llama-8b-tootsie-phase3: step-819999

config.json

@@ -1 +1 @@
-{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"}
+{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73aa976565ef197d7e7da7964372d791854d77706d5ae7a2fa4cf018b9e7c976
+oid sha256:1713ec7668422385db16f0b31a12cfb93670f6ee61555e548f1517f8923b9ce4
 size 9831465704

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cf3055457cbc0543f13d4d67e275f788ce839a2c44952ea27de095fc106e29
+oid sha256:a812786892d16754f821c4fff94e30d36fb06a4c8e46938f2f129fb5d9aa758b
 size 9865007800

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0c426c795b2b1d1bbbbffcecc956853320d2a6c53d3bd0568db2880e92836f
+oid sha256:56e583f31e089b0a488a7202ad945150899586a782b175934d1d00f147219c7b
 size 8221912272

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a668915925ec8024563f7034a956cfb00c6e5e33e7da2518e9f172c53ff65894
+oid sha256:69af15bea9a671df7fa8b68237590049181fcc61fb7648afff0171b18c29d2cc
 size 4202692840

special_tokens_map.json

@@ -12,5 +12,6 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "pad_token": "<|end_of_text|>"
 }

tokenizer_config.json

@@ -2058,5 +2058,6 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }