Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| Faro-Yi-34B-DPO.Q2_K.gguf | Q2_K | 11.94GB |
| Faro-Yi-34B-DPO.IQ3_XS.gguf | IQ3_XS | 13.26GB |
| Faro-Yi-34B-DPO.IQ3_S.gguf | IQ3_S | 13.99GB |
| Faro-Yi-34B-DPO.Q3_K_S.gguf | Q3_K_S | 13.93GB |
| Faro-Yi-34B-DPO.IQ3_M.gguf | IQ3_M | 14.5GB |
| Faro-Yi-34B-DPO.Q3_K.gguf | Q3_K | 15.51GB |
| Faro-Yi-34B-DPO.Q3_K_M.gguf | Q3_K_M | 15.51GB |
| Faro-Yi-34B-DPO.Q3_K_L.gguf | Q3_K_L | 16.89GB |
| Faro-Yi-34B-DPO.IQ4_XS.gguf | IQ4_XS | 17.36GB |
| Faro-Yi-34B-DPO.Q4_0.gguf | Q4_0 | 18.13GB |
| Faro-Yi-34B-DPO.IQ4_NL.gguf | IQ4_NL | 18.3GB |
| Faro-Yi-34B-DPO.Q4_K_S.gguf | Q4_K_S | 18.25GB |
| Faro-Yi-34B-DPO.Q4_K.gguf | Q4_K | 19.24GB |
| Faro-Yi-34B-DPO.Q4_K_M.gguf | Q4_K_M | 19.24GB |
| Faro-Yi-34B-DPO.Q4_1.gguf | Q4_1 | 20.1GB |
| Faro-Yi-34B-DPO.Q5_0.gguf | Q5_0 | 22.08GB |
| Faro-Yi-34B-DPO.Q5_K_S.gguf | Q5_K_S | 22.08GB |
| Faro-Yi-34B-DPO.Q5_K.gguf | Q5_K | 22.65GB |
| Faro-Yi-34B-DPO.Q5_K_M.gguf | Q5_K_M | 22.65GB |
| Faro-Yi-34B-DPO.Q5_1.gguf | Q5_1 | 24.05GB |
| Faro-Yi-34B-DPO.Q6_K.gguf | Q6_K | 26.28GB |
| Faro-Yi-34B-DPO.Q8_0.gguf | Q8_0 | 34.03GB |
1import io
2import requests
3from PyPDF2 import PdfReader
4from vllm import LLM, SamplingParams
5
6llm = LLM(model="wenbopan/Faro-Yi-34B-DPO", kv_cache_dtype="fp8_e5m2", max_model_len=100000)
7
8pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
9document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages
10
11question = f"{document}\n\nAccording to the paper, what is the parameter count of GPT-4?"
12messages = [ {"role": "user", "content": question} ] # 83K tokens
13prompt = llm.get_tokenizer().apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
14output = llm.generate(prompt, SamplingParams(temperature=0.8, max_tokens=500))
15print(output[0].outputs[0].text)
16# Yi-9B-200K: 175B. GPT-4 has 175B \nparameters. How many models were combined to create GPT-4? Answer: 6. ...
17# Faro-Yi-9B: GPT-4 does not have a publicly disclosed parameter count due to the competitive landscape and safety implications of large-scale models like GPT-4. ...1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Yi-34B-DPO', device_map="cuda")
4tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Yi-34B-DPO')
5messages = [
6 {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
7 {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
8]
9input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
10generated_ids = model.generate(input_ids, max_new_tokens=512, temperature=0.5)
11response = tokenizer.decode(generated_ids[0], skip_special_tokens=True) # Aye, matey! The Pythagorean theorem is a nautical rule that helps us find the length of the third side of a triangle. ...