Upload folder using huggingface_hub

README.md

@@ -0,0 +1,35 @@
+---
+license: other
+---
+# Join our Discord! https://discord.gg/Nbv9pQ88Xb
+## 1000 MEMBERS STRONG 💪
+---
+
+[BeaverAI](https://huggingface.co/BeaverAI) proudly presents...
+
+# Donnager 70B v1 🚀
+
+![image/gif](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/_qbBZb5iSlQH2fi1J0346.gif)
+
+*Hitch your tits and pucker up, it's time to peel the paint!*
+
+## Arsenal (Supported Chat Templates)
+- Metharme (recommended)
+- Text Completion (recommended)
+- Mistral
+- Alpaca
+- Vicuna
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/lP90If4h0i8H82AgOjr5z.png)
+
+## Links
+- Original: https://huggingface.co/TheDrummer/Donnager-70B-v1
+- GGUF: https://huggingface.co/TheDrummer/Donnager-70B-v1-GGUF
+
+## Credit
+
+Thank you for the compute, Garg!
+
+Thank you @invisietch for the base model!
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/cyD7QKFLdvPrHEiPHVQh1.png)

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "BeaverAI/Donnager-70B-v1a",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32764,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.44.2",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.9",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

huggingface-metadata.txt

@@ -0,0 +1,34 @@
+url: https://huggingface.co/TheDrummer/Donnager-70B-v1
+branch: main
+download date: 2024-09-14 17:01:25
+sha256sum:
+    4a650b0896ce1b2bc9eee48ef60fd21892a7ae0f3cf7cef8895933fd0a5e1110 model-00001-of-00029.safetensors
+    07176987e2cca1875df83aeeae6df04d697665bfe1b23951990942b6e0aaf9d6 model-00002-of-00029.safetensors
+    356888a9f89b556d315f09cca8a663732bcdad23738c54c45df9301f4b3f9373 model-00003-of-00029.safetensors
+    68c8c23fc60fa947576f231ea0141f8ca1929b642195f2cc5087372f9a9e8db3 model-00004-of-00029.safetensors
+    79b2f1875200c468d2955f8c2b341b3e8ec1d261840521529d99ce6e872750ee model-00005-of-00029.safetensors
+    d237a4ee01e04bf83001de3188374d2d301d6ce3ba9cb5f5d867a00ca35ed7ad model-00006-of-00029.safetensors
+    e4312663cb97c9e41697b576f1e0b991ccd166aac63dc068052a901e2fd79e57 model-00007-of-00029.safetensors
+    b649f05a19f9d2d3b9d0825c30ff14fad36585f06b751ba15f695cdc9e1bb348 model-00008-of-00029.safetensors
+    86b90ceebbf67154deb49a1f008f282499a32f2735c346502f6640e6b5ed36df model-00009-of-00029.safetensors
+    ff4f821dfd4b33bb2396c3e725541a9efb2db1554973cac2a64d32ac35ce7490 model-00010-of-00029.safetensors
+    df5c87a306e000675c7892373da0bd3565ab1156920c9c10b42347412e5eff63 model-00011-of-00029.safetensors
+    e750a11246166879a055e5e8e4f9e3f38113ad920bb0ded96e0650acd4776a05 model-00012-of-00029.safetensors
+    5d05a09d9c92f40c4ce766cc79aefbfdb9595ecc907870a73dc2170d0dd64316 model-00013-of-00029.safetensors
+    68eb0b0fc73cc7b9467cc33c65e6e491c3344489eb4cf2717cf01ae880b5d8c1 model-00014-of-00029.safetensors
+    503a124c00064ab9779e310f40260b2902521479e07824c0b80a7e671e441352 model-00015-of-00029.safetensors
+    914feda23ecc50a04fba88aa4cf4765373309ae1fd4ba9d61394cde3460a7ceb model-00016-of-00029.safetensors
+    4c7bf9e5916be561ef2ab1fdd8439a69ff2dd4d007838ed67c25582a5e43c595 model-00017-of-00029.safetensors
+    ef938459dadcfaadff7256c6e04c5462037708974bb122adc5acdd4647550121 model-00018-of-00029.safetensors
+    599a86515e572f9ea3a172816690cd962e30d5a6573664f2d42893f76bcd8ec6 model-00019-of-00029.safetensors
+    8ff456f3e9aa1cbfee4de372a30e59a8e24b0e3e6e64a24be72b8deb20557cf9 model-00020-of-00029.safetensors
+    76c841934ecff9250dfcdf7ec52238b4feb7bac8ff0d127301c4a126968c6de3 model-00021-of-00029.safetensors
+    25e42b664a51e9bd3476b225b975942c11b81f4202968c5deafe639e7724acd1 model-00022-of-00029.safetensors
+    9c2b1b40c944284992ff6b5c0583d803bf125d958147e48b29ec4a62670b00a0 model-00023-of-00029.safetensors
+    3af9218cb83537fdb7dd20a95936c8b7969342bb6f11acbecb63916d01826cb5 model-00024-of-00029.safetensors
+    579efbcbd1f9b833b9fe3cfa68c0245ccd3ed8505b3d85967009a9bd8771d8ba model-00025-of-00029.safetensors
+    b5b88dfe01ea7668fe16a13baf02f8b8c16576f0207a30e968177a9e279a240d model-00026-of-00029.safetensors
+    8b5d77792359e45f067c5d067135f4fcaa7f6be546741c15a745604d0539f05c model-00027-of-00029.safetensors
+    2dbcc167ee5e2cf0997306a48694017fb38990b05a76d24475cb2c3462b6f685 model-00028-of-00029.safetensors
+    fb6d6d73cb93dac0e85db103dcc4b00da1f7cf46f889a3b9399f9e9e47a1d423 model-00029-of-00029.safetensors
+    9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 137953296384}, "weight_map": {"lm_head.weight": "model-00001-of-00029.safetensors", "model.embed_tokens.weight": "model-00001-of-00029.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.51.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.64.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.74.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.77.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.norm.weight": "model-00029-of-00029.safetensors"}}

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9024dfedcf766eddb99f1d4255d63f620b996b8f72f70f94d0425ff3ad0943f2
+size 8499879488

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661af9a7977a7fcfd87f946ab5a8b5fd5cff6904cc57672c26c8443d7c410147
+size 8585824244

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4686e650e9d6abbf9585796757409a1461e8a4275096a194887a9c3ea9fbde69
+size 8581131984

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305926f419f6626cb06d4940102f7dceaaa066bb8a680e431701f465c7c35839
+size 8538936852

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9403f1cc5ed932dfc93e1705d7f91aaa3fae43e1fd5820277fccf4167660ff48
+size 753925688

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}