Upload 9 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "VDrontGPT50m-Base",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 256,
+  "n_embd": 584,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 5,
+  "n_positions": 256,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e8867def7a9e6667814d692b5274a52a09757b51d04c8a846f1968ef2efc1e
+size 200014688

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "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|>",
+  "max_length": 64,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

use.py

@@ -0,0 +1,77 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+
+MODEL_PATH = "VDrontGPT50m-Base"
+TEMPERATURE = 0.6
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+def load_model_and_tokenizer(model_path):
+    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_path,
+        torch_dtype=torch.float16 if DEVICE == "cuda" else torch.float32,
+        device_map="auto",
+        trust_remote_code=False
+    )
+    if tokenizer.pad_token is None:
+        tokenizer.pad_token = tokenizer.eos_token
+    return model, tokenizer
+
+
+def generate_stream(model, tokenizer, prompt, temperature=0.4, max_new_tokens=128):
+    # Text continuation generator without chat history
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=2048)
+    inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True,
+        top_p=0.98,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+        streamer=streamer,
+    )
+
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    for new_text in streamer:
+        yield new_text
+
+    thread.join()
+
+
+def interactive_chat(model, tokenizer, temperature):
+    print(f"Simple text continuation (temp={temperature})")
+    print("Enter the beginning of the text, and the model will continue it.")
+    print("Commands: 'exit' or 'quit' — exit.")
+
+    while True:
+        try:
+            user_input = input("\nYou: ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print("\nGoodbye!")
+            break
+
+        if user_input.lower() in ["exit", "quit"]:
+            print("Goodbye!")
+            break
+
+        if not user_input:
+            continue
+
+        print()  # empty line before continuation
+        for token in generate_stream(model, tokenizer, user_input, temperature=temperature):
+            print(token, end="", flush=True)
+        print()  # finish the line
+
+
+if __name__ == "__main__":
+    model, tokenizer = load_model_and_tokenizer(MODEL_PATH)
+    interactive_chat(model, tokenizer, temperature=TEMPERATURE)