Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+k2_chat_evals.png filter=lfs diff=lfs merge=lfs -text
+k2_chat_table_of_tables.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+---
+# K2-Chat: a fully-reproducible large language model outperforming Llama 2 70B Chat using 35% less compute
+
+K2 Chat is finetuned from [K2-65B](https://huggingface.co/LLM360/K2). K2 Chat outperforms Llama 2-70B-Chat on all evaluations conducted. The model also outperforms Llama 3-70B-Instruct on coding tasks.
+
+<center><img src="k2_chat_eval_table.png" alt="k2 eval table" /></center>
+
+## LLM360 Model Performance and Evaluation Collection
+The LLM360 Performance and Evaluation Collection is a robust evaluations set consisting of general and domain specific evaluations to assess model knowledge and function.
+
+Evaluations include standard best practice benchmarks, medical, math, and coding knowledge. More about the evaluations can be found here.
+
+<center><img src="k2_chat_table_of_tables.png" alt="k2 big eval table"/></center>
+
+## Datasets and Mix
+
+| Subset      | #Tokens | Avg. #Q | Avg. Query Len | Avg. #R | Avg. Reply Len |
+| ----------- | ----------- |----------- |----------- |----------- |----------- |
+| [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)      | 66,639,699       | 1.00 | 81.53 | 1.00 | 172.78 |
+| [OpenHermes-2](https://huggingface.co/datasets/teknium/OpenHermes-2.5)   |404,820,694        | 1.01 | 152.38	| 1.01	| 249.12 |
+| [FLAN_3M](https://arxiv.org/abs/2109.01652)   | 2,346,961,387        | 1.00 | 727.49	| 1.00	| 54.83 | 
+| [Standford Encyclopedia Philosophy](https://huggingface.co/datasets/AiresPucrs/stanford-encyclopedia-philosophy)   | 786,928        | 1.00	| 219.09 |	1.00	| 166.28 | 
+| [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories)   | 1,448,898        | 1.00	| 260.82	| 1.00	| 207.47 |
+| Safety & Alignment Data   | 99,976,621        | 1.00	| 126.71	| 1.00	| 373.79 |
+| Total | 2,920,634,227
+
+## Loading K2-Chat
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("LLM360/K2-Chat")
+model = AutoModelForCausalLM.from_pretrained("LLM360/K2-Chat")
+
+prompt = '<|beginofuser|>what is the highest mountain on earth?<|beginofsystem|>'
+
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+gen_tokens = model.generate(input_ids, do_sample=True, max_new_tokens=128)
+
+print("-"*20 + "Output for model"  + 20 * '-')
+print(tokenizer.batch_decode(gen_tokens)[0])
+```
+Alternatively, you can construct the prompt by applying the chat template of tokenizer on input conversation:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("LLM360/K2-Chat")
+model = AutoModelForCausalLM.from_pretrained("LLM360/K2-Chat")
+
+messages = [{"role": "user", "content": "what is the highest mountain on earth?"}]
+
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+gen_tokens = model.generate(input_ids, do_sample=True, max_new_tokens=128)
+
+print("-"*20 + "Output for model"  + 20 * '-')
+print(tokenizer.batch_decode(gen_tokens)[0])
+```
+## LLM360 Developer Suite
+We provide step-by-step finetuning tutorials for tech enthusiasts, AI practitioners and academic or industry researchers [here](https://www.llm360.ai/developer.html).
+
+## About LLM360
+LLM360 is an open research lab enabling community-owned AGI through open-source large model research and development.
+
+LLM360 enables community-owned AGI by creating standards and tools to advance the bleeding edge of LLM capability and empower knowledge transfer, research, and development.
+
+We believe in a future where artificial general intelligence (AGI) is created by the community, for the community. Through an open ecosystem of equitable computational resources, high quality data, and flowing technical knowledge, we can ensure ethical AGI development and universal access for all innovators.
+
+[Visit us](https://www.llm360.ai/)
+
+## Citation
+
+**BibTeX:**
+
+```bibtex
+@article{
+      title={LLM360 K2-65B: Scaling Up Fully Transparent Open-Source LLMs}, 
+      author={The LLM360 Team},
+      year={2024},
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "<commit_after>": 32016,
+  "<commit_before>": 32014,
+  "<commit_msg>": 32015,
+  "<empty_output>": 32013,
+  "<filename>": 32004,
+  "<fim_middle>": 32001,
+  "<fim_pad>": 32003,
+  "<fim_prefix>": 32000,
+  "<fim_suffix>": 32002,
+  "<gh_stars>": 32005,
+  "<issue_closed>": 32008,
+  "<issue_comment>": 32007,
+  "<issue_start>": 32006,
+  "<jupyter_code>": 32011,
+  "<jupyter_output>": 32012,
+  "<jupyter_start>": 32009,
+  "<jupyter_text>": 32010,
+  "<reponame>": 32017,
+  "<|beginofsystem|>": 32019,
+  "<|beginofuser|>": 32020,
+  "<|endofchat|>": 32021,
+  "<|endofsystemprompt|>": 32018
+}

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "LLM360/K2-Chat",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 22016,
+    "max_position_embeddings": 8192,
+    "max_sequence_length": 8192,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 64,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.40.1",
+    "use_cache": true,
+    "vocab_size": 32032,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.1",
+        "bits": 3.0,
+        "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": "4.39.3"
+}

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 130572369920
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00027-of-00027.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.norm.weight": "model-00027-of-00027.safetensors"
+  }
+}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedad1e7379335f4e85d1bf12ae3bd396b5b6d501b3b8b125951c03c246be466
+size 8530929672

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011309e3efcd847f267afd03a2a9db475a3f7d17b525774ca468b6a8cb76853d
+size 8589146380

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0a2933141de8372d73b29ce7f6ed5d952c3b4578bca4ded15034cd2ed37a33
+size 7896614692

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<|endofsystemprompt|>",
+    "<|beginofsystem|>",
+    "<|beginofuser|>",
+    "<|endofchat|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 +1,223 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|endofsystemprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<|beginofsystem|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<|beginofuser|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<|endofchat|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endofsystemprompt|>",
+    "<|beginofsystem|>",
+    "<|beginofuser|>",
+    "<|endofchat|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}