Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+base_model:
+- MaziyarPanahi/calme-3.2-instruct-78b
+- dfurman/CalmeRys-78B-Orpo-v0.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [dfurman/CalmeRys-78B-Orpo-v0.1](https://huggingface.co/dfurman/CalmeRys-78B-Orpo-v0.1) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [MaziyarPanahi/calme-3.2-instruct-78b](https://huggingface.co/MaziyarPanahi/calme-3.2-instruct-78b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: MaziyarPanahi/calme-3.2-instruct-78b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: dfurman/CalmeRys-78B-Orpo-v0.1
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "dfurman/CalmeRys-78B-Orpo-v0.1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: MaziyarPanahi/calme-3.2-instruct-78b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: dfurman/CalmeRys-78B-Orpo-v0.1
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3065c1960fe1bea9d747a79c22452558581a5db200ac6ab938ec2157edbf9a79
+size 4969152856

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb16c5338fe354452e1326c21eb561b2c6068a38582b68565ba077663d9d8d2d
+size 4980864400

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eec9bbee4872de5e134d25f8dbb33b8a0ffe1ea08b674d27418f6ccccbe69c
+size 4764874368

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2ffd2ad29a71f7c2301b51ab9bdc090366660f811ac683ef9475b297d03e85
+size 4781670352

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853c20f9f711f606dc0b05064f9dff118f9e912d21b05f2e55ea0dcbad59e522
+size 4781670368

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3263c7b666ed3cab82ac0c0fdd509930eb908403de46fb29c9a350a67afb1fb8
+size 4980864408

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e4b4cde3ba23e6ae61410bb2144abcf79d7eab04a71a51cee7e208455ed45e
+size 4764874368

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9388d9a3855b251adbacbc0b8eea6e1e27cb7d31285a20729e99dc6ed47c15db
+size 4781670352

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192694ef93b04627fcc67048c6ca18adbc241a509172af7e49de1a5be128f306
+size 4781670368

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a067d47f580464855bf536f72772e956b2d7591bd39f989985389c3213a757e
+size 4980864408

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce59f692390b7a57718c08ac94940dbb2ea24ddab2d44c5381f10376a94b74fb
+size 4764874368

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7398e3ac9fb72ce8174bbcb68cf2fb4d394edbbe7be93e5ff4e22663e5ccbf4a
+size 4781670352

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae9f4368cc49139b8bd1cee778d1918c208d3d6e537f9347f532317ea82ac47
+size 4781670368

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fb234450a3d20942e022908a45dffaecd7995d3ef192ab53355089e5178c96
+size 4980864408

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab95d66db458a0c281e68fa14a49f5ac12c19daa7b061a8053a7eb35aefd500
+size 4764874368

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fabe80ce0e17f27f317b492847ef45f941e5b69902e6b4b97445a6996936fcc
+size 4781670352

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1165e77a86ca458f83957b81e2e08562155eec0bcf13993aa2725ec03ef8710
+size 4781670368

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a6772f32072abe6c7401294b7f92cb41bce1fa1ee15c4cad9cd86e3b678d5b
+size 4980864408

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2ac0660b90e12d5ab4c237ab3700675677c9e21536c7449bb58c6f302391af
+size 4764874368

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6489e76d2143b5c0eb1708f60bf1f5ffdda1b56924aa715ab34876841009287a
+size 4781670352

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6728cc011041e68447ccf258f0022cf0d144a804c23ae86a66a9606323735d5b
+size 4781670368

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24dba5d0b52b650fb69ccc0b82bd6d543e22f5fabb737262351865257fc17d7f
+size 4980864408

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f835b5bcb7cd0934635773a8e706e204b68ff9d8824e1435f5db5c6dfb1714
+size 4764874368

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbf42ef5cd05e77bfdf77f3f1fbfaae76d03ea1602849301960b6f15f35e49d
+size 4781670352

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dc3285884a50a96b147a1554095adb38ca206ac4c445ec75d139ac1a12cb6f
+size 4781670368

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a972e7b8675b3a813999ad98ede6b0b0172f97eb4a0481f542c83ffeda430a10
+size 4980864408

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7b1b67860bc796f8eff67ad5b990baa285262ba4b5bc48ed745c119d3b9de4
+size 4764874368

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09be82f7aae0dca7b7c3b9e2eb6f907bcfb49afc98469df5aba9208f156b7e9c
+size 4781670352

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de158b94aca60a01a0cbd2987c8450cecdf818fb1b36f3769e8f7bd8f007a4fc
+size 4781670368

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477ffaec2d24417fa34ae3a304a2e219346bfa446cc1c49508cfb030b4578a82
+size 4980864408

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39bab45deff6dad6c6eb1d3776311da7b7abc6f8d4bca6e24a92de9e490f326
+size 4764874368

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eea0c1a1b103be5123fa36a674811b9fc94ffc15a2bde9edc01ee1124391ad4
+size 4781670352

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b279322eb625aa2af86c2a5013a42b86590f102fb9f126ddab7fa319527ea542
+size 1270928624

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 155930927104}, "weight_map": {"lm_head.weight": "model-00001-of-00033.safetensors", "model.embed_tokens.weight": "model-00001-of-00033.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.norm.weight": "model-00033-of-00033.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}