Upload README.md

README.md

@@ -1,3 +1,164 @@
 ---
 license: apache-2.0
+language:
+- en
+library_name: transformers
+inference: false
 ---
+# h2oGPT Model Card
+## Summary
+
+H2O.ai's `h2ogpt-oasst1-512-12b` is a 12 billion parameter instruction-following large language model licensed for commercial use.
+
+- Base model: EleutherAI/pythia-12b
+- Fine-tuning dataset: [h2oai/openassistant_oasst1](https://huggingface.co/datasets/h2oai/openassistant_oasst1)
+- Data-prep and fine-tuning code: [H2O.ai Github](https://github.com/h2oai/h2ogpt)
+- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-oasst1-512-12b/blob/main/pythia-12b.openassistant_oasst1.json.1_epochs.d45a9d34d34534e076cc6797614b322bd0efb11c.15.zip)
+
+## Usage
+
+To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `accelerate` libraries installed.
+
+```bash
+pip install transformers==4.28.1
+```
+
+```python
+import torch
+from transformers import pipeline
+
+generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+res = generate_text("Why is drinking water so healthy?")
+print(res[0]["generated_text"])
+```
+
+Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-oasst1-512-12b/blob/main/h2oai_pipeline.py),
+store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
+
+```
+import torch
+from h2oai_pipeline import H2OTextGenerationPipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", padding_side="left")
+model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", device_map="auto", torch_dtype=torch.bfloat16)
+
+generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
+```
+
+### 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.
+
+```
+import torch
+from transformers import pipeline
+
+generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-12b", 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:
+
+```
+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:
+
+```
+print(llm_chain.predict(instruction="Why is drinking water so healthy?").lstrip())
+```
+
+Example predicting using an instruction with context:
+
+```
+context = """Model A: AUC=0.8
+Model from Driverless AI: AUC=0.95
+Model C: AUC=0.6
+Model D: AUC=0.7
+"""
+
+print(llm_context_chain.predict(instruction="Which model performs best?", context=context).lstrip())
+```
+
+## Model Architecture
+
+```
+GPTNeoXForCausalLM(
+  (gpt_neox): GPTNeoXModel(
+    (embed_in): Embedding(50688, 5120)
+    (layers): ModuleList(
+      (0-35): 36 x GPTNeoXLayer(
+        (input_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
+        (post_attention_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
+        (attention): GPTNeoXAttention(
+          (rotary_emb): RotaryEmbedding()
+          (query_key_value): Linear(in_features=5120, out_features=15360, bias=True)
+          (dense): Linear(in_features=5120, out_features=5120, bias=True)
+        )
+        (mlp): GPTNeoXMLP(
+          (dense_h_to_4h): Linear(in_features=5120, out_features=20480, bias=True)
+          (dense_4h_to_h): Linear(in_features=20480, out_features=5120, bias=True)
+          (act): GELUActivation()
+        )
+      )
+    )
+    (final_layer_norm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
+  )
+  (embed_out): Linear(in_features=5120, out_features=50688, bias=False)
+)
+```
+
+## Model Configuration
+
+```
+GPTNeoXConfig {
+  "_name_or_path": "h2oai/h2ogpt-oasst1-512-12b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM"
+    }
+  },
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50688
+}
+
+```