Added application file

demo.py

@@ -0,0 +1,161 @@
+import gradio as gr
+import torch
+import transformers
+
+model: transformers.AlbertForQuestionAnswering = (
+    transformers.AlbertForQuestionAnswering.from_pretrained("./model")
+)
+tokenizer: transformers.AlbertTokenizer = (
+    transformers.AlbertTokenizerFast.from_pretrained("./model")
+)
+
+n_best_size = 20
+max_answer_length = 30
+null_score_diff_threshold = 0.0
+max_length = 384
+stride = 128
+
+article = """Check out the project repository at [GitHub]().
+
+Training logs can be found at [ClearML](https://app.clear.ml/projects/cd2f4008afa34a68bd085588fe8f44e1/experiments/a971b54e499a4dbe8b90faf9b6969608/output/execution) (you must be registered to access the log).
+"""
+
+example_context = 'The Normans (Norman: Nourmands; French: Normands; Latin: Normanni) were the people who in the 10th and 11th centuries gave their name to Normandy, a region in France. They were descended from Norse ("Norman" comes from "Norseman") raiders and pirates from Denmark, Iceland and Norway who, under their leader Rollo, agreed to swear fealty to King Charles III of West Francia. Through generations of assimilation and mixing with the native Frankish and Roman-Gaulish populations, their descendants would gradually merge with the Carolingian-based cultures of West Francia. The distinct cultural and ethnic identity of the Normans emerged initially in the first half of the 10th century, and it continued to evolve over the succeeding centuries.'
+example_question = "In what country is Normandy located?"
+
+
+def predict(context: str, question: str) -> str:
+    model_inputs = tokenizer(
+        question,
+        context,
+        max_length=max_length,
+        truncation="only_second",
+        stride=stride,
+        return_overflowing_tokens=True,
+        return_offsets_mapping=True,
+        padding="max_length",
+        return_tensors="pt",
+    )
+    offset_mapping = model_inputs.pop("offset_mapping")
+    model_inputs.pop("overflow_to_sample_mapping")
+    output = model(**model_inputs)
+    prelim_predictions = []
+    min_null_prediction = None
+    null_score = 0.0
+
+    for i, offest in enumerate(offset_mapping):
+        start_logits = output.start_logits[i]
+        end_logits = output.end_logits[i]
+
+        # Update minimum null prediction.
+        feature_null_score = start_logits[0] + end_logits[0]
+        min_null_prediction = {
+            "offsets": (0, 0),
+            "score": feature_null_score,
+            "start_logit": start_logits[0],
+            "end_logit": end_logits[0],
+        }
+
+        # Go through all possibilities for the `n_best_size` greater start and end logits.
+        start_indexes = torch.argsort(start_logits, descending=True)[
+            :n_best_size
+        ].tolist()
+        end_indexes = torch.argsort(end_logits, descending=True)[:n_best_size].tolist()
+        for start_index in start_indexes:
+            for end_index in end_indexes:
+                # Don't consider out-of-scope answers, either because the indices are out of bounds or correspond
+                # to part of the input_ids that are not in the context.
+                if (
+                    start_index >= len(offest)
+                    or end_index >= len(offest)
+                    or offest[start_index] is None
+                    or len(offest[start_index]) < 2
+                    or offest[end_index] is None
+                    or len(offest[end_index]) < 2
+                ):
+                    continue
+                # Don't consider answers with a length that is either < 0 or > max_answer_length.
+                if (
+                    end_index < start_index
+                    or end_index - start_index + 1 > max_answer_length
+                ):
+                    continue
+
+                prelim_predictions.append(
+                    {
+                        "offsets": (
+                            offest[start_index][0],
+                            offest[end_index][1],
+                        ),
+                        "score": start_logits[start_index] + end_logits[end_index],
+                        "start_logit": start_logits[start_index],
+                        "end_logit": end_logits[end_index],
+                    }
+                )
+    if min_null_prediction is not None:
+        prelim_predictions.append(min_null_prediction)
+        null_score = min_null_prediction["score"]
+
+    # Only keep the best `n_best_size` predictions.
+    predictions = sorted(prelim_predictions, key=lambda x: x["score"], reverse=True)[
+        :n_best_size
+    ]
+
+    if min_null_prediction is not None and not any(
+        p["offsets"] == (0, 0) for p in predictions
+    ):
+        predictions.append(min_null_prediction)
+
+    # Use the offsets to gather the answer text in the original context.
+    for pred in predictions:
+        offsets = pred.pop("offsets")
+        pred["text"] = context[offsets[0] : offsets[1]]
+
+    # In the very rare edge case we have not a single non-null prediction, we create a fake prediction to avoid
+    # failure.
+    if len(predictions) == 0 or (
+        len(predictions) == 1 and predictions[0]["text"] == ""
+    ):
+        predictions.insert(
+            0, {"text": "empty", "start_logit": 0.0, "end_logit": 0.0, "score": 0.0}
+        )
+
+    probs = torch.nn.functional.softmax(
+        torch.tensor([pred.pop("score") for pred in predictions]), dim=0
+    )
+
+    # Include the probabilities in our predictions.
+    for prob, pred in zip(probs, predictions):
+        pred["probability"] = prob
+
+    # Pick the best prediction.
+    i = 0
+    while predictions[i]["text"] == "":
+        i += 1
+    best_non_null_pred = predictions[i]
+
+    # Then we compare to the null prediction using the threshold.
+    score_diff = (
+        null_score - best_non_null_pred["start_logit"] - best_non_null_pred["end_logit"]
+    )
+    return (
+        "The context doesn't contain answer to this question."
+        if score_diff > null_score_diff_threshold
+        else best_non_null_pred["text"]
+    )
+
+
+if __name__ == "__main__":
+    demo = gr.Interface(
+        fn=predict,
+        inputs=[
+            gr.TextArea(label="Context", value=example_context),
+            gr.Textbox(label="Question", value=example_question),
+        ],
+        outputs=gr.Textbox(label="Answer"),
+        title="EureQA: Extractive Question Answering model",
+        description="""EureQA is an extractive question answering model based on the [ALBERT Base v2](https://huggingface.co/albert/albert-base-v2) 
+architecture and finetuned on [SQuAD 2.0](https://huggingface.co/datasets/rajpurkar/squad_v2) dataset.""",
+        article=article,
+    )
+    demo.launch(share=True)

