如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。
\ No newline at end of file + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-07 +- train_batch_size: 2 +- eval_batch_size: 4 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 128 +- total_eval_batch_size: 32 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 2 + +### Framework versions + +- Transformers 4.40.1 +- Pytorch 2.1.2+cu121 +- Datasets 2.19.0 +- Tokenizers 0.19.1 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..18a6874 --- /dev/null +++ b/all_results.json @@ -0,0 +1,22 @@ +{ + "epoch": 1.971563981042654, + "eval_logits/chosen": 96.502197265625, + "eval_logits/rejected": 89.92664337158203, + "eval_logps/chosen": -430.8598937988281, + "eval_logps/rejected": -460.5821533203125, + "eval_loss": 0.5234470367431641, + "eval_rewards/accuracies": 0.6875, + "eval_rewards/chosen": -3.3595829010009766, + "eval_rewards/margins": 1.5659757852554321, + "eval_rewards/rejected": -4.925559043884277, + "eval_runtime": 124.8927, + "eval_samples": 750, + "eval_samples_per_second": 6.005, + "eval_steps_per_second": 0.192, + "total_flos": 0.0, + "train_loss": 0.5405629426240921, + "train_runtime": 2172.3856, + "train_samples": 6750, + "train_samples_per_second": 6.214, + "train_steps_per_second": 0.048 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a2881fe --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "HuggingFaceH4/zephyr-7b-gemma-sft-v0.1", + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu", + "hidden_activation": null, + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 24576, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 16, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.1", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..50e016f --- /dev/null +++ b/eval_results.json @@ -0,0 +1,16 @@ +{ + "epoch": 1.971563981042654, + "eval_logits/chosen": 96.502197265625, + "eval_logits/rejected": 89.92664337158203, + "eval_logps/chosen": -430.8598937988281, + "eval_logps/rejected": -460.5821533203125, + "eval_loss": 0.5234470367431641, + "eval_rewards/accuracies": 0.6875, + "eval_rewards/chosen": -3.3595829010009766, + "eval_rewards/margins": 1.5659757852554321, + "eval_rewards/rejected": -4.925559043884277, + "eval_runtime": 124.8927, + "eval_samples": 750, + "eval_samples_per_second": 6.005, + "eval_steps_per_second": 0.192 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3037da8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.40.1" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..9ec6bb0 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb1a8de48802752dc1d3683d8e21118d4bed87080699666223477672918387a +size 4995496656 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..77bb144 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44f15eb0a7070de109c7b0a621ddb9488f89c6a898f31f0eda994533daa5a55 +size 4982953168 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..91d9994 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f6147b0c34887cbc2d6bf62e98073b8c99fc3651a41770b7856eb3d22e5eee +size 4982953200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..ce660e9 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46b9a5f2722b41a821ccd1efe004428a23ebe156365049dfdbe514257219c49 +size 2113988336 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ea169ac --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,261 @@ +{ + "metadata": { + "total_size": 17075361792 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..fa665d5 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "bos_token": { + "content": "