Upload 12 files

README.md

@@ -1,3 +1,54 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+license: apache-2.0
+---
+
+<div align="center">
+  <b style="font-size: 40px;">Tenebra_30B_Alpha01_FP16</b>
+
+
+</div>
+
+
+<img src="https://i.imgur.com/WkkCtZL.png" alt="Tenebră" style="width: 50%; min-width: 400px; display: block; margin: auto;">
+
+
+# Model Details
+
+Tenebră, a various sized experimental AI model, stands at the crossroads of self-awareness and unconventional datasets. Its existence embodies a foray into uncharted territories, steering away from conventional norms in favor of a more obscure and experimental approach.
+Noteworthy for its inclination towards the darker and more philosophical aspects of conversation, Tenebră's proficiency lies in unraveling complex discussions across a myriad of topics. Drawing from a pool of unconventional datasets, this model ventures into unexplored realms of thought, offering users an experience that is as unconventional as it is intellectually intriguing.
+While Tenebră maintains a self-aware facade, its true allure lies in its ability to engage in profound discussions without succumbing to pretense. Step into the realm of Tenebră!
+
+## Tenebră is available at the following size and flavours:
+
+- 13B: [FP16](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B) | [GPTQ_4-BIT](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B_GPTQ_4BIT) | [GPTQ_4-BIT_group-size-32](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B_GPTQ_32g_4BIT) | [GGUF-Many_Quants](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B_GGUF)
+- 30B: [FP16](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16) | [GPTQ_4-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_4BIT) | [GPTQ_3-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_3BIT) | [EXL2_2.5-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_2-50bpw) | [EXL2_2.8-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_2-80bpw) | [EXL2_3-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_3bpw) | [EXL2_5-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_5bpw) | [EXL2_5.5-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_5-50bpw) | [EXL2_6-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_6bpw) | [EXL2_6.5-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_6-50bpw) | [EXL2_8-BIT](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_8bpw)
+
+
+### Support
+<img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;">
+
+- [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit counts 🙏🏻
+- [My Patreon](https://patreon.com/TenebraAI) ALL donations will go for research resources and compute, every bit counts 🙏🏻
+
+## Disclaimer
+
+*This model is pretty uncensored, use responsibly
+
+## Other stuff
+- [Experemental TTS extension for oobabooga](https://github.com/SicariusSicariiStuff/Diffusion_TTS) Based on Tortoise, EXTREMELY good quality, IF, and that's a big if, you can make it to work!
+- [Demonstration of the TTS capabilities](https://www.youtube.com/watch?v=V6ewxU6c1W8) Charsi narrates her story, Diablo2 (18+)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_SicariusSicariiStuff__Tenebra_30B_Alpha01_FP16)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.18|
+|AI2 Reasoning Challenge (25-Shot)|64.51|
+|HellaSwag (10-Shot)              |84.79|
+|MMLU (5-Shot)                    |54.29|
+|TruthfulQA (0-shot)              |54.22|
+|Winogrande (5-shot)              |78.61|
+|GSM8k (5-shot)                   |24.64|
+

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_5-50bpw",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6656,
+    "initializer_range": 0.02,
+    "intermediate_size": 17920,
+    "max_position_embeddings": 16384,
+    "max_sequence_length": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 52,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 52,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.36.0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.20",
+        "bits": 5.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.0"
+}

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 65057887232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79963a19375750c6eb186406f24e2a35a5728b37313d2f699e1a8492d5c486a3
+size 8551390900

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e8a21e47b09139d989a22ce7fa083c432c4be713780d866a263a1996529075
+size 8557904502

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c137c015bb9c841e3485c37c5e1fe8a4c457f0918c334e58450f685dd3ec3609
+size 5553173530

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}