model/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "albert/albert-base-v2",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fbd6be3b4f27957bdf0a28537443b3d8dd66b382f454e4ac77ec8657e34c1d
+size 44381360

model/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

model/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

model/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

model/trainer_state.json

@@ -0,0 +1,332 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 21994,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_HasAns_exact": 0.06747638326585695,
+      "eval_HasAns_f1": 7.18502154989456,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 0.0336417157275021,
+      "eval_NoAns_f1": 0.0336417157275021,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 50.07159100480081,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 50.075846569172874,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 0.050534826918217805,
+      "eval_f1": 3.6042118881306284,
+      "eval_runtime": -14.2699,
+      "eval_samples_per_second": -852.912,
+      "eval_steps_per_second": -13.385,
+      "eval_total": 11873,
+      "step": 0
+    },
+    {
+      "epoch": 0.18186778212239701,
+      "grad_norm": 40.6475715637207,
+      "learning_rate": 2.7271983268164044e-05,
+      "loss": 1.4132,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18186778212239701,
+      "eval_HasAns_exact": 67.25708502024291,
+      "eval_HasAns_f1": 74.98296116605809,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 70.81581160639193,
+      "eval_NoAns_f1": 70.81581160639193,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 69.03899604143855,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 72.89640308198375,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 69.03899604143855,
+      "eval_f1": 72.89640308198369,
+      "eval_runtime": 136.0827,
+      "eval_samples_per_second": 89.438,
+      "eval_steps_per_second": 1.404,
+      "eval_total": 11873,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36373556424479403,
+      "grad_norm": 41.061927795410156,
+      "learning_rate": 2.4543966536328087e-05,
+      "loss": 1.2638,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36373556424479403,
+      "eval_HasAns_exact": 73.59986504723346,
+      "eval_HasAns_f1": 81.00757791997825,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 65.78637510513036,
+      "eval_NoAns_f1": 65.78637510513036,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 69.68752632022235,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 73.38607950051664,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 69.68752632022235,
+      "eval_f1": 73.38607950051639,
+      "eval_runtime": 136.2286,
+      "eval_samples_per_second": 89.342,
+      "eval_steps_per_second": 1.402,
+      "eval_total": 11873,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5456033463671911,
+      "grad_norm": 52.56464767456055,
+      "learning_rate": 2.1815949804492137e-05,
+      "loss": 1.3977,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5456033463671911,
+      "eval_HasAns_exact": 71.94669365721997,
+      "eval_HasAns_f1": 79.2064004599959,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 72.17830109335576,
+      "eval_NoAns_f1": 72.17830109335576,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 72.07108565653162,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 75.69574176087386,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 72.0626631853786,
+      "eval_f1": 75.68731928972085,
+      "eval_runtime": 136.1854,
+      "eval_samples_per_second": 89.371,
+      "eval_steps_per_second": 1.403,
+      "eval_total": 11873,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7274711284895881,
+      "grad_norm": 49.72623825073242,
+      "learning_rate": 1.908793307265618e-05,
+      "loss": 1.3384,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7274711284895881,
+      "eval_HasAns_exact": 72.0310391363023,
+      "eval_HasAns_f1": 78.95689148837117,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 75.00420521446594,
+      "eval_NoAns_f1": 75.00420521446594,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 73.51975069485387,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 76.9777185835984,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 73.51975069485387,
+      "eval_f1": 76.97771858359845,
+      "eval_runtime": 135.7796,
+      "eval_samples_per_second": 89.638,
+      "eval_steps_per_second": 1.407,
+      "eval_total": 11873,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9093389106119851,
+      "grad_norm": 39.458927154541016,
+      "learning_rate": 1.6359916340820223e-05,
+      "loss": 1.2258,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9093389106119851,
+      "eval_HasAns_exact": 73.54925775978407,
+      "eval_HasAns_f1": 80.29283351227244,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 76.23212783851976,
+      "eval_NoAns_f1": 76.23212783851976,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 74.88419102164575,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 78.25115110424915,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 74.89261349279879,
