Update README.md

README.md

@@ -2,4 +2,37 @@
 datasets:
 - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
 license: llama2
----
+---
+
+## llama2-7b-WizardLM-alpaca-evol-instruct-35k-mini
+
+It is a 4-bit qlora refinement of llama-v2-guanaco, fine tuned on the 15k rows of Hermes dataset.
+
+## Example:
+
+```
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "aloobun/llama2-7b-WizardLM-alpaca-evol-instruct-35k-mini"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+sequences = pipeline(
+    f'[INST] {prompt} [/INST]',
+    do_sample=True,
+    top_k=10,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+    max_length=200,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```