Squash history for large model

Co-authored-by: leaderboard-pr-bot <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+license: llama2
+datasets:
+- the_pile_books3
+- togethercomputer/RedPajama-Data-1T-Sample
+language:
+- en
+---
+
+very wip experiment.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_chargoddard__llama-2-34b-uncode)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 36.2   |
+| ARC (25-shot)         | 39.51          |
+| HellaSwag (10-shot)   | 33.9    |
+| MMLU (5-shot)         | 38.49         |
+| TruthfulQA (0-shot)   | 40.94   |
+| Winogrande (5-shot)   | 74.35   |
+| GSM8K (5-shot)        | 20.77        |
+| DROP (3-shot)         | 5.43         |

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "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": "4.32.0.dev0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6970426c8dd4f773b21324da371b3b938719d452476a6dd0ce8d5d1ee5fc94ad
+size 9852623728

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6fe7226e03331e08c7dd6a7545ea35e7362d98f616f9627a4fbf557ac7d693
+size 9689078904

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43fe196566b21a81025ea712dca02e6cb2f01fe21690de954f60cd85e81df100
+size 9689078928

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee6fb22c8a79f3867271055a062ffd3f62a67dee783fa2b1f33eea32c65435f
+size 9689078928

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df7a3568702400936f2b504b17fa33fc0f509b9da4c1486d722c9ee4c0d13d1
+size 9689078928

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d2c304a2457042b27a008705030c3c213c98553335e5f61c70cdd8139feefc
+size 9689078928

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978cb9604c0219f39c73c6e4ba0f095722ab2b8717bcdf07b9b356a1a286e864
+size 9189972632

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}