[init] model

README.md

@@ -1,7 +1,77 @@
 ---
-license: apache-2.0
-language:
-- en
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: r-zephyr-7b-beta-qlora
+  results: []
 ---
 
-The 'r' means replicate. This model is a model replicated by using https://github.com/huggingface/alignment-handbook.
+# r-zephyr-7b-beta-qlora
+
+The 'r' means replicate. This model is a model replicated by using https://github.com/huggingface/alignment-handbook.
+
+This model is a fine-tuned version on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5232
+- Rewards/chosen: -0.9374
+- Rewards/rejected: -1.7181
+- Rewards/accuracies: 0.7734
+- Rewards/margins: 0.7807
+- Logps/rejected: -420.1122
+- Logps/chosen: -341.2448
+- Logits/rejected: 0.6190
+- Logits/chosen: 0.6345
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5917        | 0.21  | 100  | 0.5950          | -0.3904        | -0.7775          | 0.7109             | 0.3872          | -326.0618      | -286.5451    | -1.9790         | -1.9769       |
+| 0.5281        | 0.42  | 200  | 0.5492          | -0.8657        | -1.6137          | 0.7617             | 0.7479          | -409.6739      | -334.0814    | -0.2289         | -0.2367       |
+| 0.5321        | 0.63  | 300  | 0.5321          | -0.7444        | -1.4427          | 0.7734             | 0.6983          | -392.5731      | -321.9463    | 0.3829          | 0.3741        |
+| 0.5149        | 0.84  | 400  | 0.5233          | -0.9570        | -1.7432          | 0.7617             | 0.7862          | -422.6298      | -343.2071    | 0.6479          | 0.6688        |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fbcd5b76a21637fcf61e07a7d71ffb01dd5cc48bf75fa7ae8d1b4d7b2f50a0
+size 1889595342

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4006c7b92a2517eaf203a52aa12df67086fddaea60b3bfd0288f4b5814c2b6
+size 1946254384

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac7f710314fca15b2b35f138bc52c7ee30debc0f1d7bea0bf1757cb06d3836b
+size 1979790678

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee05d0e799fc0db32c7c54f2cc2977bbc8f40b92ea28a11679aa76d039a7c640
+size 1946254448

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5f5468cf718a13ebb6c56abad099d77a045a8ff7e4458241cc0b1a8a4fb8dc
+size 1979790742

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b8f087d1d2ba31f131810084ede249fcf2d8fc6eb06c7f3efbf87440feb568
+size 1946254448

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e4e75a73f4f1a023523a0053e2eea69c343ea67acad81765865e4e1761c71d
+size 1979790742

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867adee93532cf34e1d6c4b833c5ec643188a310497541326337c56d29522a22
+size 815838630

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}