Upload folder using huggingface_hub

README.md

@@ -3,6 +3,13 @@ library_name: transformers
 license: apache-2.0
 language:
 - en
+pipeline_tag: text-generation
+tags:
+- safetensors
+- onnx
+- transformers.js
+base_model:
+- HuggingFaceTB/SmolLM2-1.7B
 ---
 
 
@@ -22,15 +29,18 @@ language:
 
 ## Model Summary
 
-SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.
+SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. More details in our paper: https://arxiv.org/abs/2502.02737v1
 
 The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using [UltraFeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).
 
 The instruct model additionally supports tasks such as text rewriting, summarization and function calling thanks to datasets developed by [Argilla](https://huggingface.co/argilla) such as [Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1).
+You can find the SFT dataset here: https://huggingface.co/datasets/HuggingFaceTB/smoltalk.
+
+For more details refer to: https://github.com/huggingface/smollm. You will find pre-training, post-training, evaluation and local inference code.
 
 ### How to use
 
-### Transformers
+#### Transformers
 ```bash
 pip install transformers
 ```
@@ -52,13 +62,40 @@ print(tokenizer.decode(outputs[0]))
 ```
 
 
-### Chat in TRL
+#### Chat in TRL
 You can also use the TRL CLI to chat with the model from the terminal:
 ```bash
 pip install trl
 trl chat --model_name_or_path HuggingFaceTB/SmolLM2-1.7B-Instruct --device cpu
 ```
 
+#### Transformers.js
+
+```bash
+npm i @huggingface/transformers
+```
+
+```js
+import { pipeline } from "@huggingface/transformers";
+
+// Create a text generation pipeline
+const generator = await pipeline(
+  "text-generation",
+  "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+);
+
+// Define the list of messages
+const messages = [
+  { role: "system", content: "You are a helpful assistant." },
+  { role: "user", content: "Tell me a joke." },
+];
+
+// Generate a response
+const output = await generator(messages, { max_new_tokens: 128 });
+console.log(output[0].generated_text.at(-1).content);
+// "Why don't scientists trust atoms?\n\nBecause they make up everything!"
+```
+
 ## Evaluation
 
 In this section, we report the evaluation results of SmolLM2. All evaluations are zero-shot unless stated otherwise, and we use [lighteval](https://github.com/huggingface/lighteval) to run them.
@@ -100,7 +137,7 @@ Below are some system and instruct prompts that work well for special tasks
 ```python
 system_prompt_rewrite = "You are an AI writing assistant. Your task is to rewrite the user's email to make it more professional and approachable while maintaining its main points and key message. Do not return any text other than the rewritten message."
 user_prompt_rewrite = "Rewrite the message below to make it more friendly and approachable while maintaining its main points and key message. Do not add any new information or return any text other than the rewritten message\nThe message:"
-messages = [{"role": "system", "content": system_prompt_rewrite}, {"role": "user", "content":f"{user_prompt_rewrite} The CI is failing after your last commit!}"]
+messages = [{"role": "system", "content": system_prompt_rewrite}, {"role": "user", "content":f"{user_prompt_rewrite} The CI is failing after your last commit!"}]
 input_text=tokenizer.apply_chat_template(messages, tokenize=False)
 inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
@@ -114,7 +151,7 @@ Hey there! I noticed that the CI isn't passing after your latest commit. Could y
 
 ```python
 system_prompt_summarize = "Provide a concise, objective summary of the input text in up to three sentences, focusing on key actions and intentions without using second or third person pronouns."
-messages = [{"role": "system", "content": system_prompt_rewrite}, {"role": "user", "content": INSERT_LONG_EMAIL]
+messages = [{"role": "system", "content": system_prompt_summarize}, {"role": "user", "content": INSERT_LONG_EMAIL}]
 input_text=tokenizer.apply_chat_template(messages, tokenize=False)
 inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
@@ -192,7 +229,73 @@ def parse_response(text: str) -> str | dict[str, any]:
     if matches:
         return json.loads(matches[0])
     return text
+
+
+model_name_smollm = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(model_name_smollm, device_map="auto", torch_dtype="auto", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name_smollm)
+
+from datetime import datetime
+import random
+
+def get_current_time() -> str:
+    """Returns the current time in 24-hour format.
+
+    Returns:
+        str: Current time in HH:MM:SS format.
+    """
+    return datetime.now().strftime("%H:%M:%S")
+
+
+def get_random_number_between(min: int, max: int) -> int:
+    """
+    Gets a random number between min and max.
+
+    Args:
+        min: The minimum number.
+        max: The maximum number.
+
+    Returns:
+        A random number between min and max.
+    """
+    return random.randint(min, max)
+
+
+tools = [get_json_schema(get_random_number_between), get_json_schema(get_current_time)]
+
+toolbox = {"get_random_number_between": get_random_number_between, "get_current_time": get_current_time}
+
+query = "Give me a number between 1 and 300"
+
+messages = prepare_messages(query, tools=tools)
+
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+
+tool_calls = parse_response(result)
+# [{'name': 'get_random_number_between', 'arguments': {'min': 1, 'max': 300}}
+
+# Get tool responses
+tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
+# [63]
+
+# For the second turn, rebuild the history of messages:
+history = messages.copy()
+# Add the "parsed response"
+history.append({"role": "assistant", "content": result})
+query = "Can you give me the hour?"
+history.append({"role": "user", "content": query})
+
+inputs = tokenizer.apply_chat_template(history, add_generation_prompt=True, return_tensors="pt").to(model.device)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+
+tool_calls = parse_response(result)
+tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
+# ['07:57:25']
 ```
+More details such as parallel function calls and tools not available can be found [here](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct/blob/main/instructions_function_calling.md)
 
 ## Limitations
 
@@ -213,7 +316,7 @@ SmolLM2 models primarily understand and generate content in English. They can pr
 ### Software
 
 - **Training Framework:** [nanotron](https://github.com/huggingface/nanotron/tree/main)
-- **Alignement Handbook** [alignement-handbook](https://github.com/huggingface/alignment-handbook/)
+- **Alignment Handbook** [alignment-handbook](https://github.com/huggingface/alignment-handbook/)
 
 ## License
 
@@ -221,9 +324,13 @@ SmolLM2 models primarily understand and generate content in English. They can pr
 
 ## Citation
 ```bash
-@misc{allal2024SmolLM2,
-      title={SmolLM2 - with great data, comes great performance}, 
-      author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Gabriel Martín Blázquez and Lewis Tunstall and Agustín Piqueres and Andres Marafioti and Cyril Zakka and Leandro von Werra and Thomas Wolf},
-      year={2024},
+@misc{allal2025smollm2smolgoesbig,
+      title={SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model}, 
+      author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Gabriel Martín Blázquez and Guilherme Penedo and Lewis Tunstall and Andrés Marafioti and Hynek Kydlíček and Agustín Piqueres Lajarín and Vaibhav Srivastav and Joshua Lochner and Caleb Fahlgren and Xuan-Son Nguyen and Clémentine Fourrier and Ben Burtenshaw and Hugo Larcher and Haojun Zhao and Cyril Zakka and Mathieu Morlon and Colin Raffel and Leandro von Werra and Thomas Wolf},
+      year={2025},
+      eprint={2502.02737},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2502.02737}, 
 }
 ```

tokenizer_config.json

@@ -146,7 +146,7 @@
   "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
-  "model_max_length": 2048,
+  "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",