Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+---
+# LuminRP-13B-128k-v0.5
+LuminRP-13B-128k-v0.5 is the 13B parameter version of the v0.5, LuminRP-7B model which specializes in RP/ERP by merging a couple models that excels in it.
+***
+>[!IMPORTANT]
+> * Link to [Ppoyaa/LuminRP-7B-128k-v0.5](https://huggingface.co/Ppoyaa/LuminRP-7B-128k-v0.5)
+
+> * This model can and will output X-rated content.
+***
+## SillyTavern
+**Template**: Alpaca, ChatML, and Mistral should be okay.
+
+**Instruct Mode**: On
+***
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Ppoyaa/LuminRP-13B-128k-v0.5"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```
+***
+Merge Details Below:
+
+<details><summary>See Merge Config</summary>
+  
+```
+ChaoticNeutrals/BuRP_7B
+Endevor/InfinityRP-v1-7B
+Nitral-AI/Kunocchini-7b-128k-test
+core-3/kuno-royale-v2-7b
+KatyTheCutie/LemonadeRP-4.5.3
+grimjim/kukulemon-7B
+MaziyarPanahi/Calme-7B-Instruct-v0.9
+icefog72/WestIceLemonTeaRP-32k-7b
+crestf411/daybreak-kunoichi-2dpo-7b
+Undi95/Mistral-RP-0.1-7B
+```
+</details><br>

config.json

@@ -0,0 +1,43 @@
+{
+    "_name_or_path": "Ppoyaa/LuminRP-7B-128k-v0.5",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 16.0,
+        "finetuned": true,
+        "original_max_position_embeddings": 8192,
+        "type": "yarn"
+    },
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.3",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.1",
+        "bits": 3.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

mergekit_config.yml

@@ -0,0 +1,24 @@
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [4, 12]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [8, 16]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [12, 20]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [16, 24]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [20, 28]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+- sources:
+  - layer_range: [24, 32]
+    model: Ppoyaa/LuminRP-7B-128k-v0.5
+merge_method: passthrough
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 24952840192}, "weight_map": {"lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.embed_tokens.weight": "model-00010-of-00013.safetensors", "model.norm.weight": "model-00010-of-00013.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00013.safetensors"}}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997ef31cde667dd061fb21cc5a675eadaec1bd3dfb5c3d46da5b8439e08f5b77
+size 4947336508

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}