feat(pytorch): added pytorch model

config.json

@@ -1,25 +1,16 @@
 {
-  "_name_or_path": "imone/Mistral_7B_with_EOT_token",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
+  "architecture": "llama",
+  "block_size": 8192,
+  "vocab_size": 32002,
+  "n_layer": 32,
+  "n_head": 32,
+  "dim": 4096,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.34.1",
-  "use_cache": true,
-  "vocab_size": 32002
-}
+  "hidden_act": "silu",
+  "rope_type": "norm",
+  "mlp_gate": true,
+  "layernorm": false,
+  "n_local_heads": 8,
+  "norm_eps": 9.999999747378752e-06,
+  "rope_base": 10000.0
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f2dc7a51f04dd8e1cdd20cb409a2877f31c914a8c1e6ded3bbefc34b82c791
+size 7695315862

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:59f006be56d8a743f6d39f22abe25d3e6556f95334953fe93ce038f54957470f
+size 556731

tokenizer_config.json

@@ -1,62 +1,17 @@
 {
+  "bos_token": "<s>",
+  "eos_token": "<|end_of_turn|>",
+  "unk_token": "<unk>",
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "1": {
       "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
-      "content": "<|end_of_turn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|pad_0|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
       "special": true
     }
-  },
-  "additional_special_tokens": [
-    "<|end_of_turn|>",
-    "<|pad_0|>"
-  ],
-  "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|end_of_turn|>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true
-}
+  }
+}