Initial commit

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/scratch/project_462000319/general-tools/viking_v2_checkpoints/viking_v2_33B_iter_0191000_bfloat16",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "max_sequence_length": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "untie_embeddings_and_output_weights": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": -1,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ab147b8618d9ae9e755618ae9166e6e438f6ebc2d5f8e99b71d40a5878d3c6
+size 4932561768

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a915645ff5d0f7a9cfe9908c88e63b05cbab11942809adf2f81dbbd48f0c81
+size 4991370120

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d33176009aa8ce1a3b9df13def77089cf2c6bd9fbdf14bd34afb7dc88239777
+size 4756459736

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a349d5f56820865f42e1fb163866df0dfc8ecd8703897491e89279b4acfde9
+size 4756459760

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924b5da662e99c0087eb564a0a1d71811fdd951d3eaa2d48fedd0277d4c488fc
+size 4991370160

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011dd6adcaae7a67a705a3fa40beed1edde7fc67ce9ebc3b75f7ba16b0b0d0a4
+size 4756459760

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d1ab014581c6075d516a3ea9926829c9963a1d1b69bfa05cfd42b53fcb6740
+size 4756459760

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa12dc117da2a7fb2fd5ebf5c62244fa4b133e577e18fccd02f0627cd36e18c0
+size 4991370160

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebb06b58b997d90d764f356ab065071f817775987b1fd102a90748b8d425f04
+size 4756459760

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56258ed5d10871a511624d32e22356de060b1f170088fe82be7a448f53db297
+size 4756459760

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac4552b5cced05d1183cb8a8952a3c2a048802081ad98c2c76d6a9ff98c6cdf
+size 4991370160

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8976fb97cef8ab468175226a7b2ddc6740f64cbe64d1dfbcca2f68f67d23eca
+size 4756459760

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d09d268072cb2b00019407824579677ab402b90e9db256d310af25147f22d49
+size 4756459760

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0de43d97e6adff8d41891863d1bd5015994851059016e1c90a1177901be680
+size 3288407640

model.safetensors.index.json

@@ -0,0 +1,514 @@
+{
+  "metadata": {
+    "total_size": 66238068736
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "additional_special_tokens": [
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,227 @@
+{
+  "add_prefix_space": 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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}