Update README.md

README.md

@@ -5,4 +5,68 @@ language:
 tags:
 - mistral
 - text-generation-inference
----
+---
+### mistral-indo-7b
+
+[Mistral 7b v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) fine-tuned on [Indonesian's instructions dataset](https://huggingface.co/datasets/sarahlintang/Alpaca_indo_instruct).
+
+
+### Prompt template:
+```
+### Human: {Instruction}### Assistant: {response}
+```
+
+### Example of Usage
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer, GenerationConfig
+
+model_id = "sarahlintang/mistral-indo-7b"
+
+model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+def create_instruction(instruction):
+    prompt = f"### Human: {instruction} ### Assistant: "
+    return prompt
+
+
+def generate(
+        instruction,
+        max_new_tokens=128,
+        temperature=0.1,
+        top_p=0.75,
+        top_k=40,
+        num_beams=4,
+        **kwargs
+):
+    
+    prompt = create_instruction(instruction)
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].to("cuda")
+    attention_mask = inputs["attention_mask"].to("cuda")
+    generation_config = GenerationConfig(
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        num_beams=num_beams,
+        **kwargs,
+    )
+    with torch.no_grad():
+        generation_output = model.generate(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            generation_config=generation_config,
+            return_dict_in_generate=True,
+            output_scores=True,
+            max_new_tokens=max_new_tokens,
+            early_stopping=True
+        )
+    s = generation_output.sequences[0]
+    output = tokenizer.decode(s)
+    return output.split("### Assistant:")[1].strip()
+
+instruction = "Sebutkan lima macam makanan khas Indonesia."
+print(generate(instruction))
+
+```