init commit

.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 +1,12 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM-360M-Instruct
+tags:
+- rope
+library_name: transformers
+language:
+- en
+---
+
+
+8192 ctx length version of [SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct)

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM-360M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 41829.36592889948,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "max_new_tokens": 40,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f841de9bf656ea5af3c8d89e5647ee0f39121b28adf4202d1eec02f69619c5e
+size 723674912

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_prompts.py

@@ -0,0 +1,106 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+BASE_PATH = "/fsx/loubna/projects/alignment-handbook/recipes/cosmo2/sft/data"
+TEMPERATURE = 0.2
+TOP_P = 0.9
+
+CHECKPOINT = "loubnabnl/smollm-350M-instruct-add-basics"
+
+print(f"💾 Loading the model and tokenizer: {CHECKPOINT}...")
+device = "cuda"
+tokenizer = AutoTokenizer.from_pretrained(CHECKPOINT)
+model_s = AutoModelForCausalLM.from_pretrained(CHECKPOINT).to(device)
+
+print("🧪 Testing single-turn conversations...")
+L = [
+    "Hi",
+    "Hello",
+    "Tell me a joke",
+    "Who are you?",
+    "What's your name?",
+    "How do I make pancakes?",
+    "Can you tell me what is gravity?",
+    "What is the capital of Morocco?",
+    "What's 2+2?",
+    "Hi, what is 2+1?",
+    "What's 3+5?",
+    "Write a poem about Helium",
+    "Hi, what are some popular dishes from Japan?",
+]
+
+
+for i in range(len(L)):
+    print(f"🔮 {L[i]}")
+    messages = [{"role": "user", "content": L[i]}]
+    input_text = tokenizer.apply_chat_template(messages, tokenize=False)
+    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+    outputs = model_s.generate(
+        inputs, max_new_tokens=200, top_p=TOP_P, do_sample=True, temperature=TEMPERATURE
+    )
+    with open(
+        f"{BASE_PATH}/{CHECKPOINT.split('/')[-1]}_temp_{TEMPERATURE}_topp{TOP_P}.txt",
+        "a",
+    ) as f:
+        f.write("=" * 50 + "\n")
+        f.write(tokenizer.decode(outputs[0]))
+        f.write("\n")
+
+
+print("🧪 Now testing multi-turn conversations...")
+# Multi-turn conversations
+messages_1 = [
+    {"role": "user", "content": "Hi"},
+    {"role": "assistant", "content": "Hello! How can I help you today?"},
+    {"role": "user", "content": "What's 2+2?"},
+]
+messages_2 = [
+    {"role": "user", "content": "Hi"},
+    {"role": "assistant", "content": "Hello! How can I help you today?"},
+    {"role": "user", "content": "What's 2+2?"},
+    {"role": "assistant", "content": "4"},
+    {"role": "user", "content": "Why?"},
+]
+messages_3 = [
+    {"role": "user", "content": "Who are you?"},
+    {"role": "assistant", "content": "I am an AI assistant. How can I help you today?"},
+    {"role": "user", "content": "What's your name?"},
+]
+messages_4 = [
+    {"role": "user", "content": "Tell me a joke"},
+    {"role": "assistant", "content": "Sure! Why did the tomato turn red?"},
+    {"role": "user", "content": "Why?"},
+]
+messages_5 = [
+    {"role": "user", "content": "Can you tell me what is gravity?"},
+    {
+        "role": "assistant",
+        "content": "Sure! Gravity is a force that attracts objects toward each other. It is what keeps us on the ground and what makes things fall.",
+    },
+    {"role": "user", "content": "Who discovered it?"},
+]
+messages_6 = [
+    {"role": "user", "content": "How do I make pancakes?"},
+    {
+        "role": "assistant",
+        "content": "Sure! Here is a simple recipe for pancakes: Ingredients: 1 cup flour, 1 cup milk, 1 egg, 1 tbsp sugar, 1 tsp baking powder, 1/2 tsp salt. Instructions: 1. Mix all the dry ingredients together in a bowl. 2. Add the milk and egg and mix until smooth. 3. Heat a non-stick pan over medium heat. 4. Pour 1/4 cup of batter onto the pan. 5. Cook until bubbles form on the surface, then flip and cook for another minute. 6. Serve with your favorite toppings.",
+    },
+    {"role": "user", "content": "What are some popular toppings?"},
+]
+
+L = [messages_1, messages_2, messages_3, messages_4, messages_5, messages_6]
+
+for i in range(len(L)):
+    input_text = tokenizer.apply_chat_template(L[i], tokenize=False)
+    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+    outputs = model_s.generate(
+        inputs, max_new_tokens=200, top_p=TOP_P, do_sample=True, temperature=TEMPERATURE
+    )
+    with open(
+        f"{BASE_PATH}/{CHECKPOINT.split('/')[-1]}_temp_{TEMPERATURE}_topp{TOP_P}_MT.txt",
+        "a",
+    ) as f:
+        f.write("=" * 50 + "\n")
+        f.write(tokenizer.decode(outputs[0]))
+        f.write("\n")
+
+print("🔥 Done!")

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% 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": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}