+      "eval_f1": 78.25957357540227,
+      "eval_runtime": 136.1576,
+      "eval_samples_per_second": 89.389,
+      "eval_steps_per_second": 1.403,
+      "eval_total": 11873,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0912066927343822,
+      "grad_norm": 41.23106002807617,
+      "learning_rate": 1.363189960898427e-05,
+      "loss": 0.7822,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0912066927343822,
+      "eval_HasAns_exact": 77.26045883940621,
+      "eval_HasAns_f1": 84.1124672080756,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 69.97476871320437,
+      "eval_NoAns_f1": 69.97476871320437,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 73.6208203486903,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 77.04191911138483,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 73.61239787753728,
+      "eval_f1": 77.0334966402318,
+      "eval_runtime": 135.9367,
+      "eval_samples_per_second": 89.534,
+      "eval_steps_per_second": 1.405,
+      "eval_total": 11873,
+      "step": 12000
+    },
+    {
+      "epoch": 1.273074474856779,
+      "grad_norm": 21.682905197143555,
+      "learning_rate": 1.0903882877148312e-05,
+      "loss": 0.6771,
+      "step": 14000
+    },
+    {
+      "epoch": 1.273074474856779,
+      "eval_HasAns_exact": 73.78542510121457,
+      "eval_HasAns_f1": 80.35769680092089,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 80.7569386038688,
+      "eval_NoAns_f1": 80.7569386038688,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 77.27617282910806,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 80.55760352361308,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 77.27617282910806,
+      "eval_f1": 80.55760352361317,
+      "eval_runtime": 136.5688,
+      "eval_samples_per_second": 89.12,
+      "eval_steps_per_second": 1.399,
+      "eval_total": 11873,
+      "step": 14000
+    },
+    {
+      "epoch": 1.4549422569791761,
+      "grad_norm": 56.2855339050293,
+      "learning_rate": 8.175866145312359e-06,
+      "loss": 0.6521,
+      "step": 16000
+    },
+    {
+      "epoch": 1.4549422569791761,
+      "eval_HasAns_exact": 71.82860998650472,
+      "eval_HasAns_f1": 77.91336965584932,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 85.18082422203533,
+      "eval_NoAns_f1": 85.18082422203533,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 78.52269855975743,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 81.56072225384261,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 78.51427608860439,
+      "eval_f1": 81.55229978268969,
+      "eval_runtime": 136.3366,
+      "eval_samples_per_second": 89.272,
+      "eval_steps_per_second": 1.401,
+      "eval_total": 11873,
+      "step": 16000
+    },
+    {
+      "epoch": 1.6368100391015732,
+      "grad_norm": 24.467727661132812,
+      "learning_rate": 5.447849413476403e-06,
+      "loss": 0.6455,
+      "step": 18000
+    },
+    {
+      "epoch": 1.6368100391015732,
+      "eval_HasAns_exact": 75.57354925775978,
+      "eval_HasAns_f1": 82.12994203860852,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 79.0412111017662,
+      "eval_NoAns_f1": 79.0412111017662,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 77.31828518487325,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 80.59178778782702,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 77.30986271372021,
+      "eval_f1": 80.58336531667406,
+      "eval_runtime": 136.1893,
+      "eval_samples_per_second": 89.368,
+      "eval_steps_per_second": 1.402,
+      "eval_total": 11873,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8186778212239703,
+      "grad_norm": 36.233985900878906,
+      "learning_rate": 2.7198326816404476e-06,
+      "loss": 0.6175,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8186778212239703,
+      "eval_HasAns_exact": 74.19028340080972,
+      "eval_HasAns_f1": 80.57880057678263,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 83.46509671993272,
+      "eval_NoAns_f1": 83.46509671993272,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 78.83432999241978,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 82.02401497676792,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 78.83432999241978,
+      "eval_f1": 82.02401497676809,
+      "eval_runtime": 136.3043,
+      "eval_samples_per_second": 89.293,
+      "eval_steps_per_second": 1.401,
+      "eval_total": 11873,
+      "step": 20000
+    },
+    {
+      "epoch": 2.0,
+      "step": 21994,
+      "total_flos": 4371201741330432.0,
+      "train_loss": 0.9652459149015072,
+      "train_runtime": 5408.776,
+      "train_samples_per_second": 48.794,
+      "train_steps_per_second": 4.066
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 21994,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4371201741330432.0,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2c525ecfe7ce4b8f382b372daf75d3a2dc88321c507d37cee5f6b480f3c276
+size 5176

