Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+license: mit
+tags:
+- merge
+- mergekit
+- HuggingFaceH4/zephyr-7b-beta
+- mlabonne/NeuralHermes-2.5-Mistral-7B
+---
+
+# zephyr-7b-beta-passthrough
+
+zephyr-7b-beta-passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
+* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: HuggingFaceH4/zephyr-7b-beta
+      layer_range: [0, 32]
+  - sources:
+    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
+      layer_range: [16, 32]
+base_model: HuggingFaceH4/zephyr-7b-beta
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+slices:
+  - sources:
+    - model: HuggingFaceH4/zephyr-7b-beta
+      layer_range: [0, 32]
+  - sources:
+    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
+      layer_range: [16, 32]
+base_model: HuggingFaceH4/zephyr-7b-beta
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bcfbb0a2690c0d2fa89b7e6cb02fda232a6b2083801da110b4bc2f8a4c608f
+size 1973473592

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793eede4b646817f2d313d80d4fdf926efbc18d0407b1f77488e75ecb26f1328
+size 1946235688

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20371005d03bf772cb628b94aec98506895843e220b8cfd35e32b3dc40db3f6
+size 1946227336

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3ef8f86c179c9e3f167b16f289b69c8825fce790ace2b9413fbfaa84896c79
+size 1889644936

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a09836fc69d521f1f1dfcad015628c8b74f04483ffac0205145c66e8e009b1
+size 1979781456

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6cdef795b0547ce04930ea5bc4ea3a3bdd79e2c72e05a3aa2c5929b86b428c6
+size 1979781456

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a622519f2de7583d41139c1a9a6e6cb8fd9e5fc461e4cbd5e574d7349029838e
+size 1946243968

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91665921dd673e0e3ee0e6c695e37e9fa17dbf57a9fc518c8e8d02e23c4a35e4
+size 1979781440

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04a96a4aace9df0c75e06efc3edd6f2fc906f23aa013d8387fdaa5f3d9dfe05
+size 1946243992

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ef199de7017a510dea869a775d8b621d64e7e3f4cc6835decb2f506df2bbd0
+size 1979781440

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf439622b1f4e91829517a2db416d555ab0b172711c8fc59f79b8235b2bd505
+size 1895919816

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "lm_head.weight": "model-00004-of-00011.safetensors", "model.norm.weight": "model-00004-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.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.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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>",
+  "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
+}