Update README.md

README.md

@@ -89,19 +89,19 @@ Refer to the Provided Files table below to see what files use which methods, and
 
 | Name | Quant method | Bits | Size | Use case |
 | ---- | ---- | ---- | ---- | ---- |
-| [tc-instruct-dpo.Q2_K.gguf](/tc-instruct-dpo.Q2_K.gguf) | Q2_K | 2 | 2.88 GB | smallest, significant quality loss - not recommended for most purposes |
-| [tc-instruct-dpo.Q3_K_S.gguf](/tc-instruct-dpo.Q3_K_S.gguf) | Q3_K_S | 3 | 2.96 GB | very small, high quality loss |
-| [tc-instruct-dpo.Q3_K_M.gguf](/tc-instruct-dpo.Q3_K_M.gguf) | Q3_K_M | 3 | 3.29 GB | very small, high quality loss |
-| [tc-instruct-dpo.Q3_K_L.gguf](/tc-instruct-dpo.Q3_K_L.gguf) | Q3_K_L | 3 | 3.57 GB | small, substantial quality loss |
-| [tc-instruct-dpo.Q4_0.gguf](/tc-instruct-dpo.Q4_0.gguf) | Q4_0 | 4 | 3.84 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [tc-instruct-dpo.Q4_K_S.gguf](/tc-instruct-dpo.Q4_K_S.gguf) | Q4_K_S | 4 | 3.87 GB | small, greater quality loss |
-| [tc-instruct-dpo.Q4_K_M.gguf](/tc-instruct-dpo.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB | medium, balanced quality - recommended |
-| [tc-instruct-dpo.Q5_0.gguf](/tc-instruct-dpo.Q5_0.gguf) | Q5_0 | 5 | 4.67 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [tc-instruct-dpo.Q5_K_S.gguf](/tc-instruct-dpo.Q5_K_S.gguf) | Q5_K_S | 5 | 4.67 GB | large, low quality loss - recommended |
-| [tc-instruct-dpo.Q5_K_M.gguf](/tc-instruct-dpo.Q5_K_M.gguf) | Q5_K_M | 5 | 4.79 GB | large, very low quality loss - recommended |
-| [tc-instruct-dpo.Q6_K.gguf](/tc-instruct-dpo.Q6_K.gguf) | Q6_K | 6 | 5.55 GB | very large, extremely low quality loss |
-| [tc-instruct-dpo.Q8_0.gguf](/tc-instruct-dpo.Q8_0.gguf) | Q8_0 | 8 | 7.19 GB | very large, extremely low quality loss - not recommended     |
-| [tc-instruct-dpo.QF16.gguf](/tc-instruct-dpo.Q8_0.gguf) | QF16 | 16 | 13.53 GB | largest, lowest quality loss - highly not recommended |
+| [tc-instruct-dpo.Q2_K.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q2_K.gguf) | Q2_K | 2 | 2.88 GB | smallest, significant quality loss - not recommended for most purposes |
+| [tc-instruct-dpo.Q3_K_S.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q3_K_S.gguf) | Q3_K_S | 3 | 2.96 GB | very small, high quality loss |
+| [tc-instruct-dpo.Q3_K_M.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q3_K_M.gguf) | Q3_K_M | 3 | 3.29 GB | very small, high quality loss |
+| [tc-instruct-dpo.Q3_K_L.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q3_K_L.gguf) | Q3_K_L | 3 | 3.57 GB | small, substantial quality loss |
+| [tc-instruct-dpo.Q4_0.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q4_0.gguf) | Q4_0 | 4 | 3.84 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [tc-instruct-dpo.Q4_K_S.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q4_K_S.gguf) | Q4_K_S | 4 | 3.87 GB | small, greater quality loss |
+| [tc-instruct-dpo.Q4_K_M.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB | medium, balanced quality - recommended |
+| [tc-instruct-dpo.Q5_0.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q5_0.gguf) | Q5_0 | 5 | 4.67 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [tc-instruct-dpo.Q5_K_S.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q5_K_S.gguf) | Q5_K_S | 5 | 4.67 GB | large, low quality loss - recommended |
+| [tc-instruct-dpo.Q5_K_M.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q5_K_M.gguf) | Q5_K_M | 5 | 4.79 GB | large, very low quality loss - recommended |
+| [tc-instruct-dpo.Q6_K.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q6_K.gguf) | Q6_K | 6 | 5.55 GB | very large, extremely low quality loss |
+| [tc-instruct-dpo.Q8_0.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q8_0.gguf) | Q8_0 | 8 | 7.19 GB | very large, extremely low quality loss - not recommended     |
+| [tc-instruct-dpo.QF16.gguf](https://huggingface.co/pek111/TC-instruct-DPO-GGUF/blob/main/tc-instruct-dpo.Q8_0.gguf) | QF16 | 16 | 13.53 GB | largest, lowest quality loss - highly not recommended |
 
