Upload folder using huggingface_hub

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "SillyTilly/c4ai-command-r-08-2024",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.0625,
+  "max_position_embeddings": 131072,
+  "model_type": "cohere",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 4000000,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": false,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "do_sample": true,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8191fa26b1670aec3df67c82e65872842386d170f5a43a688c7da8cd06c9e0fc
+size 4898947792

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30713ad2ce5227e44d15eb197c9dd9909b5a02aab9a6cb8b197c7cae1da9b6ae
+size 4932553552

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5fdff8303f6626f909403ebb11076c022113ce028a3c927de828648ba53f54
+size 4932570048

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9088b42fc7d1816bc5e213d5b4e366fedb5d907a82af148b3a72fdb610649155
+size 4831890616

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af18ea3edf0466aa0d0691619ce38be7eb975837c6b06b19fc0bfc330c2934e9
+size 4932553584

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8125e5d562344b8ed0871f4133f6bcbb84528c9a844e17aa8e2e436c1f4dd1
+size 4932553576

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6dd1a070584e48f65eedcc8bdf7a3e6bcb49b1c3e6184df1e1a3688a59ff799
+size 4932570080

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a72ae569a7803d6aa0553137efa95124b1b8472fa531d29fc920a7b890b5c3
+size 4831890640

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53068f7900feaee891e88028dcdd6f8e96b17a3fbd183066396f43edcf7ad21c
+size 4932553584

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fa33691941994da666ef5a587a2d4f78e524644b27d7850b9f8cd6815fde13
+size 4932553576

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cb425a851ec3e112018c29e2e876c16775d98f0e257517ee3cf58744651ffa
+size 4932570080

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788a60a4640fd99b8b26806debb4550af8a65f72014eae8af1ce7886bfd621fe
+size 4831890640

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8a7772360d89b5231e0e4ad133875b8159e99fd30b8267ff40ba8ae8a28277
+size 4932553584

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ffeaa3edb049489eabc8447588f2436c09c659d49e187956e7f2659046cbd0
+size 805339592

model.safetensors.index.json

@@ -0,0 +1,329 @@
+{
+  "metadata": {
+    "total_size": 64592953344
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-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.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.up_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.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-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.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.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-00010-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-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.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e773a231706a3ee5d05050ff27aa122a19df09ee7dd59eafa906b7487035b9
+size 12778456

tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255033": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c0fd31290e177a922d12e7258658361e86b9b3162093ccd4467b0d928fb2b7
+size 8184