初始化项目，由ModelHub XC社区提供模型

Model: CerebrumTech/cere-llama-3-8b-tr
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+cere2.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+license: llama3
+language:
+- tr
+
+---
+<img src="https://huggingface.co/CerebrumTech/cere-llama-3-8b-tr/resolve/main/cere2.png"
+alt="CEREBRUM LLM" width="420"/>
+
+
+# CERE-LLMA-3-8b-TR
+
+This model is an fine-tuned version of a Llama3 8b Large Language Model (LLM) for Turkish. It was trained on a high quality Turkish instruction sets created from various open-source and internal resources. Turkish Instruction dataset carefully annotated to carry out Turkish instructions in an accurate and organized manner. 
+
+## Model Details
+
+- **Base Model**: LLMA 3 8B based LLM
+- **Tokenizer Extension**: Specifically extended for Turkish
+- **Training Dataset**: Cleaned Turkish raw data with 5 billion tokens, custom Turkish instruction sets
+- **Training Method**: Initially with DORA, followed by fine-tuning with LORA
+
+## Benchmark Results
+
+- **Winogrande_tr**: 56.16
+- **TruthfulQA_tr_v0.2**: 47.46
+- **Mmlu_tr_v0.2**: 46.46
+- **HellaSwag_tr_v0.2**: 48.87
+- **GSM8k_tr_v0.2**: 25.43
+- **Arc_tr_v0.2**: 41.97
+
+
+## Usage Examples
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Cerebrum/cere-llama-3-8b-tr",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Cerebrum/cere-llama-3-8b-tr")
+
+prompt = "Python'da ekrana 'Merhaba Dünya' nasıl yazılır?"
+messages = [
+    {"role": "system", "content": "Sen, Cerebrum Tech tarafından üretilen ve verilen talimatları takip ederek en iyi cevabı üretmeye çalışan yardımcı bir yapay zekasın."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    temperature=0.3,
+    top_k=50,
+    top_p=0.9,
+    max_new_tokens=512,
+    repetition_penalty=1,
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```

cere2.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06409aaa3442ab74e463ff1afd99fdcb968cbe2aeec763e36af270dd0901ad52
+size 5220763

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "nvidia/Llama3-ChatQA-1.5-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "transformers_version": "4.41.2"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80aed79d1681747e6cb788fea38737e9921e0b7e5cfca205247f2f277eaaab63
+size 1050673288

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e82852bba171778b1e1817b75645b5b9a82e6ebbee57cad3f445b9b5ba8b12
+size 956336592

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2d07615e101a85161f61aaa61c7197fd62c8109030813dc081cf8ee633a3c4
+size 989890680

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4128f6928c3df57e7b55bd378d63f741368a5a384616b108d69692208a4eae
+size 989890680

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbf0ff27b913eb158e73d0c0e1d56c31f7b042cda854b06366f74599ca7a98b
+size 989907288

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bd0d752201ceddd86926c4bb3a6d8cb9e624e4f7ce3ef08ba121cb691948a8
+size 956336608

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f053a55fe87f99bab85a1c242f7618b3de39aade3021ef78998574ae8c558815
+size 989890696

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc753c60281637a0272e4e14dc16bbd588ae9bcddee92662785a8cfaf69f1112
+size 989890696

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79272fe226b8558c728d8eaf29390125466bd42381f3a2d847b3dfeb8f851827
+size 989907312

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830fe55d79f348e4ef7491f06b7041f0b7cb9760d3d0296159d5637818e5827e
+size 956336616

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0efa902a424a01329a81e8362e995456ddc7be5a273b5a451f12d26214b23b45
+size 989890696

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d30f58477a0dda03790d6557f985719de7145b9a157b26dbcb9b3ed82c9998d2
+size 989890696

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c31a7cb820f33e38ef251ee12bbba4c93830e4eb10f1b9ef9c88003822234c8
+size 989907312

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1fa0f68b6ce73cee45b9687764f376a2b6928cf7c22532211aa04b6e7087f1
+size 956336616

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6027ae15fef52e4c053f45028f2d6d6732f80b63b829e6065fcb66cb49ee07
+size 989890696

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd08cfdb7e6cfdea5a9a56db82baaa5b0d5a01fdfe955ac8c49f788a6de59f3
+size 234906168

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e13d82dd95b22c2bb3ebc8d9948820043c7ee9a416a51c193ba1c8d87ee853
+size 1050673280

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.norm.weight": "model-00016-of-00017.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}