Upload InkubaLM multi-task with adapters

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "YvanCarre/InkubaLM-multitask_distill",
+  "adapters": {
+    "adapters": {
+      "machine-translation": "seq_bn",
+      "sentiment-analysis": "seq_bn",
+      "xnli": "seq_bn"
+    },
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusion_name_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "LlamaAdapterModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModelForCausalLM": "lelapa/InkubaLM-0.4B--vulavulaslm.VulavulaLlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 32,
+  "prediction_heads": {
+    "machine-translation": {
+      "activation_function": "gelu",
+      "bias": true,
+      "dropout_prob": null,
+      "embedding_size": 1024,
+      "head_type": "causal_lm",
+      "label2id": null,
+      "layer_norm": true,
+      "layers": 2,
+      "shift_labels": true,
+      "vocab_size": 61788
+    },
+    "sentiment-analysis": {
+      "activation_function": "tanh",
+      "bias": true,
+      "dropout_prob": null,
+      "head_type": "classification",
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1,
+        "LABEL_2": 2
+      },
+      "layers": 2,
+      "num_labels": 3,
+      "use_pooler": false
+    },
+    "xnli": {
+      "activation_function": "tanh",
+      "bias": true,
+      "dropout_prob": null,
+      "head_type": "classification",
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1,
+        "LABEL_2": 2
+      },
+      "layers": 2,
+      "num_labels": 3,
+      "use_pooler": false
+    }
+  },
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 61788
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.1"
+}

machine-translation/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "machine-translation",
+  "version": "adapters.1.1.0"
+}

machine-translation/head_config.json

@@ -0,0 +1,20 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "dropout_prob": null,
+    "embedding_size": 1024,
+    "head_type": "causal_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": true,
+    "vocab_size": 61788
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "machine-translation",
+  "version": "adapters.1.1.0"
+}

machine-translation/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd574ea0d6427a0a3a53c284c8901a73ee0c1cdc54e8bb1cab44955d46650b6
+size 465434

machine-translation/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f94019959f76ba5744845bf97ea1f47a9f49a183347935c5baf8f2359c5ebd
+size 33318594

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f95ff5dcae433d413f63f618f2493417de985555d6af8aeb13024f8df0d33ee
+size 241922568

sentiment-analysis/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "sentiment-analysis",
+  "version": "adapters.1.1.0"
+}

sentiment-analysis/head_config.json

@@ -0,0 +1,22 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "layers": 2,
+    "num_labels": 3,
+    "use_pooler": false
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "sentiment-analysis",
+  "version": "adapters.1.1.0"
+}

sentiment-analysis/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a3b3227ad33f4c11d8c41ebe166dc838000c4176f1201305c04db24b540c05
+size 465370

sentiment-analysis/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb845315a8bf12b2997c7ff74ca84978fa9120302436eed20f9b4c610d75447
+size 552306

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c41fcc6d44fcc4e8269e41dffe0123687baf800bd95a9c8b5d48abd9cb8971b
+size 991189

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

xnli/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "xnli",
+  "version": "adapters.1.1.0"
+}

xnli/head_config.json

@@ -0,0 +1,22 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "layers": 2,
+    "num_labels": 3,
+    "use_pooler": false
+  },
+  "hidden_size": 1024,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "YvanCarre/InkubaLM-multitask_distill",
+  "model_type": "llama",
+  "name": "xnli",
+  "version": "adapters.1.1.0"
+}

xnli/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859b9e906ed47986007036046853c59173bd8913f1eeec326a6aa3ce39d1714e
+size 464218

xnli/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b9aaadc91a7329a94d861093ea1ac95e21b75f1397698cb389193ab5a4d8a7
+size 553995