versae commited on
Commit
f5f653b
1 Parent(s): d139b7b

Upload for step 100 from Levanter

Browse files
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 8192, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "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": [1, 2], "architectures": ["MistralForCausalLM"], "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": 1, "pad_token_id": 2, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 1, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.41.1", "model_type": "mistral"}
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5b82b8f1fc3bf506d1129d9ac6f048843c072b55b0fee404272fa1f7e8711c
3
+ size 9831465704
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4fe990b20895972bce441b6dd1ea2874e24825684bac3e305a8af6942b4b763
3
+ size 9865007800
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18261f01ca5fd47d9f4359a9040b73b52cff6b62b12993c5dbb77744dd29fa02
3
+ size 9270488504
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"total_size": 28966928384}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors", "model.embed_tokens.weight": "model-00003-of-00003.safetensors", "lm_head.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }