EleutherAI
/

Hermes-RWKV-v5-3B-HF

@@ -1,190 +1,49 @@
 ---
 license: apache-2.0
 ---
-![An eagle soaring above a transformer robot](https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6bbd31a7-21b4-4ff6-b43f-8735d1decf25_2048x1652.png)
-### Huggingface RWKV-5 Eagle 7B Model - via HF Transformers Library
-> **! Important Note !**
->
-> The following is the HF transformers implementation of the RWKV-5 Eagle 7B model. **This is meant to be used with the huggingface transformers**
->
-> For the full model weights on its own, to use with other RWKV libraries, refer to [here](https://huggingface.co/RWKV/v5-Eagle-7B)
->
-> This is not an instruct tune model! (soon...)
-- [HF Demo](https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-2)
-- [Our wiki](https://wiki.rwkv.com)
-- [pth model weights](https://huggingface.co/RWKV/v5-Eagle-7B)
-#### Running on CPU via HF transformers
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-def generate_prompt(instruction, input=""):
-    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
-    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
-    if input:
-        return f"""Instruction: {instruction}
-Input: {input}
-Response:"""
-    else:
-        return f"""User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: {instruction}
-Assistant:"""
-model = AutoModelForCausalLM.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True).to(torch.float32)
-tokenizer = AutoTokenizer.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True)
-text = "请介绍北京的旅游景点"
-prompt = generate_prompt(text)
-inputs = tokenizer(prompt, return_tensors="pt")
-output = model.generate(inputs["input_ids"], max_new_tokens=333, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
-print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
-```
-output:
-```shell
-User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: 请介绍北京的旅游景点
-Assistant: 北京是中国的首都，拥有众多的旅游景点，以下是其中一些著名的景点：
-1. 故宫：位于北京市中心，是明清两代的皇宫，内有大量的文物和艺术品。
-2. 天安门广场：是中国最著名的广场之一，是中国人民政治协商会议的旧址，也是中国人民政治协商会议的中心。
-3. 颐和园：是中国古代皇家园林之一，有着悠久的历史和丰富的文化内涵。
-4. 长城：是中国古代的一道长城，全长约万里，是中国最著名的旅游景点之一。
-5. 北京大学：是中国著名的高等教育机构之一，有着悠久的历史和丰富的文化内涵。
-6. 北京动物园：是中国最大的动物园之一，有着丰富的动物资源和丰富的文化内涵。
-7. 故宫博物院：是中国最著名的博物馆之一，收藏了大量的文物和艺术品，是中国最重要的文化遗产之一。
-8. 天坛：是中国古代皇家
 ```
-#### Running on GPU via HF transformers
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-def generate_prompt(instruction, input=""):
-    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
-    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
-    if input:
-        return f"""Instruction: {instruction}
-Input: {input}
-Response:"""
-    else:
-        return f"""User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: {instruction}
-Assistant:"""
-model = AutoModelForCausalLM.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True, torch_dtype=torch.float16).to(0)
-tokenizer = AutoTokenizer.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True)
-text = "介绍一下大熊猫"
-prompt = generate_prompt(text)
-inputs = tokenizer(prompt, return_tensors="pt").to(0)
-output = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
-print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
 ```
-output:
-```shell
-User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: 介绍一下大熊猫
-Assistant: 大熊猫是一种中国特有的哺乳动物，也是中国的国宝之一。它们的外貌特征是圆形的黑白相间的身体，有着黑色的毛发和白色的耳朵。大熊猫的食物主要是竹子，它们会在竹林中寻找竹子，并且会将竹子放在竹笼中进行储存。大熊猫的寿命约为20至30年，但由于栖息地的丧失和人类活动的
-```
-#### Batch Inference
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-def generate_prompt(instruction, input=""):
-    instruction = instruction.strip().replace('\r\n', '\n').replace('\n\n', '\n')
-    input = input.strip().replace('\r\n', '\n').replace('\n\n', '\n')
-    if input:
-        return f"""Instruction: {instruction}
-Input: {input}
-Response:"""
-    else:
-        return f"""User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: {instruction}
-Assistant:"""
-model = AutoModelForCausalLM.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True).to(torch.float32)
-tokenizer = AutoTokenizer.from_pretrained("RWKV/HF_v5-Eagle-7B", trust_remote_code=True)
-texts = ["请介绍北京的旅游景点", "介绍一下大熊猫", "乌兰察布"]
-prompts = [generate_prompt(text) for text in texts]
-inputs = tokenizer(prompts, return_tensors="pt", padding=True)
-outputs = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
-for output in outputs:
-    print(tokenizer.decode(output.tolist(), skip_special_tokens=True))
-```
-output:
-```shell
-User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: 请介绍北京的旅游景点
-Assistant: 北京是中国的首都，拥有丰富的旅游资源和历史文化遗产。以下是一些北京的旅游景点：
-1. 故宫：位于北京市中心，是明清两代的皇宫，是中国最大的古代宫殿建筑群之一。
-2. 天安门广场：位于北京市中心，是中国最著名的城市广场之一，也是中国最大的城市广场。
-3. 颐和
-User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: 介绍一下大熊猫
-Assistant: 大熊猫是一种生活在中国中部地区的哺乳动物，也是中国的国宝之一。它们的外貌特征是圆形的黑白相间的身体，有着黑色的毛发和圆圆的眼睛。大熊猫是一种濒危物种，目前只有在野外的几个保护区才能看到它们的身影。大熊猫的食物主要是竹子，它们会在竹子上寻找食物，并且可以通
-User: hi
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
-User: 乌兰察布
-Assistant: 乌兰察布是中国新疆维吾尔自治区的一个县级市，位于新疆维吾尔自治区中部，是新疆的第二大城市。乌兰察布市是新疆的第一大城市，也是新疆的重要城市之一。乌兰察布市是新疆的经济中心，也是新疆的重要交通枢纽之一。乌兰察布市的人口约为2.5万人，其中汉族占绝大多数。乌
-```

 ---
 license: apache-2.0
+datasets:
+- teknium/OpenHermes-2.5
+language:
+- en
 ---
+This is a 3B parameter RWKV-v5 ("Eagle") RNN language model pretrained on multi-lingual data and fine-tuned on Nous Research's OpenHermes 2.5 chat dataset.
+The chat format is identical to the default HuggingFace format, **EXCEPT** that we replace the `<|im_start|>` and `<|im_end|>` special tokens with the unused ASCII codes `"\x16"` and `"\x17"` respectively. This was done to ensure complete compatibility withe standard RWKV World tokenizer.
+An example interaction:
 ```
+\x16user
+Write a poem about the beauty of mathematics in the style of Emily Dickinson.\x17
+\x16assistant
+In the heart of Numbers, so precise,
+A Beauty dwells - both cool and nice.
+An elegance that sings in sums,
+And dances to algebraic drums.
+Addition's grace, subtraction's might,
+Multiplication's sheer delight,
+Division's firm yet gentle hand,
+All part of this enchanted land.
+Infinity, a lover bold,
+To whom the stars their secrets told,
+While Zero, cloaked in mystery,
+Unlocks each mathematical decree.
+Fractals bloom like flowers wild,
+Geometry, Nature's favored child,
+Calculus, with steady gaze,
+Maps out life's intricate maze.
+Pi, an endless serenade,
+In circles' arms forever laid,
+And prime numbers,
+standing lone,
+Make the universe their own.
+Each equation, theorem scribed,
+In
+parchment old or computer imbibed,
+Is but a whisper from the skies,
+A cosmic truth in disguise.\x17
 ```
+In the above, newlines are printed without escaping, while ASCII codes are escaped for readability.