Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+base_model:
+- psmathur/orca_mini_v3_13b
+- garage-bAInd/Platypus2-13B
+- TheBloke/Llama-2-13B-fp16
+- WizardLM/WizardMath-13B-V1.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# output-model-directory
+
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
+* [garage-bAInd/Platypus2-13B](https://huggingface.co/garage-bAInd/Platypus2-13B)
+* [WizardLM/WizardMath-13B-V1.0](https://huggingface.co/WizardLM/WizardMath-13B-V1.0)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: psmathur/orca_mini_v3_13b
+    parameters:
+      density: [1, 0.7, 0.1] # density gradient
+      weight: 1.0
+  - model: garage-bAInd/Platypus2-13B
+    parameters:
+      density: 0.5
+      weight: [0, 0.3, 0.7, 1] # weight gradient
+  - model: WizardLM/WizardMath-13B-V1.0
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: ties
+base_model: TheBloke/Llama-2-13B-fp16
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "TheBloke/Llama-2-13B-fp16",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+models:
+  - model: psmathur/orca_mini_v3_13b
+    parameters:
+      density: [1, 0.7, 0.1] # density gradient
+      weight: 1.0
+  - model: garage-bAInd/Platypus2-13B
+    parameters:
+      density: 0.5
+      weight: [0, 0.3, 0.7, 1] # weight gradient
+  - model: WizardLM/WizardMath-13B-V1.0
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: ties
+base_model: TheBloke/Llama-2-13B-fp16
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb54c434258b3400d15f415e36f58072e449d13237e60c6b903df3cf52f71fa0
+size 1955648560

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea6cf14ba04c5a0720c88397540bc8d273910e033e90df45cea00e49ee98250
+size 1955658904

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b6e6b421512fd81c9f02b592569316d385e736211d637c13aec669df45c42e
+size 1947784000

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1741cdfcb224fb0f08a5a68362eb6f54eb2f31c8f1105b32fe43b0bf975dd5f
+size 1903230016

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d039a93b1a9ab9b43f1cfb1e768fb680013b09ea9788e7c3b561ff2d53d53a6
+size 1903229992

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4217e567a2f869d20ac90c4b296739bdce95f06ec5b8420adae5a4dc83d5c8
+size 1976640456

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e232c72be542154b437f6c8f9d05c5476fecd28180582c13b213733e7cf3d15
+size 1955658936

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d845ab37b5c270b6a4a8c25bf92b26d8db3e5abdceda37801f04d3b6c077986b
+size 1955648568

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae97477b666d1ff5f0ac69323f0c9edc4d518d200d2f90baff584cd2cce24e60
+size 1903230016

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6917bca5b7acc7d0266a0589d4a9b642186d3251966b75d276894b2ff81d6d86
+size 1903230016

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e7020de0ab9e724cca32c5a4f68ef7460c748056abcc4b2a48689bc57d4cdb
+size 1955648568

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19121afff5ec23a1aba67e14c35663db2d65547966a8e5894f6400ce232ee5d4
+size 1955658936

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f013991695742449f0b1cb191ff045320df9dd1962ec8cf67263252da0f248b
+size 1984515088

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a430be5fd80c2852be440faa8e06a7943f8d18ab1d5ac74ce655fc8ed70705c4
+size 775988592

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.embed_tokens.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "lm_head.weight": "model-00013-of-00014.safetensors", "model.norm.weight": "model-00013-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}