we used our dataset of 10k data which consists of Questions and Responses. The dataset name is lumatic-ai/BongChat-v0-10k.
 
-&lt;|im_start|&gt;user এটি কি ইতিবাচক পর্যালোচনা? এই ফ্র্যাঞ্চাইজি কখনও হার্ট স্টপ স্টান্টস, ফাইট সিকোয়েন্স এবং তারকা শক্তি বন্ধ করে হতাশ করে না।এবার মূল চারটি ছাড়াও নতুন মুখগুলি হলেন আবুয়েলিতা চরিত্রে রিতা মোরেনো এবং দান্তে জেসন মোমোয়া যিনি শোটি চুরি করেছেন।&lt;|im_end|&gt; &lt;|im_start|&gt;assistant এটি একটি খুব ইতিবাচক পর্যালোচনা, এটি ইঙ্গিত করে যে ফ্র্যাঞ্চাইজি শ্রোতাদের জন্য আরও পছন্দসই চরিত্রগুলি যুক্ত করার পাশাপাশি অতীতের প্রত্যাশার ভিত্তিতে বিতরণ করেছে।&lt;|im_end|&gt;
+**Example Data**
+- &lt;|im_start|&gt;user এটি কি ইতিবাচক পর্যালোচনা? এই ফ্র্যাঞ্চাইজি কখনও হার্ট স্টপ স্টান্টস, ফাইট সিকোয়েন্স এবং তারকা শক্তি বন্ধ করে হতাশ করে না।এবার মূল চারটি ছাড়াও নতুন মুখগুলি হলেন আবুয়েলিতা চরিত্রে রিতা মোরেনো এবং দান্তে জেসন মোমোয়া যিনি শোটি চুরি করেছেন।&lt;|im_end|&gt; &lt;|im_start|&gt;assistant এটি একটি খুব ইতিবাচক পর্যালোচনা, এটি ইঙ্গিত করে যে ফ্র্যাঞ্চাইজি শ্রোতাদের জন্য আরও পছন্দসই চরিত্রগুলি যুক্ত করার পাশাপাশি অতীতের প্রত্যাশার ভিত্তিতে বিতরণ করেছে।&lt;|im_end|&gt;
 
 
 ## 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
 
 - Dataset Format
 &lt;|im_start|&gt;user &lt;question&gt;&lt;|im_end|&gt; &lt;|im_start|&gt;assistant &lt;response&gt;&lt;|im_end|&gt;
 
-### Speeds, Sizes, Times
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-## Training hyperparameters
+### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
@@ -165,7 +86,7 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
-## Framework versions
+### Framework versions
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
@@ -174,27 +95,8 @@ The following hyperparameters were used during training:
  
 # Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-## Testing Data, Factors & Metrics
-
-### Testing Data
-
-<!-- This should link to a Data 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. -->
-
 - train/loss
 - steps
 
@@ -245,8 +147,6 @@ We will be further finetuning this model on large dataset to see how it performs
 
 # 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:** 1 X Tesla T4
@@ -255,23 +155,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 - **Compute Region:** India
 - **Carbon Emitted:** 0.14
 
-# Technical Specifications [optional]
+# Technical Specifications
 
 ## Model Architecture and Objective
 
 Finetuned on Tiny-Llama 1.1B Chat model
 
-## Compute Infrastructure
-
-More information needed
 
 ### Hardware
 
 1 X Tesla T4
 
-### Software
-
-More information needed
 
 # Citation
 
@@ -279,10 +173,6 @@ More information needed
 
 **BibTeX:**
 
-More information needed
-
-**APA:**
-
 @misc{BongLlama-1.1B-Chat-alpha-v0,
       url={[https://huggingface.co/lumatic-ai/BongLlama-1.1B-Chat-alpha-v0](https://huggingface.co/lumatic-ai/BongLlama-1.1B-Chat-alpha-v0)},
       title={BongLlama 1.1B Chat Aplha V0},
@@ -290,19 +180,8 @@ More information needed
       year={2024}, month={Jan}
 }
 
-# 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]
 
-<!-- This section provides another layer of transparency and accountability. Whose views is this model card representing? How many voices were included in its construction? Etc. -->
+# Model Card Authors
 
 lumatic-ai
 
@@ -317,6 +196,108 @@ Use the code below to get started with the model.
 <details>
 <summary> Click to expand </summary>
 
-# ⚠️ Type of model unknown
+### Pipeline
+
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+
+def formatted_prompt(question)-> str:
+    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"
+
+hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"
+
+tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
+pipe = pipeline(
+    "text-generation",
+    model=hub_model_name,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+from time import perf_counter
+start_time = perf_counter()
+
+prompt = formatted_prompt('হ্যালো')
+sequences = pipe(
+    prompt,
+    do_sample=True,
+    temperature=0.1,
+    top_p=0.9,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+    max_new_tokens=256
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+
+output_time = perf_counter() - start_time
+print(f"Time taken for inference: {round(output_time,2)} seconds")
+```
+
+### Streaming Response (ChatGPT, Bard like)
+
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+def formatted_prompt(question)-> str:
+    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"
+
+hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"
+
+tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
+model = AutoModelForCausalLM.from_pretrained(hub_model_name)
+
+prompt = formatted_prompt('prompt here')
+inputs = tokenizer([prompt], return_tensors="pt")
+streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, eos_token_id=[tokenizer.eos_token_id],streamer=streamer, max_new_tokens=256)
+```
+
+### Using Generation Config
+
+```
+import torch
+from transformers import GenerationConfig
+from time import perf_counter
+
+def formatted_prompt(question)-> str:
+    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"
+
+hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"
+
+tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
+model = AutoModelForCausalLM.from_pretrained(hub_model_name)
+
+prompt = formatted_prompt('হ্যালো')
+
+# Check for GPU availability
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
+
+# Move model and inputs to the GPU (if available)
+model.to(device)
+inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+generation_config = GenerationConfig(
+    penalty_alpha=0.6,
+    do_sample=True,
+    top_k=5,
+    temperature=0.5,
+    repetition_penalty=1.2,
+    max_new_tokens=256,
+    pad_token_id=tokenizer.eos_token_id
+)
+
+start_time = perf_counter()
+outputs = model.generate(**inputs, generation_config=generation_config)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+output_time = perf_counter() - start_time
+print(f"Time taken for inference: {round(output_time, 2)} seconds")
+```
 
 </details>