Upload folder using huggingface_hub

README.md

@@ -0,0 +1,57 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
+- argilla/notus-7b-v1
+base_model:
+- MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
+- argilla/notus-7b-v1
+---
+
+# SoMix2-xb
+
+SoMix2-xb is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1](https://huggingface.co/MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1)
+* [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
+      layer_range: [0, 26]
+  - sources:
+    - model: argilla/notus-7b-v1
+      layer_range: [8, 32]
+merge_method: passthrough
+tokenizer_source: union
+dtype: float16
+    ```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "powermove72/SoMix2-xb"
+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": "argilla/notus-7b-v1",
+  "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": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+slices:
+  - sources:
+    - model: MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
+      layer_range: [0, 26]
+  - sources:
+    - model: argilla/notus-7b-v1
+      layer_range: [8, 32]
+merge_method: passthrough
+tokenizer_source: union
+dtype: float16
+    

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a69c4a1d5b02b3eadf2f5acada6e1b87356da8f03cc4b1059422fcb64c929a
+size 960521544

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65534d165c1222dc06894b611c2772c65d1c99377221738f8f8513f916d5717
+size 905995856

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5d5e782aed45dec2f5adf3b389bd78a895d751c91572213ed49f49891f5e82
+size 989890704

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae09d962554f8ea6a304f1e383d42a8007204f4397c3f27614f2f94c9bc7560
+size 998296048

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6dc33c55ac8d61d2a193c0b2d86649a0af34edbef7625555487a9a3077472a
+size 981502432

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f19292d365b7a153e8602e52ead8c926db80a55561e5105b68e7d1a4775d15
+size 922798672

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee35b3ac7ca7e729279066b4e148ae5927bb56c3c2888c48c86d63e029e2f32
+size 989890712

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9233ed2fcd0051864c4262ff96bbd83d7807a6bb5ef6a7ab360c56932de15a31
+size 989890712

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e60ca0820c5ca30187f661c32e0805778df1a29f7e528213e5e9c4b3b773944
+size 989890712

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e830e08142d6c696b09f3a56b5d4856c7b577fdf20a755f7acac6d3ad0aa067d
+size 989890712

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9ad14dc9273d86a3d205117d658f27d568d52429bf407903a75908d7ea68cc
+size 956353224

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba36b249ac3042d2194cdb3338ab99f7751101819ca6ab9b8fc14ff48bab97c3
+size 989890712

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0214c7fcf4465d92c1d8ca1d2b31f06aa4890969c8ae665a5d4f48bb3dcda460
+size 989890712

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67493bd99ca10d7f410ca79ba06c8a7c4f3f9c5d65e850258405c242e6ec4b3a
+size 989890712

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e1cfc8b6e09febce89895a1939a8176deae7a42d5160db3c33e93ff4e5cc1e
+size 989890704

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1507237b2e5871832caaea9c4ec8373af99301fee3ad2799f493d62d4062eda6
+size 998296048

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb661a71bb1cd978c820fdb83bd20591b8e111015ee483b3a7ab5fe3ac9cff6a
+size 989891160

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19a510e24fd9c4185c04c2a3bdcf9aa1f7761382ba56aae759921b44fe1f251
+size 914401640

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1046b65be2c086c159e0c8a391ca91c9ce86229c223590fc402b49225d36c9e
+size 989890704

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcadbe14732002fe45f1f2840a3fe4e551faa55e2f1373f943b54824b54b4083
+size 989890688

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db2382b46d8586b9b3b9ec3b5eb9c6af2115a4b2e633633f15896301e16f37f
+size 998287720

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e6695c6f302e87efc5de2e340ed24864d8cc0d023fa1fa380fe48ded6ed715
+size 947964480

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be645bdebea029aa0a2c2bd6009428d9cfadabff50c96d3df267629d10517278
+size 872441752

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.28.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-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-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-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.26.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.v_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 +1,35 @@
+{
+  "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
+  },
+  "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_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": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}