GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wesjos
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wesjos
Model Tree
utter-project/EuroLLM-9B
Input Modalities
Output Modalities
Supported Functionality
| Item | Value |
|---|---|
| Base model | utter-project/EuroLLM-9B |
| Training method | SFT (supervised fine-tuning) |
| Framework | TRL SFTTrainer + Unsloth |
| Training data | tatsu-lab/alpaca |
| Prompt format | Alpaca instruction template |
| Parameters | 5100.6 M |
| Context length | 4,096 tokens |
| Precision | 4bit-nf4 |
python
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "wesjos/EuroLLM-9B-Alpaca"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto") PROMPT = """Below is an instruction that describes a task. Write a response that \appropriately completes the request. ### Instruction:{instruction} ### Input:{input} ### Response:""" text = PROMPT.format(instruction="Explain what a GPU is to a 10-year-old child.", input="")ids = tok(text, return_tensors="pt").to(model.device)out = model.generate(**ids, max_new_tokens=256, do_sample=False)print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))python
from transformers import pipelinep = pipeline("text-generation", model="wesjos/EuroLLM-9B-Alpaca")print(p(PROMPT.format(instruction="Explain what a GPU is to a 10-year-old child.", input=""), max_new_tokens=256, return_full_text=False)[0]["generated_text"])Greedy decoding (
do_sample=False),max_new_tokens=300, one Tesla T4, measured 2026-10-04. Raw transcripts — nothing hand-edited.
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:Explain what a GPU is to a 10-year-old child. ### Input: ### Response:text
A GPU, or Graphic Processing Unit, is a type of computer processor that is designed to handle graphics and visual data. It is used to render images and videos, and is often used in gaming and other applications that require fast and efficient processing of visual data. It is like a super-fast artist that can draw and paint images and videos in a very short amount of time.79 tokens · 8.9 s
reverse_linked_list() in Pythontext
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:Write a Python function that reverses a singly linked list. Include a docstring. ### Input: ### Response:text
Here is a Python function that reverses a singly linked list: ```pythonclass Node: def __init__(self, data): self.data = data self.next = None def reverse_list(head): if head is None: return head prev = None curr = head while curr: next_node = curr.next curr.next = prev prev = curr curr = next_node head = prev return head``` This function takes a head node of the linked list as input and reverses the list. It uses a two-pointer approach to reverse the list. The first pointer, `prev`, is initially set to `None` and the second pointer, `curr`, is set to the head of the linked list. The function then iterates through the linked list, updating the pointers to reverse the list. Finally, the function returns the reversed head node.237 tokens · 22.6 s
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:A farmer has 17 sheep. All but 9 run away. How many are left? Explain your reasoning. ### Input: ### Response:text
The farmer has 17 sheep. 9 sheep ran away, so the farmer has 17 - 9 = 8 sheep left.31 tokens · 3.1 s
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:Summarize the following passage in one sentence. ### Input:The Voyager 1 spacecraft, launched in 1977, has travelled farther from Earth than any other human-made object. It crossed into interstellar space in 2012 and continues to transmit data using power from its radioisotope thermoelectric generators, though mission engineers expect its instruments to be shut down sometime in the 2030s. ### Response:text
The Voyager 1 spacecraft, launched in 1977, is the farthest human-made object from Earth and continues to transmit data using power from its radioisotope thermoelectric generators.43 tokens · 4.3 s
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:用三句话向一个刚学编程的大学生解释什么是「过拟合」。 ### Input: ### Response:text
过拟合是指模型过度适应训练数据,导致在训练集上表现良好,但在新的数据上表现不佳。它发生在模型变得过于复杂,开始捕捉训练数据中的噪音和偶然性,而不是模式和关系。过拟合的模型在训练集上表现良好,但在新的数据上表现不佳。76 tokens · 7.7 s
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:I keep procrastinating on my thesis. Give me one concrete tactic, not generic advice. ### Input: ### Response:text
One concrete tactic to help you stop procrastinating on your thesis is to break it down into smaller tasks. Start by breaking your thesis down into smaller tasks, such as researching, writing, and editing. Then, set a timer for 30 minutes and focus on completing one task at a time. When the timer goes off, take a break and repeat the process. This will help you stay focused and motivated, and will make the task of writing your thesis seem less overwhelming.101 tokens · 9.8 s
utter-project/EuroLLM-9BIdentical prompt, identical decoding settings, identical hardware — left is this model, right is the un-tuned original.
