Update README.md

README.md

@@ -10,7 +10,113 @@ tags:
 - words
 - text2gpt
 ---
-<figure class="inline-block size-full items-center justify-center rounded-r-xl bg-gradient-to-br from-amber-500/10 to-transparent text-4xl max-md:py-6">
-  Text2GPT
-</figure>
-<h1>Thank you for using Text2GPT</h1>
+# Text2GPT (81.9M parameters)
+Currently Text2GPT uses the base model: distilbert/distilgpt2 to fine-tune
+
+# Files
+The following JSON files here:
+- tokenizer_config.json
+```json
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
+```
+- config.json
+```json
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}
+```
+other files...
+# Use it:
+## Load model directly
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("kulia-moon/Text2GPT")
+model = AutoModelForCausalLM.from_pretrained("kulia-moon/Text2GPT")
+```
+## Use a pipeline as a high-level helper
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="kulia-moon/Text2GPT")
+```
+# vLLM use:
+## Deploy with docker on Linux:
+```shell
+docker run --runtime nvidia --gpus all \
+	--name my_vllm_container \
+	-v ~/.cache/huggingface:/root/.cache/huggingface \
+ 	--env "HUGGING_FACE_HUB_TOKEN=<secret>" \
+	-p 8000:8000 \
+	--ipc=host \
+	vllm/vllm-openai:latest \
+#	--model kulia-moon/Text2GPT
+```
+## Load and run the model:
+```shell
+docker exec -it my_vllm_container bash -c "vllm serve kulia-moon/Text2GPT"
+```