upload tokenizer and config from stable lm

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "StableLmForCausalLM"
+  ],
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm",
+  "layer_norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.25,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0",
+  "use_cache": true,
+  "use_qkv_bias": true,
+  "vocab_size": 100352
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2TokenizerFast",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}