Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- powermove72/Trinity_Notus-xb
+- powermove72/SoMix-xb
+base_model:
+- powermove72/Trinity_Notus-xb
+- powermove72/SoMix-xb
+---
+
+# Elysium-Slerp
+
+Elysium-Slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [powermove72/Trinity_Notus-xb](https://huggingface.co/powermove72/Trinity_Notus-xb)
+* [powermove72/SoMix-xb](https://huggingface.co/powermove72/SoMix-xb)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: powermove72/Trinity_Notus-xb
+        layer_range: [0, 50]
+      - model: powermove72/SoMix-xb
+        layer_range: [0, 50]
+merge_method: slerp
+base_model: powermove72/Trinity_Notus-xb
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+    ```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "powermove72/Elysium-Slerp"
+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"])
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "powermove72/Trinity_Notus-xb",
+  "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": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 50,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+
+slices:
+  - sources:
+      - model: powermove72/Trinity_Notus-xb
+        layer_range: [0, 50]
+      - model: powermove72/SoMix-xb
+        layer_range: [0, 50]
+merge_method: slerp
+base_model: powermove72/Trinity_Notus-xb
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+    

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64edb00f0082b73a42b5e5eff1465dcdb0daff86b5db816faaa3436048abf627
+size 960521552

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca02001cbef28a3f62c3729f1c921b4ec96ea0ee240f43e7882ca001666cbd48
+size 989890720

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb37d9937c06f90d24a5638b7fcec88c1a56ed0cf37e2e51665d3297023b91a
+size 989890728

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c47affd26a6f8fc2e97967956b8eafc59f7affb46f1d9271ae183eea5b7c01
+size 998287760

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781cd35f925d50afc51c87adfe02bfeab79aba75069474e7a95f9c095b57d77c
+size 947956216

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f667b686383ecd5f75dd7f64f38e6b0e04ce0c07db3212b3fd7bcf28b38ee4
+size 989890728

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e10404de7df77866057c7e9b0b7ea7f38744d1f22e599539a7f55c8f4e1c368
+size 989890720

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe0023ae2c5885c2eee90aee217540f3d99aa4500d538ffabd3f903634a4e32
+size 998287760

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86790066c6b5aa4e4c6db2cdd832bcdb081c66ab754d76723cc484daceecfeb0
+size 947956216

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8973337e4a9cca1c0789fb864d6d93e18cf4a1d033b8d795b8307b966da652
+size 989890728

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc960cf2429970e8bdc8aa8bffae612a734d6baaecdbefcb39f8cc8cf4310741
+size 989890728

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fb8fbd070b0424449680ea1f9f75c969c9b0cf52537116108ac573f1c52b48
+size 998287752

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac2fc533e6b77766ba941a60d109f1de371e0df52b04efc6735a1ec05ea7af9
+size 947956216

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b245e4585cb97d5ff41710ced930432f92d0c7d188f81596a56b052997b4fd7d
+size 989890728

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa3e418f21e50643ed52457406dcc1961b77e1f5f85957fe09f42043f5aaa4c
+size 989890728

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a78af07cac40ca1e69ce8a93f18a54141866cc6477f387d5acce3e47de71a7
+size 998287752

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873392f82491e4542c341bc730bdf02522dbec664a15985ca68dffd46c0f9916
+size 947956216

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15402c65c30b19b1c7d4072aaf12612fb8a5c3bb905a54cf15622bf5c243439
+size 989890728

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4b937ab1e2bd2a67a7803aaeee6f49d13cfdf5acf1a8ab1b04db52cf37ec5e
+size 989890728

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3071116d9e9ebeacfbd4a33762cc5e66dcb4db723d9480ef40a779708bd07a2
+size 998287760

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d0a65a7e2e7ce11eeeea5d319bc5d6495f8634da52a29ae883b3b1adf86dd9
+size 947956208

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d22c52ad520ccccee0f393f50e43a81dcb4d6eae6017c7855100829125e5a63
+size 989890712

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638c136b3f1b9737e00c198631e777fece098bbd91b601b91cc57c169e48dfa3
+size 755009440

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 22335496192}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00001-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "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 +1,48 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}