初始化项目，由ModelHub XC社区提供模型

Model: HA-Siala/Mamba-full-v0.1
Source: Original Platform

.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 +1,14 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+license: apache-2.0
+tags:
+- mistral
+- fine-tuned
+---
+
+# HA-Siala/Mamba-full-v0.1
+
+Fine-tuned Mistral model to detect flaws in Mamba code and produce refactored versions of the code.
+For the dataset and source code used in this study, please refer to the official GitHub repository: https://github.com/Hanan-Abdulwahab-Siala/Mamba
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856078299e6150c0a3cd06f0f9162dd2191361bb5e5247deb048d8a12d702457
+size 469762760

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97da7b639775d9e25425b5df6ca5a280be105c908f1290af4ca0c146ab42b8ad
+size 436225048

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112f69adc63042b7f1d673edd68d9fdcf25f9aa7477bb4cb3100f8f91b683df6
+size 436225048

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be92c5174542bd3d97115ef8de720980bfe0437dd92bbb70c2be61ac2af97a1e
+size 436225048

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ba09a6710f7deb46c61915ca5823ede116ca6cf19307511b0ea1fbc407a460
+size 436225048

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0122f122e44a1b92c8f21d72c93205377abdfe730b87ca9fcda22e0627a4b715
+size 436225048

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0da7eab9f1c638ca57e61a7b2a56815a8cb372b47ee436d997a263c4dea304
+size 436225048

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f09d52f36c0a2d51d883d0e7a04364e0ff40340f3353845e2fe456910a6528
+size 436225048

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8324fe547dd370d90652b79c750c4f47d33327150191eb7f7f0e620901c8a5
+size 436225048

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e102dfcf2ed87cd5e654886aff830bf39265e82c0bd43cc60ef773e1259183cb
+size 436225048

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3779c33545dbe4325efb3847fb53f9b8da8b3bc86fd8bc9a1b36b89449ef969
+size 436225064

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3d8455ae144747d6a5889d6f8f55e100f035f7679192bdde0bb3a07ef26530
+size 436225056

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04aa8ac5fd694d70bf755cb1c7dfc4753733add0e88b760fec7abe32e0ebcc07
+size 436225056

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2dbcc695702890e709a21e8410179af35824fe18a981d829c74c7d15b4e4d7
+size 436225056

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f54aff2b8ab57f5660a3584640fe8a03bc44bb9407cf84e428dc9db8fa4ea9
+size 436225056

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98fcc4443fa8fbf7165664b41391ddaff923ae9af372d6083b0d795fb2d19c84
+size 436225056

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d942bfddddab50579ca4ac226c6176eca59036ebddc13bf70da479aebd18eb5
+size 436225056

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdd9ae518d90875c62365d392b4a7389052469706e82a0c08bb0075ca72a79d
+size 436225056

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939069f39a2330a4389fe6b46ea55376dfc12d20eb262e786b4f6152639b4f8d
+size 436225056

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fa1e153a178f9e989ceb3430b0e89775cf355b12174ae76323d09fb1d2bef8
+size 436225056

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7012b157c92673db330e15449cbbd0654ed9dc75b4cb2aafb1749f0749d54e
+size 436225056

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb3aed84f58d2fce3290d4f95c1787b0a0adb99c78059a42991009274a6bed9
+size 436225056

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e2ea7f45943109707d964850c08ca71b593147716f7dda5bc1d879fcfef758
+size 436225056

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a2dc0f3d34832e2a21491daac9b4076ce72ad7b69a171f62a4f567bd273df2
+size 436225056

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62970a55b7feb7b5f6eba89b375fff8d375e00fe1ddd4c885bbefc248d9fedfe
+size 436225056

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8490b265baab2752f3dc0eef4cc24b5f83ad151757c4fc2797013dedb4e989c
+size 436225056

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeff52b5f4aaede6cf75631c2a6ad780a3bbd45747f40bfc3b850a956cdf6aa
+size 436225056

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de94b6d9b5d30906a54a812c9fb7b99ab5817be8e492a29017d83e410d80621b
+size 436225056

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17374f35f4238b52c3383b70231930812f5e3b6d72d4841611d687bfd1c8c715
+size 436225056

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83226c910a13e502df66f615e412c3f9070f2d8ac6e4cf520ac4239e246a357
+size 436225056

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d5ada710dfbb343101cadbc7c74039e5522fd0c0fe0a65fb6c1011792294b8
+size 436225056

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bfc6ae0cc0d8d8437bfa1cabf462eadc8a965ca0d1bcec6c18eb570542cc5d
+size 436225056

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a99880ae1f38d8da18ddb500ed00d2a27d8ca74ef86d96bb7059d40d4e582e6
+size 234906168

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2975cd68958320f7134dcb0f89de98116c008519d1ef7645f9506982867f67b3
+size 268435584

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00034-of-00034.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00034.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00034.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00034.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00034.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00034.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00034.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00034.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00034.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00034.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00034.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00034.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00034.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00034.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00034.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00034.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00034.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00034.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00034.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00034.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00034.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00034.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00034.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00034.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00034.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00034.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00034.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00034.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00034.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00034.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00034.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00034.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00034.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00034.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00034.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00034.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00034.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00034.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00034.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00034.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00034.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00034.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00034.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00034.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00031-of-00034.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00034.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00034.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00034.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00032-of-00034.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00034.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00033-of-00034.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00034.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00034.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00034.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00034.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00034.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00034.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00034.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00034.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00034.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00034.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00034.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00034.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00034.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00034.safetensors",
+    "model.norm.weight": "model-00033-of-00034.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404