Upload 30 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "theNovaAI/Supernova-experimental",
+  "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": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc94010b85b1f2f4ecef92b4b0e5741302f43841b4a89f173cbefc57b3fccd18
+size 1761651400

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4e5ff5addc16e31008dd7ec94d324cac6c89f9de500c04a974101ac4136c4f
+size 1879615864

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c0b6d4c1e7437705bd44fa87cc40f663a0656a694b4d57a8d7746ff6e60585
+size 1918979560

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a446bd4f467971fd0efe23a5ea2f101516ab40bc9d4b317a14b9063228c17b
+size 1955648576

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fe6a8fcafb5ea9f6b23735d46a2fff278b6380c40c10e6b2fa2badbc31073e
+size 1903219640

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f3e660a7d3bd0c14a646ceb1ecb0b79016604993e2f9a4322b2a5baba86d91
+size 1903230000

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bef87721dac03f9976226d6aed4fbaa4d74d95344244c6bc6a9cf58104dfc5
+size 1976640448

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6d8dd5ba4968f957c38723e3ec7131356a5196e1d7ac8b6c76240565826ec0
+size 1918969224

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c1ba3b4fe60f5675a4a4d7b22f8119fa827627ef9aa00b0255c227b73f501c
+size 1971387800

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475ed3bcda61d01e80a8eb3753e3e833ef69d9b16fdeb18e9e38695f08b82cf5
+size 1992348616

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff1cd33b051e029f226781010ece0db7a01816818706c166ca92d62ddf2cec8
+size 1939919688

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a840a71a3d5295c14937b469de58bc62234497587e766146264ca1c32764916f
+size 1903250712

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f508fa7313dc9200ae2aedb4921e3a26f8f68067554e0bc1617eaffd148047ec
+size 1879646904

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f90d1c01c7b4cf373ce24ca516b34ad3b3ce63a2179bfc7531287c4338db48
+size 1127262128

model-1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc94010b85b1f2f4ecef92b4b0e5741302f43841b4a89f173cbefc57b3fccd18
+size 1761651400

model-10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475ed3bcda61d01e80a8eb3753e3e833ef69d9b16fdeb18e9e38695f08b82cf5
+size 1992348616

model-2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4e5ff5addc16e31008dd7ec94d324cac6c89f9de500c04a974101ac4136c4f
+size 1879615864

model-3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c0b6d4c1e7437705bd44fa87cc40f663a0656a694b4d57a8d7746ff6e60585
+size 1918979560

model-4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a446bd4f467971fd0efe23a5ea2f101516ab40bc9d4b317a14b9063228c17b
+size 1955648576

model-5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fe6a8fcafb5ea9f6b23735d46a2fff278b6380c40c10e6b2fa2badbc31073e
+size 1903219640

model-6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f3e660a7d3bd0c14a646ceb1ecb0b79016604993e2f9a4322b2a5baba86d91
+size 1903230000

model-7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bef87721dac03f9976226d6aed4fbaa4d74d95344244c6bc6a9cf58104dfc5
+size 1976640448

model-8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6d8dd5ba4968f957c38723e3ec7131356a5196e1d7ac8b6c76240565826ec0
+size 1918969224

model-9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c1ba3b4fe60f5675a4a4d7b22f8119fa827627ef9aa00b0255c227b73f501c
+size 1971387800

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}