Upload folder using huggingface_hub

README.md

@@ -1,3 +1,131 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+license: apache-2.0
+library_name: peft
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+base_model: DavidLanz/Meta-Llama-3-8B-Instruct
+model_name: Llama 3 8B Instruct
+inference: false
+model_creator: Meta Llama 3
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: QLoRA
+---
+
+# Model Card for Model ID
+
+This PEFT model is designed for predicting the prices of these five Taiwan stocks:
+
+| 證券代號 | 證券名稱 |
+|---------|--------|
+| 3661    | 世芯-KY |
+| 2330    | 台積電   |
+| 3017    | 奇鋐     |
+| 2618    | 長榮航   |
+| 2317    | 鴻海     |
+
+Disclaimer: This model is for a time series problem on LLM performance, and it's not for investment advice; any prediction results are not a basis for investment reference.
+
+## Model Details
+
+The training data source is from the [臺灣證券交易所](https://www.twse.com.tw/).
+
+### Model Description
+
+This repo contains QLoRA format model files for [Meta's Llama 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
+
+## Uses
+
+```python
+import torch
+from peft import LoraConfig, PeftModel
+
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+    HfArgumentParser,
+    TrainingArguments,
+    TextStreamer,
+    pipeline,
+    logging,
+)
+
+device_map = {"": 0}
+use_4bit = True
+bnb_4bit_compute_dtype = "float16"
+bnb_4bit_quant_type = "nf4"
+use_nested_quant = False
+compute_dtype = getattr(torch, bnb_4bit_compute_dtype)
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=use_4bit,
+    bnb_4bit_quant_type=bnb_4bit_quant_type,
+    bnb_4bit_compute_dtype=compute_dtype,
+    bnb_4bit_use_double_quant=use_nested_quant,
+)
+
+based_model_path = "meta-llama/Meta-Llama-3-8B-Instruct"
+adapter_path = "DavidLanz/llama3_8b_taiwan_stock_qlora"
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    based_model_path,
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    quantization_config=bnb_config,
+    torch_dtype=torch.float16,
+    device_map=device_map,
+)
+model = PeftModel.from_pretrained(base_model, adapter_path)
+
+tokenizer = AutoTokenizer.from_pretrained(based_model_path, trust_remote_code=True)
+
+import torch
+from transformers import pipeline, TextStreamer
+
+text_gen_pipeline = pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    tokenizer=tokenizer,
+)
+
+messages = [
+    {
+        "role": "system",
+        "content": "你是一位專業的台灣股市交易分析師",
+    },
+    {"role": "user", "content": "股票名稱為台積電，股票代號為2330。關於昨日的表現，開盤價為761，當日最高價為761，最低價為752，收盤價為754，與前一日相比漲了12，交易量為32,067,682，成交金額為24,247,217,869。請預測今天的收盤價?"},
+]
+
+prompt = text_gen_pipeline.tokenizer.apply_chat_template(
+        messages, 
+        tokenize=False, 
+        add_generation_prompt=True
+)
+
+terminators = [
+    text_gen_pipeline.tokenizer.eos_token_id,
+    text_gen_pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = text_gen_pipeline(
+    prompt,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][len(prompt):])
+```
+
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "DavidLanz/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f4837c5d0ffaa6c6346d274d466394f32114230f5c0ef96ba5ef5b59d4eed5
+size 109069176