Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "euclaise/Ferret-3B",
+  "architectures": [
+    "StableLMEpochForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "euclaise/Ferret-3B--configuration_stablelm_epoch.StableLMEpochConfig",
+    "AutoModelForCausalLM": "euclaise/Ferret-3B--modeling_stablelm_epoch.StableLMEpochForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm_epoch",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rope_pct": 0.25,
+  "rope_theta": 10000,
+  "rotary_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87df7794a4a5c91e7b8fc3590da09dbc6468a42cd338a7c4549048ada6f4ad1
+size 257556616

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1223813b5f008f532260bdd6ec3e7fcccecb055005c6af10c58071c92023628
+size 194018848

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b2f42539a6b56731bb7e8d37c2315ff8926ab6cca8ea4b3d2d636a50efb6d6
+size 194008408

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4671a87b7fc95d298e736cbbf680b5dfdc9e315c999bd9ad8132216ee80144b0
+size 194018888

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638dc25ff017ae5e246ac5480712aee9df1c4fd9ea926cbb33377f7a4cf35d47
+size 197940808

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c382949794b2b776280369df5a9cf6d4c52665d1769b79b3e9ed2b027536ee90
+size 171736640

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4046029e87a08fc0935ef69d4c57d8fd8a8c735484f99899fac7ba09bed15a
+size 194008424

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c449225db947223bb6c2a84714f44f2167120ecf22fca2aeca7463aa0b78ff
+size 194008416

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852b3f0247c2f8c2653cd59c6d86b60c714cdb8f92c3de961f7bb37af813a280
+size 194018888

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6219d9c6c7bb5240bb7028ecfa037da342e0cce17fca50d9f75d82f547a98882
+size 197940808

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be56f278938ada8403355527f7e659f02af356ad5c2bbef0621899915b3bfb65
+size 171736640

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9a48c6064f6a76133449d3a19da8c821d67dc21cb1981c2e5aaa1d59b23d5c
+size 194008416

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2067e093e312e869ce0884d2937d75512f767cc30e998e7740dda87fa88cb1
+size 194008416

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244567cdfa69bc06a912471116291635686f570e3d5901e351021093d23dee20
+size 194018888

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a8b7d0008fe95f4a7e0ed42b4e96ef168fdb10a2ce373aa54e7fc72117d059
+size 197940808

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf945ae5735280146f899d9b821158b996aef6140ec756d78523330b969e318
+size 171736640

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07adecd48de06d3809bd863a56e9f817c1cab7fe18ddf95666947ea93396898
+size 194008424

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d043a682021d413548773ed2f78795d7bf69f3db534983d8f9ec1ee583d7a3f3
+size 194008416

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e20512fb45e656f47292e6631683275166d6117d3600cccb3f359977a190aa6
+size 194018888

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701ee42954a660918743e0f8e9c8ab016649bf70fb539b0b985fc3599f0d71dc
+size 175648104

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae6ee4c712712934b0aa4e52f920c771365dccc1550b74153f1482fb9a79d6f
+size 194008416

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c77d8774e69f08f651ba320c040817239baa18341a9586c8cb5643269136d74
+size 194008408

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804e3c091a27fe6236de1a8c9aee3cab8cd2287303a975c0616dbf0181fcbb15
+size 194018872

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c61bc2d871f445864c99066d2753964ba1856da5e670f79cbe80c3cc89bdaa
+size 197940800

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b998448333d8c4cdf7b861dca4ece77df96ef4fde6e71d60aab40f72fb5eaf38
+size 171736624

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268da65b39ea91d2ff05de0245d520db31cbe136a2107cfa5d160c3f79066de1
+size 158608408

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394bc8352b89f9c52731ffab843d7e6d86fcd13f51c027077ecd6ed8644df733
+size 257556608

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54e48d09a94ffbc3dd203e31aad5e3a6403ffaf49b781840794e2f0ed5d7996
+size 194039784

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74eaacff8b4cd1080142ad290ca23ae4073e8491fbadcdb59c3106f9ffb341b
+size 158618832

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00029.safetensors", "model.layers.0.input_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.1.input_layernorm.bias": "model-00002-of-00029.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00003-of-00029.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.input_layernorm.bias": "model-00003-of-00029.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.input_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00029.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.input_layernorm.bias": "model-00005-of-00029.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00029.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.input_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.14.input_layernorm.bias": "model-00006-of-00029.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00007-of-00029.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.15.input_layernorm.bias": "model-00007-of-00029.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00008-of-00029.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.input_layernorm.bias": "model-00008-of-00029.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.input_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00009-of-00029.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.input_layernorm.bias": "model-00010-of-00029.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00010-of-00029.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.input_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.2.input_layernorm.bias": "model-00011-of-00029.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00012-of-00029.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.20.input_layernorm.bias": "model-00012-of-00029.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00013-of-00029.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.input_layernorm.bias": "model-00013-of-00029.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.input_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00014-of-00029.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.input_layernorm.bias": "model-00015-of-00029.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00015-of-00029.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.input_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.25.input_layernorm.bias": "model-00016-of-00029.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00017-of-00029.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.26.input_layernorm.bias": "model-00017-of-00029.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00018-of-00029.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.input_layernorm.bias": "model-00018-of-00029.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.input_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.28.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00019-of-00029.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.3.input_layernorm.bias": "model-00020-of-00029.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00021-of-00029.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.4.input_layernorm.bias": "model-00021-of-00029.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00022-of-00029.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.input_layernorm.bias": "model-00022-of-00029.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.input_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.6.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00023-of-00029.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.input_layernorm.bias": "model-00024-of-00029.safetensors", "model.layers.7.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00024-of-00029.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.input_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.8.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.9.input_layernorm.bias": "model-00025-of-00029.safetensors", "model.layers.9.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00026-of-00029.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "lm_head.weight": "model-00027-of-00029.safetensors", "model.layers.29.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.29.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.30.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.31.input_layernorm.bias": "model-00028-of-00029.safetensors", "model.layers.31.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00029-of-00029.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.norm.bias": "model-00029-of-00029.safetensors", "model.norm.weight": "model-00029-of-00029.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}