Upload 10 files

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,50 @@
 ---
-license: mit
+tags:
+- medical
 ---
+Please note that the chatbot is designed for research purposes only and is not intended for use in real medical settings. While the chatbot has been trained to provide accurate and helpful responses, it is not a substitute for professional medical advice, diagnosis, or treatment. The information provided by the chatbot should not be used to make medical decisions, and any health concerns should be addressed by a licensed healthcare provider.
+
+## Quickstart
+
+```python
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+
+path = "jianghc/medical_chatbot"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer = GPT2Tokenizer.from_pretrained(path)
+model = GPT2LMHeadModel.from_pretrained(path).to(device)
+
+prompt_input = (
+    "The conversation between human and AI assistant.\n"
+    "[|Human|] {input}\n"
+    "[|AI|]"
+)
+sentence = prompt_input.format_map({'input': "what is parkinson's disease?"})
+inputs = tokenizer(sentence, return_tensors="pt").to(device)
+
+with torch.no_grad():
+    beam_output = model.generate(**inputs,
+                                min_new_tokens=1, 
+                                max_length=512,
+                                num_beams=3,
+                                repetition_penalty=1.2,
+                                early_stopping=True,
+                                eos_token_id=198 
+                                )
+    print(tokenizer.decode(beam_output[0], skip_special_tokens=True))
+```
+
+## Example Outputs
+```
+The conversation between human and AI assistant.
+[|Human|] what is parkinson's disease?
+[|AI|] Parkinson's disease is a neurodegenerative disorder that affects movement. It is caused by the loss of dopamine-producing cells in the brain.
+```
+
+```
+The conversation between human and AI assistant.
+[|Human|] what type of honey is best for a bad covid cough?
+[|AI|] Manuka honey has been shown to have anti-inflammatory and antibacterial properties that can help alleviate symptoms of a bad covid cough.
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 28895
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "biomedLM_baize/checkpoint-1000",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 28895,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 28895,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 2560,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": false,
+  "vocab_size": 28896
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 28895,
+  "eos_token_id": 28895,
+  "transformers_version": "4.26.1",
+  "use_cache": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cac4bd8d32e7fce74c7cc3dc5bba17fefa7c26942f36916557ee9a3a3d7f0ba
+size 10410689701

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "[PAD]",
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "biomedLM_baize/checkpoint-1000",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}