Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,290 @@
+{
+  "architectures": [
+    "UltravoxModel"
+  ],
+  "audio_config": {
+    "_name_or_path": "openai/whisper-small",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "apply_spec_augment": false,
+    "architectures": [
+      "WhisperForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "bos_token_id": 50257,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 50258,
+    "dropout": 0.0,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "eos_token_id": 50257,
+    "forced_decoder_ids": [
+      [
+        1,
+        50259
+      ],
+      [
+        2,
+        50359
+      ],
+      [
+        3,
+        50363
+      ]
+    ],
+    "init_std": 0.02,
+    "is_encoder_decoder": true,
+    "max_length": 448,
+    "max_source_positions": 1500,
+    "max_target_positions": 448,
+    "median_filter_width": 7,
+    "model_type": "whisper",
+    "num_hidden_layers": 12,
+    "num_mel_bins": 80,
+    "pad_token_id": 50257,
+    "scale_embedding": false,
+    "suppress_tokens": [
+      1,
+      2,
+      7,
+      8,
+      9,
+      10,
+      14,
+      25,
+      26,
+      27,
+      28,
+      29,
+      31,
+      58,
+      59,
+      60,
+      61,
+      62,
+      63,
+      90,
+      91,
+      92,
+      93,
+      359,
+      503,
+      522,
+      542,
+      873,
+      893,
+      902,
+      918,
+      922,
+      931,
+      1350,
+      1853,
+      1982,
+      2460,
+      2627,
+      3246,
+      3253,
+      3268,
+      3536,
+      3846,
+      3961,
+      4183,
+      4667,
+      6585,
+      6647,
+      7273,
+      9061,
+      9383,
+      10428,
+      10929,
+      11938,
+      12033,
+      12331,
+      12562,
+      13793,
+      14157,
+      14635,
+      15265,
+      15618,
+      16553,
+      16604,
+      18362,
+      18956,
+      20075,
+      21675,
+      22520,
+      26130,
+      26161,
+      26435,
+      28279,
+      29464,
+      31650,
+      32302,
+      32470,
+      36865,
+      42863,
+      47425,
+      49870,
+      50254,
+      50258,
+      50360,
+      50361,
+      50362
+    ],
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 51865
+  },
+  "audio_model_id": "openai/whisper-small",
+  "audio_token_index": 32000,
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "initializer_range": 0.02,
+  "model_type": "ultravox",
+  "norm_init": 0.4,
+  "projector_act": "swiglu",
+  "stack_factor": 8,
+  "text_config": {
+    "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
+    "architectures": [
+      "Phi3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "auto_map": {
+      "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
+      "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
+      "AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
+      "AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
+    },
+    "embd_pdrop": 0.0,
+    "eos_token_id": 32000,
+    "hidden_size": 3072,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
+    "model_type": "phi3",
+    "original_max_position_embeddings": 4096,
+    "pad_token_id": 32000,
+    "resid_pdrop": 0.0,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "long_factor": [
+        1.0299999713897705,
+        1.0499999523162842,
+        1.0499999523162842,
+        1.0799999237060547,
+        1.2299998998641968,
+        1.2299998998641968,
+        1.2999999523162842,
+        1.4499999284744263,
+        1.5999999046325684,
+        1.6499998569488525,
+        1.8999998569488525,
+        2.859999895095825,
+        3.68999981880188,
+        5.419999599456787,
+        5.489999771118164,
+        5.489999771118164,
+        9.09000015258789,
+        11.579999923706055,
+        15.65999984741211,
+        15.769999504089355,
+        15.789999961853027,
+        18.360000610351562,
+        21.989999771118164,
+        23.079999923706055,
+        30.009998321533203,
+        32.35000228881836,
+        32.590003967285156,
+        35.56000518798828,
+        39.95000457763672,
+        53.840003967285156,
+        56.20000457763672,
+        57.95000457763672,
+        59.29000473022461,
+        59.77000427246094,
+        59.920005798339844,
+        61.190006256103516,
+        61.96000671386719,
+        62.50000762939453,
+        63.3700065612793,
+        63.48000717163086,
+        63.48000717163086,
+        63.66000747680664,
+        63.850006103515625,
+        64.08000946044922,
+        64.760009765625,
+        64.80001068115234,
+        64.81001281738281,
+        64.81001281738281
+      ],
+      "short_factor": [
+        1.05,
+        1.05,
+        1.05,
+        1.1,
+        1.1,
+        1.1500000000000001,
+        1.2000000000000002,
+        1.2500000000000002,
+        1.3000000000000003,
+        1.3500000000000003,
+        1.5000000000000004,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.000000000000001,
+        2.0500000000000007,
+        2.0500000000000007,
+        2.0500000000000007,
+        2.1000000000000005,
+        2.1000000000000005,
+        2.1000000000000005,
+        2.1500000000000004,
+        2.1500000000000004,
+        2.3499999999999996,
+        2.549999999999999,
+        2.5999999999999988,
+        2.5999999999999988,
+        2.7499999999999982,
+        2.849999999999998,
+        2.849999999999998,
+        2.9499999999999975
+      ],
+      "type": "su"
+    },
+    "sliding_window": 262144,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "text_model_id": "microsoft/Phi-3-mini-128k-instruct",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "pad_token_id": 32000,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96cc73baf290c931e6b0358ad0e7a1c501c66fe146e5e23e165309ca68abba6
+size 125866456