Super-squash branch 'main' using huggingface_hub

.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 +1,129 @@
+---
+library_name: transformers
+license: apache-2.0
+language:
+- en
+---
+
+
+# SmolLM2
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/XlT5TM3HWpfoZk_HSubrH.png)
+
+##  Table of Contents
+
+1. [Model Summary](#model-summary)
+2. [Evaluation](#evaluation)
+3. [Limitations](#limitations)
+4. [Training](#training)
+5. [License](#license)
+6. [Citation](#citation)
+
+## 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.
+
+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).
+
+### How to use
+
+```bash
+pip install transformers
+```
+
+#### Running the model on CPU/GPU/multi GPU
+* _Using full precision_
+```python
+# pip install transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+checkpoint = "HuggingFaceTB/SmolLM2-1.7B"
+device = "cuda" # for GPU usage or "cpu" for CPU usage
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))
+```
+
+* _Using `torch.bfloat16`_
+```python
+# pip install accelerate
+# for fp16 use `torch_dtype=torch.float16` instead
+model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)
+inputs = tokenizer.encode("Gravity is", return_tensors="pt").to("cuda")
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))
+```
+```bash
+>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
+Memory footprint: 3422.76 MB
+```
+
+## 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.
+
+## Base Pre-Trained Model
+
+| Metric           | SmolLM2-1.7B | Llama-1B    | Qwen2.5-1.5B | SmolLM1-1.7B |
+|------------------|--------------|-------------|---------------|--------------|
+| HellaSwag        | **68.7**     | 61.2        | 66.4          | 62.9         |
+| ARC (Average)    | **60.5**     | 49.2        | 58.5          | 59.9         |
+| PIQA             | **77.6**     | 74.8        | 76.1          | 76.0         |
+| MMLU-Pro (MCF)   | **19.4**     | 11.7        | 13.7          | 10.8         |
+| CommonsenseQA    | **43.6**     | 41.2        | 34.1          | 38.0         |
+| TriviaQA         | **36.7**     | 28.1        | 20.9          | 22.5         |
+| Winogrande       | **59.4**     | 57.8        | 59.3          | 54.7         |
+| OpenBookQA       | 42.2         | 38.4        | 40.0          | **42.4**     |
+| GSM8K (5-shot)   | 31.0         | 7.2         | **61.3**      | 5.5          |
+
+## Instruction Model
+
+| Metric                       | SmolLM2-1.7B-Instruct | Llama-1B-Instruct | Qwen2.5-1.5B-Instruct | SmolLM1-1.7B-Instruct |
+|:-----------------------------|:---------------------:|:-----------------:|:----------------------:|:----------------------:|
+| IFEval (Average prompt/inst) | **56.7**             | 53.5             | 47.4                  | 23.1                  |
+| MT-Bench                     | 6.13                | 5.48             | **6.52**              | 4.33                  |
+| OpenRewrite-Eval (micro_avg RougeL) | 44.9           | 39.2             | **46.9**              | NaN                   |
+| HellaSwag                    | **66.1**            | 56.1             | 60.9                  | 55.5                  |
+| ARC (Average)                | **51.7**            | 41.6             | 46.2                  | 43.7                  |
+| PIQA                         | **74.4**            | 72.3             | 73.2                  | 71.6                  |
+| MMLU-Pro (MCF)               | 19.3               | 12.7             | **24.2**              | 11.7                  |
+| BBH (3-shot)                 | 32.2               | 27.6             | **35.3**              | 25.7                  |
+| GSM8K (5-shot)               | **48.2**           | 26.8             | 42.8                  | 4.62                  |
+
+
+## Limitations
+
+SmolLM2 models primarily understand and generate content in English. They can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
+
+## Training
+
+### Model
+
+- **Architecture:** Transformer decoder
+- **Pretraining tokens:** 11T
+- **Precision:** bfloat16
+
+### Hardware
+
+- **GPUs:** 256 H100
+
+### Software
+
+- **Training Framework:** [nanotron](https://github.com/huggingface/nanotron/tree/main)
+
+## License
+
+[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+## 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},
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/fsx/elie_bakouch/nanotron-ckpt/360M-50B-8k-130k-rope-end/hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dc0494fa27c368c41b021666c868570469993386a093bca18aff3c1e13b065
+size 307852839

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1193528982f4ac0c0b707ce36fd7dc03a0ef6f3e1a432deb886dce2e90c300c0
+size 3422777952

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8c0174fa3ee6fe2ffd0f6e21992d4ca4ad1e9b12bd14155b57479e27f56292
+size 307905733

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c951cf31decd4a719df82f84d0ad38fca5173b09393b22b864ab8a55ba03d7c
+size 439831352