update

config.json

@@ -0,0 +1,189 @@
+{
+    "_commit_hash": null,
+    "_name_or_path": "/data/bli/checkpoints/OTTER-MPT1B-RPJama",
+    "architectures": [
+        "OtterForConditionalGeneration"
+    ],
+    "cross_attn_every_n_layers": 1,
+    "model_type": "otter",
+    "text_config": {
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "alibi": true,
+        "alibi_bias_max": 8,
+        "architectures": [
+            "MosaicGPT"
+        ],
+        "attn_clip_qkv": null,
+        "attn_impl": "torch",
+        "attn_pdrop": 0,
+        "attn_qk_ln": true,
+        "attn_uses_sequence_id": false,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "d_model": 2048,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "emb_init_std": null,
+        "emb_init_uniform_lim": null,
+        "emb_pdrop": 0,
+        "embedding_fraction": 1.0,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "fan_mode": "fan_in",
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "hidden_size": 2048,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "init_device": "cpu",
+        "init_div_is_residual": true,
+        "init_gain": 0,
+        "init_nonlinearity": "relu",
+        "init_std": 0.02,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "logit_scale": null,
+        "low_precision_layernorm": true,
+        "max_length": 20,
+        "max_seq_len": 2048,
+        "min_length": 0,
+        "mlp_ratio": 4,
+        "model_type": "mosaic_gpt",
+        "n_heads": 16,
+        "n_layers": 24,
+        "no_bias": true,
+        "no_repeat_ngram_size": 0,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": null,
+        "param_init_fn": "kaiming_normal_",
+        "prefix": null,
+        "prefix_lm": false,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "resid_pdrop": 0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "sep_token_id": null,
+        "softmax_scale": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "tokenizer_name": "EleutherAI/gpt-neox-20b",
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": "float32",
+        "torchscript": false,
+        "transformers_version": "4.29.0",
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "use_cache": false,
+        "verbose": 0,
+        "vocab_size": 50432
+    },
+    "torch_dtype": "float32",
+    "transformers_version": null,
+    "use_media_placement_augmentation": true,
+    "vision_config": {
+        "_name_or_path": "openai/clip-vit-large-patch14",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_dropout": 0.0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "hidden_act": "quick_gelu",
+        "hidden_size": 1024,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "image_size": 224,
+        "initializer_factor": 1.0,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "layer_norm_eps": 1e-05,
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "min_length": 0,
+        "model_type": "clip_vision_model",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 16,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_channels": 3,
+        "num_hidden_layers": 24,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": null,
+        "patch_size": 14,
+        "prefix": null,
+        "problem_type": null,
+        "projection_dim": 512,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": null,
+        "torchscript": false,
+        "transformers_version": "4.29.0",
+        "typical_p": 1.0,
+        "use_bfloat16": false
+    }
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fe497fcf6e5879b5cae2674c8499facf75dec4e09f3696923a58dc923a093a
+size 9991503463

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d325540380c71972d189b305093236dc165537cbc49ccc7bb51d9a0650a751da
+size 243420981