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 +1,41 @@
+---
+base_model:
+- arcee-ai/Virtuoso-Small-v2
+- Sorawiz/InTooDeep-R1-14B-Test
+- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
+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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Sorawiz/InTooDeep-R1-14B-Test](https://huggingface.co/Sorawiz/InTooDeep-R1-14B-Test) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [arcee-ai/Virtuoso-Small-v2](https://huggingface.co/arcee-ai/Virtuoso-Small-v2)
+* [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Sorawiz/InTooDeep-R1-14B-Test
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
+  - model: arcee-ai/Virtuoso-Small-v2
+merge_method: model_stock
+base_model: Sorawiz/InTooDeep-R1-14B-Test
+parameters:
+  filter_wise: false
+dtype: float32
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Sorawiz/InTooDeep-R1-14B-Test",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 46,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: Sorawiz/InTooDeep-R1-14B-Test
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
+  - model: arcee-ai/Virtuoso-Small-v2
+merge_method: model_stock
+base_model: Sorawiz/InTooDeep-R1-14B-Test
+parameters:
+  filter_wise: false
+dtype: float32

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79e3c4acec4bd912cb903910f02076140e8ee2e679ca4e21d12b86ea88f2586
+size 3106099328

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bd63cc64bf7ff040308caf7f5a1d3189995213c4f04d7f30b73606bfa6e956
+size 4773426992

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ebef49c4341d2d49fd4e79e4355f6f6f64ad80e60086ad800ecb3c7b21c57a
+size 4939147752

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64dde373a0cdaaa72e660355c0c7aa55aee3d757853df512c2e4835721e5af9a
+size 4970534504

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c959ef2b35108582b3c41235ca8fdfbc13249af38b6d735131d7be019571ff88
+size 4939147752

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7be8a88bcbcf627a7ad834f59c5d644f7c38b82c56d2ec286a0025891bfa954
+size 4970534504

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a993062c1d5a428bedee1c8f10038452a4248fcbebb8b7b7be607ee96eedb641
+size 4939147752

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373bdc9e5b524d09b8b20f920b7667ca8c63e21265d13158c9e37ad9b0d70656
+size 4970534504

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66bee24394f055ce61c88c4d1973b4d0949c9ded041a45e7bec40162ccd571
+size 4939147760

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1be5ad4cefb7a730041816b1ee8043121112df956516124d377e1c7f1506d2
+size 4970534496

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7b89c0ab1daed32539f228b5050a3d728df39ad7931acb4db19736efa78e61
+size 4939147760

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0eb11e5229dfd19eb4305032b7686d918137b8f9f391d7ec760145bed0793d
+size 4970534464

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d749113af749f24a480dff2f2a73d179b7de679194936f2764baaf8af0c6f7a7
+size 1635920312

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 59063791616}, "weight_map": {"lm_head.weight": "model-00001-of-00013.safetensors", "model.embed_tokens.weight": "model-00002-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.norm.weight": "model-00013-of-00013.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}