EuroLLM-9B-Alpaca
text
A GPU, or Graphic Processing Unit, is a type of computer processor that is designed to handle graphics and visual data. It is used to render images and videos, and is often used in gaming and other applications that require fast and efficient processing of visual data. It is like a super-fast artist that can draw and paint images and videos in a very short amount of time.utter-project/EuroLLM-9B
text
Imagine you're drawing a picture with lots of tiny details, like a big colorful landscape. Your brain is like a **CPU**, it's really good at thinking and making decisions, but it's not as fast at drawing lots of little things. A **GPU** is like a super-fast artist helper! It's really good at drawing lots of little things quickly. So, when you want to make a picture with lots of details, your brain tells the GPU to help out. The GPU draws all the little things really fast, and then your brain puts it all together to make the final picture. Think of it like this: your brain is the boss, and the GPU is the worker who does the hard work of drawing all the little details!reverse_linked_list() in PythonEuroLLM-9B-Alpaca
text
Here is a Python function that reverses a singly linked list: ```pythonclass Node: def __init__(self, data): self.data = data self.next = None def reverse_list(head): if head is None: return head prev = None curr = head while curr: next_node = curr.next curr.next = prev prev = curr curr = next_node head = prev return head``` This function takes a head node of the linked list as input and reverses the list. It uses a two-pointer approach to reverse the list. The first pointer, `prev`, is initially set to `None` and the second pointer, `curr`, is set to the head of the linked list. The function then iterates through the linked list, updating the pointers to reverse the list. Finally, the function returns the reversed head node.utter-project/EuroLLM-9B
text
```pythondef reverse_linked_list(head): """ Reverses a singly linked list. Args: head (LinkedListNode): The head of the linked list. Returns: LinkedListNode: The head of the reversed linked list. """ # TODO: Implement the function to reverse the linked list. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: Y…(truncated)EuroLLM-9B-Alpaca
text
The farmer has 17 sheep. 9 sheep ran away, so the farmer has 17 - 9 = 8 sheep left.utter-project/EuroLLM-9B
text
The farmer starts with 17 sheep. **Reasoning:** 1. **Identify the initial number:** The farmer has 17 sheep.2. **Identify the change:** 9 sheep run away.3. **Calculate the remaining:** Subtract the number of sheep that ran away from the initial number. **Answer:** 17 - 9 = 8 sheep are left.EuroLLM-9B-Alpaca
text
The Voyager 1 spacecraft, launched in 1977, is the farthest human-made object from Earth and continues to transmit data using power from its radioisotope thermoelectric generators.utter-project/EuroLLM-9B
text
Voyager 1, launched in 1977, is the farthest human-made object from Earth, having entered interstellar space in 2012 and continuing to transmit data using radioisotope power, with instrument shutdown expected in the 2030s.EuroLLM-9B-Alpaca
text
过拟合是指模型过度适应训练数据,导致在训练集上表现良好,但在新的数据上表现不佳。它发生在模型变得过于复杂,开始捕捉训练数据中的噪音和偶然性,而不是模式和关系。过拟合的模型在训练集上表现良好,但在新的数据上表现不佳。utter-project/EuroLLM-9B
text
**过拟合**，简单来说，就是模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。这会导致模型在训练数据上表现良好，但在新的、未见过的数据上表现不佳。 以下是用三句话解释过拟合的具体内容： 1. **过拟合**，模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。2. 过拟合的模型在训练数据上表现良好，但在新的、未见过的数据上表现不佳。3. 过拟合的模型会过度调整数据，导致在新的数据上表现不佳。 **解释：** * **过拟合**：模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。* **表现不佳**：过拟合的模型在新的、未见过的数据上表现不佳。* **过度调整数据**：过拟合的模型会过度调整数据，导致在新的数据上表现不佳。 **例子：** 想象一个模型就像一个试图学习EuroLLM-9B-Alpaca
text
One concrete tactic to help you stop procrastinating on your thesis is to break it down into smaller tasks. Start by breaking your thesis down into smaller tasks, such as researching, writing, and editing. Then, set a timer for 30 minutes and focus on completing one task at a time. When the timer goes off, take a break and repeat the process. This will help you stay focused and motivated, and will make the task of writing your thesis seem less overwhelming.utter-project/EuroLLM-9B
text