requirements.txt

@@ -0,0 +1,152 @@
+accelerate==0.34.2
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.6
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.0
+asttokens==2.4.1
+attrs==24.2.0
+beautifulsoup4==4.12.3
+bleach==6.1.0
+Brotli==1.1.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.3.2
+clearml==1.16.4
+click==8.1.7
+colorama==0.4.6
+comm==0.2.2
+contourpy==1.3.0
+cycler==0.12.1
+datasets==3.0.0
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.8
+dnspython==2.6.1
+email_validator==2.2.0
+entrypoints==0.4
+evaluate==0.4.3
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.0
+fastapi-cli==0.0.5
+fastjsonschema==2.20.0
+ffmpy==0.3.0
+filelock==3.16.1
+fonttools==4.54.1
+frozenlist==1.4.1
+fsspec==2024.6.1
+furl==2.1.3
+gmpy2==2.1.5
+gradio==4.44.0
+gradio_client==1.3.0
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==1.0.5
+httpx==0.27.2
+huggingface_hub==0.25.1
+hyperframe==6.0.1
+idna==3.10
+importlib_metadata==8.5.0
+importlib_resources==6.4.5
+ipython==8.27.0
+ipywidgets==8.1.5
+jedi==0.19.1
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyterlab_pygments==0.3.0
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.0.2
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+munkres==1.1.4
+nbclient==0.10.0
+nbconvert==7.16.4
+nbformat==5.10.4
+networkx==3.3
+numpy==1.26.4
+orderedmultidict==1.0.1
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pandocfilters==1.5.0
+parso==0.8.4
+pathlib2==2.3.7.post1
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==10.4.0
+pip==24.2
+pkgutil_resolve_name==1.3.10
+platformdirs==4.3.6
+prompt_toolkit==3.0.48
+psutil==6.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+PyJWT==2.8.0
+pyparsing==3.1.4
+PySocks==1.7.1
+python-dateutil==2.9.0
+python-multipart==0.0.10
+pytz==2024.1
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+ruff==0.6.7
+safetensors==0.4.5
+semantic-version==2.10.0
+setuptools==75.1.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.5
+stack-data==0.6.2
+starlette==0.38.6
+sympy==1.13.2
+tinycss2==1.3.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+torch==2.4.1
+torchaudio==2.4.1
+torchvision==0.19.1
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.44.2
+triton==3.0.0
+typer==0.12.5
+typer-slim==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.30.6
+wcwidth==0.2.13
+webencodings==0.5.1
+websockets==12.0
+wheel==0.44.0
+widgetsnbextension==4.0.13
+xxhash==3.5.0
+yarl==1.12.1
+zipp==3.20.2
+zstandard==0.23.0