Upload folder using huggingface_hub

config.json

@@ -0,0 +1 @@
+{"return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": null, "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, "architectures": ["Olmo2ForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 100257, "pad_token_id": 100277, "eos_token_id": 100257, "sep_token_id": null, "decoder_start_token_id": 100257, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "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": [100257, 100277], "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "transformers_version": "4.57.3", "tf_legacy_loss": false, "use_bfloat16": false, "vocab_size": 100278, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "use_cache": true, "rope_theta": 500000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "rms_norm_eps": 1e-06, "model_type": "olmo2", "output_attentions": false}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cce8d1ccf97f61d0464c77e1d38c330eb3e9ee262909ec964432b90c4dfe49c
+size 4905044688

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12c3368e21f64efc6349d18a20bc3baba65c70c88d328d1b87683e8b47a8502
+size 4857404920

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9ad40428136f8dcdc7dbcd1bb994082f905631b3dd56d098aaf55177daf62b
+size 4857404912

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a72067c2145a74236bf5743598aa980aad8713400893feb54ae659582f7bc2
+size 4857404920

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce3afd1afd842e7ab9916c31b8a5b6d35e982dbfc033d72809f6c3b134b9909
+size 4857404912

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573f1518c224420fa8d401830be8cd5f8fcb7fa56697f8498cb485745c8f8fcc
+size 4857421328

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 29192044544}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.3.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.4.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}