Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model:
+- davzoku/cria-llama2-7b-v1.3
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Untitled Model (1)
+
+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:
+* [davzoku/cria-llama2-7b-v1.3](https://huggingface.co/davzoku/cria-llama2-7b-v1.3)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+# https://huggingface.co/Undi95/Mistral-11B-v0.1
+slices:
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [0, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "davzoku/cria-llama2-7b-v1.3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 32,
+  "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": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+# https://huggingface.co/Undi95/Mistral-11B-v0.1
+slices:
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [0, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336ddf6726292c1fc3b318051cf14cb8734ce695a5eb4766f9d1a25d50411157
+size 1979781688

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994e6bb0edceb9fac0f889c751cfa05197a738a52b3ae317123d7e97e5566c05
+size 1967215752

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d132bcc48c932e40a39f4ddb6bed983fc23d1d550f741499d6d765db535c1deb
+size 1990284288

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b347242214b32754e32efc7e3014048841d1458ad5045e726e7583504f33379
+size 1990284304

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e94485b7387695fc180fb7e05dd339e031a9076b3037ae21df12a8d6d79adfa
+size 1967215736

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ea7e713ef1692293002fb896dc4130a6f56756f50633b0d9ee88ce3e0b0529
+size 1979798288

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3556fb31933f3ff44d7c4e0f274636be19aa04840595fdca954cdc9f8ab3bc
+size 1977701688

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1511a4e0af2641cd8cd0332c15c18e5396c503c4ac21d7bfc0cc71ffbcbc3965
+size 1933661136

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6862d7204f571d1c4cca1763e42fbb691c8a5c03de649017e49154509b537ec4
+size 1918955104

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70e09ed963b97944d63e235993ffba9b46fcf3be37b3e6207bd9b2787e46c70
+size 1933661192

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0812856059e57846ee561291ac450d38df2fcb14b633a9b8267fb679c696e9ca
+size 314590128

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.39.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.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.22.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.22.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.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.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.21.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.21.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.21.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.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.20.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.20.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.20.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.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.19.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.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.9.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.9.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.9.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.9.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.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.8.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.8.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.8.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.embed_tokens.weight": "model-00009-of-00011.safetensors", "lm_head.weight": "model-00009-of-00011.safetensors", "model.norm.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.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.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": 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
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}