Upload folder using huggingface_hub

README.md

@@ -1,3 +1,42 @@
 ---
-license: apache-2.0
+base_model:
+- flemmingmiguel/MBX-7B
+- flemmingmiguel/MBX-7B-v3
+tags:
+- mergekit
+- merge
+
 ---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [flemmingmiguel/MBX-7B](https://huggingface.co/flemmingmiguel/MBX-7B)
+* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+    - model: flemmingmiguel/MBX-7B-v3
+      layer_range: [0, 32]
+  - sources:
+    - model: flemmingmiguel/MBX-7B
+      layer_range: [20, 32]
+merge_method: passthrough
+dtype: float16
+
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "flemmingmiguel/MBX-7B",
+  "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": 44,
+  "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": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+
+slices:
+  - sources:
+    - model: flemmingmiguel/MBX-7B-v3
+      layer_range: [0, 32]
+  - sources:
+    - model: flemmingmiguel/MBX-7B
+      layer_range: [20, 32]
+merge_method: passthrough
+dtype: float16
+

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16e15b690c65d2ee77a599d25c2084dbdb5d9c5286e23b3791578fca6e689ff
+size 1912681544

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02508581bccaf389723b046bf77aab40a6d901ba8521902d312e878f1fd2b93f
+size 1979781416

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e402e42e85ef6601408c1d97e172129f4a85bc0ae6d2a1504253e667865a97b
+size 1946243928

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2339034cc50fd5ca7c83776f62d788bef2e58daa14fc5cad2aadc82a5b8f4020
+size 1979781384

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3288066b169ed5937e2f84eaf27c862c70e627a60ce4a68fd54039b7850e80bb
+size 1862349040

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5abee31dec1388e961d2a95c9c91c9527fd5a94d967bc22545fed9feb930239
+size 1889595352

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2527b2f38b19811b4471a4978064a89f5fbb5e5bfcf0d1ca4445d370779451b
+size 1946243920

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0d5239f34c7e1ee5059bbe05f4e35b9360548607cd46364eb8859dbc54ce0a
+size 1973489712

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac62abdff5fb818cda4621db7216588a258245ded2af819dbe31d0d665e31305
+size 1929466032

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ae0fea3dbc66aa0b06eded85528e0ad3f712188ddb760c3b523d835a11b9e0
+size 1979781400

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea09ad965fd8de8e6d8a4f2559270f0acc788b355d95c901c1e7a5a16f29227
+size 318784432

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}