Initial push of smartplat 3b v1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "CobraMamba/mamba-gpt-3b-v3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f09eef8f6f23611896543f9dbb009c3d93b9a99c95bf812d3ddfb7c791cf3d
+size 397315297

pytorch_model-00002-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab7cb2ca939393ae77762fad2e86072c68ab0b58c483da6595fe2c1fb6345d6
+size 385056275

pytorch_model-00003-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7738eea68ac0dd335630d1a82a48eed72179c1e84b64d745a57229647d5d203
+size 358417383

pytorch_model-00004-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9d77c04163041df93319ccd19335eb3f01a36ef0fdbbe256527a754ebffd51
+size 385056275

pytorch_model-00005-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf889aaa7cc916b79f8bab4e54071a3e198d5be9bdc6be76ea1674cbbe07bac4
+size 358417383

pytorch_model-00006-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0397c111abe72cc6c1f3dae626106a90bcd80adab10668489c06753320faed09
+size 385056275

pytorch_model-00007-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2c0a7789126b810483309258f6d8679395880e3434361e32659d143a6fa708
+size 358417383

pytorch_model-00008-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cf6bf88416a0e5d901c5b7504a062c9402fa69376522299d49418513a407ae
+size 385056275

pytorch_model-00009-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60407eb0ac974e909b99ff6dc6247cf4cb9a40b3f21e2ea82c370499c735d80c
+size 358417383

pytorch_model-00010-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb04ed5ff7c18072839a01af1bf6a2455d9dd676f99cf3a4c3ff3b3294db574a
+size 385056275

pytorch_model-00011-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab663b7101a705cf796844eab2deda3378c6f0f4b7e41197f8375bde096fceb5
+size 358417383

pytorch_model-00012-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6326532a33618fee800291a115888667062425123bae050f718dc325a21357
+size 385056275

pytorch_model-00013-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1554f6453f948760b065f7d1e059e4c081a9d3f02fb5bcd6aa4735dc11f5a246
+size 358417383

pytorch_model-00014-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f5d014ab1b89571836e8aab7472e4f6a46e17e305f7f5b1ec25a6098bb0c66
+size 385056275

pytorch_model-00015-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96edb330e58432fd5c955f744115e6b23a229dccc333ce74c79654af427c9cc7
+size 358417383

pytorch_model-00016-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f04b4bff5813f71c451ecaadc4c3cf45b4c789b45f841ba2d569defe88a2cb5
+size 385056275

pytorch_model-00017-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76083f3f0a01a3958114d07e70fdcc5c075ca71e5cdef71ebdd0add348cd4655
+size 358417383

pytorch_model-00018-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a268fa570dc8219a28f4e49f5b0698b2a88c41635e09e275423fce1f2e983a
+size 303141195

pytorch_model-00019-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17055b85ca12ecda0f8d3496084fa7650d0812284141e4f7fef64880a1d9c54
+size 204800938

pytorch_model.bin.index.json

@@ -0,0 +1,270 @@
+{
+  "metadata": {
+    "total_size": 6852952400
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00019-of-00019.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00019.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00019.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00019.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00019.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00019.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00019.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00019.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00019.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00019.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00019.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00019.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00019.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00019.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00019.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00019.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00019.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00019.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00019.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin",
+    "model.norm.weight": "pytorch_model-00018-of-00019.bin"
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}