Upload tiny Cohere2ForCausalLM

config.json

@@ -5,33 +5,40 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 5,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "dtype": "bfloat16",
-  "eos_token_id": 255001,
+  "eos_token_id": 3,
   "head_dim": 2,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
   "layer_norm_eps": 1e-05,
+  "layer_switch": 4,
   "layer_types": [
     "sliding_attention",
     "sliding_attention"
   ],
-  "logit_scale": 0.0625,
-  "max_position_embeddings": 8192,
+  "logit_scale": 1.0,
+  "max_position_embeddings": 500000,
   "model_type": "cohere2",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
+  "order_of_interleaved_layers": "local_attn_first",
   "pad_token_id": 0,
-  "rope_parameters": {
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
+  "position_embedding_type": "rope_gptj",
+  "rope_scaling": null,
+  "rope_theta": 50000,
+  "rotary_pct": 1.0,
   "sliding_window": 4096,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.2.0.dev0",
+  "transformers_version": "4.56.2",
   "use_cache": true,
-  "vocab_size": 261010
+  "use_embedding_sharing": true,
+  "use_gated_activation": true,
+  "use_parallel_block": true,
+  "use_parallel_embedding": false,
+  "use_qk_norm": false,
+  "vocab_size": 262144
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 3,
   "pad_token_id": 0,
-  "transformers_version": "5.2.0.dev0"
+  "transformers_version": "4.56.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c48a02ad4c440b11d5d77902b18899e2c2effbf3c91c4674d3c2bc7dcdc92c6
-size 4181920
+oid sha256:010b86adeb01e8dcb7d25d91e072bf4ca270a96f4ecc746b08d650b12b12da63
+size 4200064

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d150b8af762b3662bdadc1fbc8274bc535ef86c0d497d0a40469fe86d92368
-size 21376340
+oid sha256:2227ea9c52e8afb3f98bfed2679008b275f2664de69dfde174b374389eb0225d
+size 21376527

tokenizer_config.json

@@ -1,20 +1,209 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "add_prefix_space": false,
-  "backend": "tokenizers",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261000": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261001": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261002": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261003": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261004": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261005": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261006": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261007": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
   "bos_token": "<BOS_TOKEN>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<CLS>",
   "eos_token": "<|END_OF_TURN_TOKEN|>",
-  "errors": "replace",
-  "is_local": false,
+  "extra_special_tokens": {},
   "legacy": true,
-  "mask_token": "<MASK_TOKEN>",
+  "merges_file": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<PAD>",
-  "sep_token": "<SEP>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "CohereTokenizer",
   "unk_token": "<UNK>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "vocab_file": null
 }