Upload 11 files

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "EleutherAI/gpt-j-6b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|ASSISTANT|>": 50257,
+  "<|SYSTEM|>": 50259,
+  "<|USER|>": 50258
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2-large",
+  "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": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "bfloat16",
+  "transformers_version": "4.30.1",
+  "use_cache": true,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc74cffab094a7fb2e0ae37c1dcedc4a522700cf0909ee9e05d4b284f3437c0e
+size 1548210205

run_model.py

@@ -0,0 +1,38 @@
+import torch
+from transformers import GPT2Tokenizer, AutoModelForCausalLM
+start_token = "<|ASSISTANT|>"
+end_token = "<|"
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2-large')
+model = AutoModelForCausalLM.from_pretrained('gpt2-large', torch_dtype=torch.bfloat16)
+tokenizer.pad_token = "[PAD]"
+tokenizer.eos_token = "<|endoftext|>"
+tokenizer.add_special_tokens({"additional_special_tokens": ["<|ASSISTANT|>", "<|USER|>", "<|SYSTEM|>"]})
+model.resize_token_embeddings(len(tokenizer))
+model.load_state_dict(torch.load("/media/locutusque/T7/Projects/results/pytorch_model.bin"))
+model.cuda()
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+def generate_text(model, tokenizer, prompt, max_length=1024):
+    prompt = f'<|USER|> {prompt} <|ASSISTANT|> '
+    input_ids = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt").to(device)
+    attention_mask = torch.ones_like(input_ids).to(device)
+    output = model.generate(input_ids, 
+                            max_length=max_length, 
+                            do_sample=True, 
+                            top_k=0, 
+                            top_p=0.1,
+                            temperature=0.75,
+                            repetition_penalty=1.176,
+                            pad_token_id=tokenizer.pad_token_id,
+                            eos_token_id=tokenizer.eos_token_id,
+                            attention_mask=attention_mask)
+    output_ids = tokenizer.decode(output[0], skip_special_tokens=False)
+    return output_ids
+# