初始化项目，由ModelHub XC社区提供模型

Model: wenbopan/Faro-Yi-9B-DPO
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+language:
+- en
+- zh
+license: mit
+datasets:
+- wenbopan/Chinese-dpo-pairs
+- Intel/orca_dpo_pairs
+- argilla/ultrafeedback-binarized-preferences-cleaned
+- jondurbin/truthy-dpo-v0.1
+pipeline_tag: text-generation
+---
+
+# Faro-Yi-9B-DPO
+
+This is the DPO version of [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan/Faro-Yi-9B). Compared to Faro-Yi-9B and [Yi-9B-200K](https://huggingface.co/01-ai/Yi-9B-200K), the DPO model excels at many tasks, surpassing the original Yi-9B-200K by a large margin. On the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), it ranks **#2** among all 9B models, **#1** among all Yi-9B variants.
+
+| **Metric**              | **MMLU**  | **GSM8K** | **hellaswag** | **truthfulqa** | **ai2_arc** | **winogrande** | **CMMLU** |
+| ----------------------- | --------- | --------- | ------------- | -------------- | ----------- | -------------- | --------- |
+| **Yi-9B-200K**          | 65.73     | 50.49     | 56.72         | 33.80          | 69.25       | 71.67          | 71.97     |
+| **Faro-Yi-9B**          | 68.80     | 63.08     | 57.28         | 40.86          | 72.58       | 71.11          | 73.28     |
+| **Faro-Yi-9B-DPO**      | **69.98** | **66.11** | **59.04**     | **48.01**      | **75.68**   | **73.40**      | **75.23** |
+
+Faro-Yi-9B-DPO's responses are also favored by GPT-4 Judge in MT-Bench
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd3a3691d27e60db0698b0/ArlnloL4aPfiiD6kUqaSH.png)
+
+## How to Use
+
+Faro-Yi-9B-DPO uses the chatml template and performs well in both short and long contexts. For longer inputs under **24GB of VRAM**, I recommend to use vLLM to have a max prompt of 32K. Setting `kv_cache_dtype="fp8_e5m2"` allows for 48K input length. 4bit-AWQ quantization on top of that can boost input length to 160K, albeit with some performance impact. Adjust `max_model_len` arg in vLLM or `config.json` to avoid OOM.
+
+
+```python
+import io
+import requests
+from PyPDF2 import PdfReader
+from vllm import LLM, SamplingParams
+
+llm = LLM(model="wenbopan/Faro-Yi-9B-DPO", kv_cache_dtype="fp8_e5m2", max_model_len=100000)
+
+pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
+document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages
+
+question = f"{document}\n\nAccording to the paper, what is the parameter count of GPT-4?"
+messages = [ {"role": "user", "content": question} ] # 83K tokens
+prompt = llm.get_tokenizer().apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+output = llm.generate(prompt, SamplingParams(temperature=0.8, max_tokens=500))
+print(output[0].outputs[0].text)
+# Yi-9B-200K:      175B. GPT-4 has 175B \nparameters. How many models were combined to create GPT-4? Answer: 6. ...
+# 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. ...
+```
+
+
+<details> <summary>Or With Transformers</summary>
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Yi-9B-DPO', device_map="cuda")
+tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Yi-9B-DPO')
+messages = [
+    {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
+    {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
+]
+
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
+generated_ids = model.generate(input_ids, max_new_tokens=512, temperature=0.5)
+response = 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. ...
+```
+
+</details>

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/cephfs/panwenbo/work/models/Faro-9B-200K",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    7
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.39.3"
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: /cephfs/panwenbo/work/models/Faro-9B-200K
+  - model: /cephfs/panwenbo/work/models/Faro-Yi-9B-DPO
+merge_method: slerp
+base_model: /cephfs/panwenbo/work/models/Faro-9B-200K
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5 # fallback for rest of tensors
+dtype: float16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0108dc2146ee0b179d396a4247664e161127e9ad50a3acb7f5d9fa09361d5cdd
+size 9999691672

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d138aecbc5228aa58d8975daf3038c7af69b540e8ab0fec0e6f3d49e5a04877d
+size 7659172936

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}