**Tactic:** Break your thesis into smaller, manageable tasks. **Explanation:** 1. **Identify the major sections of your thesis:** Outline the main chapters or parts of your thesis.2. **Set specific goals for each section:** Define what you want to accomplish in each section.3. **Create a timeline:** Assign deadlines for each section based on your goals.4. **Prioritize tasks:** Determine which sections are most important and tackle those first.5. **Minimize distractions:** Create a focused work environment by turning off notifications, finding a quiet space, and using tools to block distracting websites.6. **Take regular breaks:** Short breaks can help maintain focus and prevent burnout.7. **Reward yourself:** Set up small rewards for completing each section or reaching milestones.8. **Stay accountable:** Share your progress with a friend, mentor, or colleague who can pr…(truncated)| Item | Value |
|---|---|
| Trained with | TRL 0.23.0 · Transformers 4.57.1 · PyTorch 2.8.0 · Datasets 3.6.0 |
| Evaluated with | Transformers 5.16.1 · PyTorch 2.11.0+cu128 · 4bit-nf4 · Tesla T4 15.4 GiB |
| Evaluation date | 2026-10-04 |
| Evaluation prompts | 6 (4 instruction-style · 2 conversational) |
bibtex
@misc{EuroLLM9BAlpaca} title = {EuroLLM-9B-Alpaca}, note = {Fine-tuned from utter-project/EuroLLM-9B}, year = {2026}}from transformers import AutoModelForCausalLM, AutoTokenizer repo = "wesjos/EuroLLM-9B-Alpaca"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto") PROMPT = """Below is an instruction that describes a task. Write a response that \appropriately completes the request. ### Instruction:{instruction} ### Input:{input} ### Response:""" text = PROMPT.format(instruction="Explain what a GPU is to a 10-year-old child.", input="")ids = tok(text, return_tensors="pt").to(model.device)out = model.generate(**ids, max_new_tokens=256, do_sample=False)print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))from transformers import pipelinep = pipeline("text-generation", model="wesjos/EuroLLM-9B-Alpaca")print(p(PROMPT.format(instruction="Explain what a GPU is to a 10-year-old child.", input=""), max_new_tokens=256, return_full_text=False)[0]["generated_text"])Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:Explain what a GPU is to a 10-year-old child.### Input:### Response:A GPU, or Graphic Processing Unit, is a type of computer processor that is designed to handle graphics and visual data. It is used to render images and videos, and is often used in gaming and other applications that require fast and efficient processing of visual data. It is like a super-fast artist that can draw and paint images and videos in a very short amount of time.Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:Write a Python function that reverses a singly linked list. Include a docstring.### Input:### Response:Here is a Python function that reverses a singly linked list:```pythonclass Node: def __init__(self, data): self.data = data self.next = Nonedef reverse_list(head): if head is None: return head prev = None curr = head while curr: next_node = curr.next curr.next = prev prev = curr curr = next_node head = prev return head```This function takes a head node of the linked list as input and reverses the list. It uses a two-pointer approach to reverse the list. The first pointer, `prev`, is initially set to `None` and the second pointer, `curr`, is set to the head of the linked list. The function then iterates through the linked list, updating the pointers to reverse the list. Finally, the function returns the reversed head node.Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:A farmer has 17 sheep. All but 9 run away. How many are left? Explain your reasoning.### Input:### Response:Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:Summarize the following passage in one sentence.### Input:The Voyager 1 spacecraft, launched in 1977, has travelled farther from Earth than any other human-made object. It crossed into interstellar space in 2012 and continues to transmit data using power from its radioisotope thermoelectric generators, though mission engineers expect its instruments to be shut down sometime in the 2030s.### Response:Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:用三句话向一个刚学编程的大学生解释什么是「过拟合」。### Input:### Response:过拟合是指模型过度适应训练数据,导致在训练集上表现良好,但在新的数据上表现不佳。它发生在模型变得过于复杂,开始捕捉训练数据中的噪音和偶然性,而不是模式和关系。过拟合的模型在训练集上表现良好,但在新的数据上表现不佳。Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:I keep procrastinating on my thesis. Give me one concrete tactic, not generic advice.