Upload folder using huggingface_hub

README.md

@@ -0,0 +1,57 @@
+---
+base_model:
+- powermove72/Shark-1
+- eren23/OGNO-7b-dpo-truthful
+tags:
+- merge
+- mergekit
+- lazymergekit
+- powermove72/Shark-1
+- eren23/OGNO-7b-dpo-truthful
+---
+
+# SharkOgno2-7b-Passthrough
+
+SharkOgno2-7b-Passthrough is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [powermove72/Shark-1](https://huggingface.co/powermove72/Shark-1)
+* [eren23/OGNO-7b-dpo-truthful](https://huggingface.co/eren23/OGNO-7b-dpo-truthful)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: powermove72/Shark-1
+      layer_range: [0, 24]
+  - sources:
+    - model: eren23/OGNO-7b-dpo-truthful
+      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/SharkOgno2-7b-Passthrough"
+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 +1,37 @@
+{
+  "_name_or_path": "powermove72/Shark-1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "GritLM/GritLM-7B--modeling_gritlm7b.MistralModel",
+    "AutoModelForCausalLM": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForCausalLM",
+    "AutoModelForSequenceClassification": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "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": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+slices:
+  - sources:
+    - model: powermove72/Shark-1
+      layer_range: [0, 24]
+  - sources:
+    - model: eren23/OGNO-7b-dpo-truthful
+      layer_range: [8, 32]
+merge_method: passthrough
+tokenizer_source: union
+dtype: float16
+    

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f06f6eacc9de7700783ff69f6a9a46ea126d9ada7cc510b67d4e0e48474211b
+size 960521544

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454b80310ef4e80508376427390ddd803c0790a9af02341ad16480a175b657d1
+size 905995856

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5e2653dd563c0fdf12a9a34a0743ce814491318aaccba3d10309ce9bf0049e
+size 989890704

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e1a6bacd7d3f677a2c70ea1649b3d40e80430cd07258caab245f979700784a
+size 998296048

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dfd07d27fef26ccce0b123ebd9514fadd2304cd42904b7a6ae0f9023708da38
+size 981502432

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcf40e07b987ca0345d434714388cd195db01e65efc317f2aed03bc5af04d3d
+size 922798672

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8ce090d5a5b17858e6581e5d2bc84409171bc09996eb04719d98ed435f4a48
+size 989890712

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4ef5e190840315a056ecdf0963aac7298ac63d6728f8b02581de0ea88cf1bc
+size 989890712

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98bce8dae89444f2fed707e4d96c59a472a2c88e349616001b1b1e748d61bd7
+size 989890712

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815db776b5ef2c9fe42f678c7d0e28e21ac0c66b1902d5f0e3360a42d019c9b9
+size 989890712

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74a1e61c95508568ee97864f72ed25e919237c5114d4df3f00abbaab7f491aa
+size 956353224

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229605c36645c990cb4976b1a1f3699090ed029fe613785abebb6545a72dbcd9
+size 989890712

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b466045c9da175f6952aef0b45a57cf8422471a6943523384f5942580692bf8d
+size 989890712

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6455fa0b3f7e94d2f5fd3351c621901b91c94db47a9cfa554781c97d2d9ae6
+size 989890712

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a168eef7922f6e890f2f4c7a252b8fae358a817286257ea57fa843fd0d66912b
+size 956344928

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f77749672fa59ba81dfefb26e3624cc357128777d418318724e19baf79328d
+size 989890712

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e39a03e59c694aedc2ee60c16b0b8157a47102aedecbc77f158057a2bbffc9a
+size 998287736

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb26ad63ec12cfed486a1c523698980462f9c733aa876ef31a960d3f286ceecd
+size 947956184

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b73bb36ec4b90d9d4f1f33bd48e317b4cce204f747d9a03053d2c2e456c1482
+size 989890688

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87e751ed2ee6aaff174da9a601317b3d4874e0554d618899158e844972acfab
+size 989890688

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a6f073fe3bfedcc8d4ffc68cb3393da98fc0f0ddf9b711aa24986fc051bbd7
+size 989898992

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246004f6312075720d3883c6782c7b0c181cbe3c2b339965f5aaa16b610f773f
+size 956344888

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21463048192}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.safetensors"}}

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_config.json

@@ -0,0 +1,50 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\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,
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}