upload model

Browse files

Files changed (12) hide show

.gitattributes +2 -0
added_tokens.json +11 -0
config.json +143 -0
generation_config.json +8 -0
model.safetensors +3 -0
optimizer.pt +3 -0
preprocessor_config.json +19 -0
scheduler.pt +3 -0
special_tokens_map.json +47 -0
tokenizer_config.json +179 -0
trainer_state.json +131 -0
training_args.bin +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* 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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

added_tokens.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "</box>": 92552,
+  "</img>": 92545,
+  "</quad>": 92548,
+  "</ref>": 92550,
+  "<IMG_CONTEXT>": 92546,
+  "<box>": 92551,
+  "<img>": 92544,
+  "<quad>": 92547,
+  "<ref>": 92549
+}

config.json ADDED Viewed

	@@ -0,0 +1,143 @@

+{
+  "_commit_hash": null,
+  "architectures": [
+    "InternVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
+    "AutoModel": "modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "llm_config": {
+    "_name_or_path": "internlm/internlm2-chat-1_8b",
+    "add_cross_attention": false,
+    "architectures": [
+      "InternLM2ForCausalLM"
+    ],
+    "attn_implementation": "flash_attention_2",
+    "auto_map": {
+      "AutoConfig": "configuration_internlm2.InternLM2Config",
+      "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
+      "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bias": false,
+    "bos_token_id": 1,
+    "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "min_length": 0,
+    "model_type": "internlm2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 2,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 2.0,
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000,
+    "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": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.37.2",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_cache": true,
+    "vocab_size": 92553
+  },
+  "max_dynamic_patch": 12,
+  "min_dynamic_patch": 1,
+  "model_type": "internvl_chat",
+  "ps_version": "v2",
+  "select_layer": -1,
+  "template": "internlm2-chat",
+  "torch_dtype": "bfloat16",
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "image_size": 448,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-06,
+    "model_type": "intern_vit_6b",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 14,
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "return_dict": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.2",
+    "use_bfloat16": true,
+    "use_flash_attn": true
+  }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.2",
+  "eos_token_id": [
+    92542,
+    92543
+  ]
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5825fc69d95f626b0462b80f1d05bb169184d2b874c6e691dda733ab0e312689
+size 4428549526

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45bbed20ff493b5ee4da34cb088b89344db020e8e21a28664437c7aa529a4fd8
+size 6832499370

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 448
+}

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:29e5cdd2694bbb0dfbe9b312be1fa3c6fe622689e3083fb2cc0d2bd79d9542a9
+size 1064

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,47 @@

+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
+  ],
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,179 @@

+{
+  "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
+    },
+    "92538": {
+      "content": "<|plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92539": {
+      "content": "<|interpreter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92540": {
+      "content": "<|action_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92541": {
+      "content": "<|action_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92542": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92543": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92544": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92545": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92546": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92547": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92548": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92549": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92550": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92551": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92552": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_internlm2.InternLM2Tokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% 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": "</s>",
+  "model_max_length": 8192,
+  "pad_token": "</s>",
+  "tokenizer_class": "InternLM2Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,131 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.830188679245283,
+  "eval_steps": 1,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 111.0,
+      "learning_rate": 6e-06,
+      "loss": 1.6151,
+      "step": 1
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 65.0,
+      "learning_rate": 1.8e-05,
+      "loss": 1.5894,
+      "step": 3
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 286.0,
+      "learning_rate": 2.9936012644425518e-05,
+      "loss": 1.9202,
+      "step": 6
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 175.0,
+      "learning_rate": 2.8987083441065335e-05,
+      "loss": 1.5979,
+      "step": 9
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 89.5,
+      "learning_rate": 2.6970258409203596e-05,
+      "loss": 1.4915,
+      "step": 12
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 128.0,
+      "learning_rate": 2.4039519545688848e-05,
+      "loss": 1.0238,
+      "step": 15
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 96.5,
+      "learning_rate": 2.0418624992807297e-05,
+      "loss": 1.2875,
+      "step": 18
+    },
+    {
+      "epoch": 1.5283018867924527,
+      "grad_norm": 122.0,
+      "learning_rate": 1.638402539194953e-05,
+      "loss": 1.1833,
+      "step": 21
+    },
+    {
+      "epoch": 1.7547169811320755,
+      "grad_norm": 87.5,
+      "learning_rate": 1.2243757232751444e-05,
+      "loss": 1.1228,
+      "step": 24
+    },
+    {
+      "epoch": 1.9811320754716981,
+      "grad_norm": 67.0,
+      "learning_rate": 8.313924663351927e-06,
+      "loss": 1.1144,
+      "step": 27
+    },
+    {
+      "epoch": 2.150943396226415,
+      "grad_norm": 100.5,
+      "learning_rate": 4.894565345301642e-06,
+      "loss": 0.7711,
+      "step": 30
+    },
+    {
+      "epoch": 2.3773584905660377,
+      "grad_norm": 60.25,
+      "learning_rate": 2.2467429640557903e-06,
+      "loss": 1.0037,
+      "step": 33
+    },
+    {
+      "epoch": 2.6037735849056602,
+      "grad_norm": 67.5,
+      "learning_rate": 5.726153524077144e-07,
+      "loss": 1.0549,
+      "step": 36
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 50.75,
+      "learning_rate": 0.0,
+      "loss": 1.0016,
+      "step": 39
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": true,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8571b2549806a355ade2e01bfe8b3afd9faa28beee154a72c054876ea38fb024
+size 5304