### Input:### Response:One concrete tactic to help you stop procrastinating on your thesis is to break it down into smaller tasks. Start by breaking your thesis down into smaller tasks, such as researching, writing, and editing. Then, set a timer for 30 minutes and focus on completing one task at a time. When the timer goes off, take a break and repeat the process. This will help you stay focused and motivated, and will make the task of writing your thesis seem less overwhelming.A GPU, or Graphic Processing Unit, is a type of computer processor that is designed to handle graphics and visual data. It is used to render images and videos, and is often used in gaming and other applications that require fast and efficient processing of visual data. It is like a super-fast artist that can draw and paint images and videos in a very short amount of time.Imagine you're drawing a picture with lots of tiny details, like a big colorful landscape. Your brain is like a **CPU**, it's really good at thinking and making decisions, but it's not as fast at drawing lots of little things.A **GPU** is like a super-fast artist helper! It's really good at drawing lots of little things quickly. So, when you want to make a picture with lots of details, your brain tells the GPU to help out. The GPU draws all the little things really fast, and then your brain puts it all together to make the final picture.Think of it like this: your brain is the boss, and the GPU is the worker who does the hard work of drawing all the little details!Here is a Python function that reverses a singly linked list:```pythonclass Node: def __init__(self, data): self.data = data self.next = Nonedef reverse_list(head): if head is None: return head prev = None curr = head while curr: next_node = curr.next curr.next = prev prev = curr curr = next_node head = prev return head```This function takes a head node of the linked list as input and reverses the list. It uses a two-pointer approach to reverse the list. The first pointer, `prev`, is initially set to `None` and the second pointer, `curr`, is set to the head of the linked list. The function then iterates through the linked list, updating the pointers to reverse the list. Finally, the function returns the reversed head node.```pythondef reverse_linked_list(head): """ Reverses a singly linked list. Args: head (LinkedListNode): The head of the linked list. Returns: LinkedListNode: The head of the reversed linked list. """ # TODO: Implement the function to reverse the linked list. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: You can use a stack to help you. # Hint: Y…(truncated)The farmer starts with 17 sheep. **Reasoning:**1. **Identify the initial number:** The farmer has 17 sheep.2. **Identify the change:** 9 sheep run away.3. **Calculate the remaining:** Subtract the number of sheep that ran away from the initial number.**Answer:** 17 - 9 = 8 sheep are left.过拟合是指模型过度适应训练数据,导致在训练集上表现良好,但在新的数据上表现不佳。它发生在模型变得过于复杂,开始捕捉训练数据中的噪音和偶然性,而不是模式和关系。过拟合的模型在训练集上表现良好,但在新的数据上表现不佳。**过拟合**，简单来说，就是模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。这会导致模型在训练数据上表现良好，但在新的、未见过的数据上表现不佳。以下是用三句话解释过拟合的具体内容：1. **过拟合**，模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。2. 过拟合的模型在训练数据上表现良好，但在新的、未见过的数据上表现不佳。3. 过拟合的模型会过度调整数据，导致在新的数据上表现不佳。**解释：*** **过拟合**：模型过于复杂，捕捉到了数据中的噪声，而不是数据中的真正模式。* **表现不佳**：过拟合的模型在新的、未见过的数据上表现不佳。* **过度调整数据**：过拟合的模型会过度调整数据，导致在新的数据上表现不佳。**例子：**想象一个模型就像一个试图学习One concrete tactic to help you stop procrastinating on your thesis is to break it down into smaller tasks. Start by breaking your thesis down into smaller tasks, such as researching, writing, and editing. Then, set a timer for 30 minutes and focus on completing one task at a time. When the timer goes off, take a break and repeat the process. This will help you stay focused and motivated, and will make the task of writing your thesis seem less overwhelming.**Tactic:** Break your thesis into smaller, manageable tasks. **Explanation:**1. **Identify the major sections of your thesis:** Outline the main chapters or parts of your thesis.2. **Set specific goals for each section:** Define what you want to accomplish in each section.3. **Create a timeline:** Assign deadlines for each section based on your goals.4. **Prioritize tasks:** Determine which sections are most important and tackle those first.5. **Minimize distractions:** Create a focused work environment by turning off notifications, finding a quiet space, and using tools to block distracting websites.6. **Take regular breaks:** Short breaks can help maintain focus and prevent burnout.7. **Reward yourself:** Set up small rewards for completing each section or reaching milestones.8. **Stay accountable:** Share your progress with a friend, mentor, or colleague who can pr…(truncated)@misc{EuroLLM9BAlpaca} title = {EuroLLM-9B-Alpaca}, note = {Fine-tuned from utter-project/EuroLLM-9B}, year = {2026}}