initial commit

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+figures/benchmark.png filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+---
+license: mit
+library_name: transformers
+---
+
+# 👉 Fathom-R1-14B-RS
+
+---
+## 🧮 Fathom-R1-14B: $499 Training Recipe for Unlocking Math Reasoning at o4-mini level using R1-distilled-14B model under 16K context
+
+ 
+<div align="center">
+ 
+[![collections](https://img.shields.io/badge/HFModels-Fathom--R1--14B-yellow?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-models-681b41a149682c7e32f8a9f2) 
+[![dataset](https://img.shields.io/badge/HFData-Fathom--R1--Data-green?logo=huggingface&style=for-the-badge)](https://huggingface.co/collections/FractalAIResearch/Fathom-r1-datasets-681b42fe6f20d4b11fc51d79) 
+[![space](https://img.shields.io/badge/HFSpace-Fathom--R1--14B-red?logo=huggingface&style=for-the-badge)](https://huggingface.co/spaces/FractalAIResearch/Fathom-R1-14B)
+[![GitHub - Fathom-R1-14B](https://img.shields.io/badge/GitHub-Fathom--R1-181717?logo=github&style=for-the-badge)](https://github.com/FractalAIResearchLabs/Fathom-R1)
+
+</div>
+

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 48,
+  "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": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9454002c16694c7aff4491ef3146abf24b69c1ccc66131f917460542ef33dd7d
+size 4907454960

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c77873364f3c38a26b30bdd5d06be0f7a37629e29db4a8330f46da850b710cf
+size 4954847384

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b23b210022e74aac2d7bb6741780edf20da5906960646d8fecc777c4eff025
+size 4954847376

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4263487d025c9891ce3f7d538d3c19dbc1ff434f5a44d1d30282b43d265e392d
+size 4954847376

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8a9f75f6aace0f37534f45619993b35c9b1a79619f89bf69d70885d256aa93
+size 4954847376

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe422e54b98cb8eda96660f16c8eaebbad8102d410d277e30cc188aa9b21c30
+size 4813289432

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 29540067328}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.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": "<|im_end|>",
+    "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 sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}