information

README.md

@@ -5,4 +5,71 @@ datasets:
 metrics:
 - accuracy
 pipeline_tag: text-generation
----
+---
+
+## Summary
+
+`Deer-3b`, an instruction-following large language model trained on the open source dataset
+that is licensed for commercial use. Based on `Bloom-3b`, Deer is trained on ~15k instruction/response fine tuning records 
+[`databricks-dolly-15k`](https://github.com/databrickslabs/dolly/tree/master/data) generated 
+by Databricks.
+
+Deer will also be available in larger models size.
+
+## Model Overview
+`deer-3b` is a 3 billion parameter causal language model created that is derived from 
+[Blooms’s] 3B model and fine-tuned 
+on a [~15K record instruction corpus](https://github.com/databrickslabs/dolly/tree/master/data) generated by Databricks.
+
+## Usage
+
+To use the model with the `transformers` library on a machine with GPUs.
+
+```python
+import torch
+from transformers import pipeline
+generate_text = pipeline(model="PSanni/Deer-3b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+```
+
+You can then use the pipeline to answer instructions:
+
+```python
+res = generate_text("Explain to me the difference between nuclear fission and fusion.")
+print(res[0]["generated_text"])
+```
+
+### LangChain Usage
+
+To use the pipeline with LangChain, you must set `return_full_text=True`, as LangChain expects the full text to be returned 
+and the default for the pipeline is to only return the new text.
+
+```python
+import torch
+from transformers import pipeline
+generate_text = pipeline(model="PSanni/Deer-3b", torch_dtype=torch.bfloat16,
+                         trust_remote_code=True, device_map="auto", return_full_text=True)
+```
+
+You can create a prompt that either has only an instruction or has an instruction with context:
+
+```python
+from langchain import PromptTemplate, LLMChain
+from langchain.llms import HuggingFacePipeline
+# template for an instrution with no input
+prompt = PromptTemplate(
+    input_variables=["instruction"],
+    template="{instruction}")
+# template for an instruction with input
+prompt_with_context = PromptTemplate(
+    input_variables=["instruction", "context"],
+    template="{instruction}\n\nInput:\n{context}")
+hf_pipeline = HuggingFacePipeline(pipeline=generate_text)
+llm_chain = LLMChain(llm=hf_pipeline, prompt=prompt)
+llm_context_chain = LLMChain(llm=hf_pipeline, prompt=prompt_with_context)
+```
+
+Example predicting using a simple instruction:
+
+```python
+print(llm_chain.predict(instruction="Give me list of morning exercises.").lstrip())
+```