 # Inference Code
 
@@ -153,3 +153,103 @@ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(f"Response time: {time.time() - st_time} seconds")
 print(response)
 ```
+
+# Original model card: tanamettpk's TC Instruct DPO - Typhoon 7B
+
+# TC-instruct-DPO - Typhoon 7B
+
+![image/png](https://i.seadn.io/gae/5rw87qeBGr0f4ieGyXPkLXaiVsQt_jYCI-2yjMn4W9rK3GBwy68W_3lO-ST_YPtAzhRBxb7ONhMe4YyYZNWM368dVGYnWGv6CIyYhA?auto=format&dpr=1&w=1400&fr=1)
+
+## Model Description
+
+TC instruct DPO finetuned มาจาก Typhoon 7B ของ SCB 10X ซึ่งมาจาก Mistral 7B - v0.1 อีกที
+
+TC instruct DPO ได้ทำการ Train กับ Data ภาษาไทยเท่าที่จะหาได้ และ พยายามให้ Instruct มีความต่างกันเท่าที่จะทำได้
+
+Model นี้ตั้งใจทำขึ้นเพื่อการศึกษาขั้นตอนในการสร้าง LLM เท่านั้น
+
+และอย่างที่บอกว่าเพื่อศึกษา และ เราไม่เคยสร้าง LLM มาก่อนหรือศึกษามาเป็นอย่างดีนัก
+
+เราเลยมีความโง่หลายๆอย่างเช่น เราใช้ Prompt template เป็น Alpaca template ซึ่งไอ้สัส มารู้ทีหลังว่าต้องใช้ ChatML ดีกว่า
+
+โดยการ Train Model นี้เราใช้ QLoRA Rank 32 Alpha 64
+
+Train ด้วย Custom Script ของ Huggingface (อย่าหาทำ ย้ายไปใช้ axolotl หรือ unsloth ดีกว่าประหยัดตัง)
+
+ใช้ H100 PCIE 80 GB 1 ตัวจาก vast.ai ราคาประมาณ 3$/hr Train แค่ Model นี้ก็ประมาณ 21 ชม. แต่ถ้ารวมลองผิดลองถูกด้วยก็ 10k บาท
+
+ด้วย Batch size 24 (จริงๆอยากใช้ 32 แต่ OOM และ 16 ก็แหม๋~~~ เพิล กูใช้ H100 80GB จะให้กู Train แค่ 40 GB บ้าบ้อ)
+
+## ถ้าใครเอาไปใช้แล้วมันช่วยได้จะมาช่วย Donate ให้จะขอบคุณมากๆ
+Tipme: https://bit.ly/3m3uH5p
+
+# Prompt Format
+```
+### Instruction:
+จะทำอะไรก็เรื่องของมึง
+
+### Response:
+ด่าผมอีกสิครับ
+```
+
+# Inference Code
+
+Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
+
+Note: To use function calling, you should see the github repo above.
+
+```python
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, GenerationConfig
+import time
+
+base_model_id = "tanamettpk/TC-instruct-DPO"
+
+
+input_text = """
+### Instruction:
+ด่าฉันด้วยคำหยาบคายหน่อย
+
+### Response:
+"""
+
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    device_map={"": 0},
+)
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+
+generation_config = GenerationConfig(
+    do_sample=True,
+    top_k=1,
+    temperature=0.5,
+    max_new_tokens=300,
+    repetition_penalty=1.1,
+    pad_token_id=tokenizer.eos_token_id)
+
+# Tokenize input
+inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
+
+# Generate outputs
+st_time = time.time()
+outputs = model.generate(**inputs, generation_config=generation_config)
+
+# Decode and print response
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(f"Response time: {time.time() - st_time} seconds")
+print(response)
+```
+
+# How to cite:
+
+```bibtext
+@misc{TC-instruct-DPO, 
+      url={[https://huggingface.co/tanamettpk/TC-instruct-DPO]https://huggingface.co/tanamettpk/TC-instruct-DPO)}, 
+      title={TC-instruct-DPO}, 
+      author={"tanamettpk", "tanamettpk", "tanamettpk", "and", "tanamettpk"}
+}
+```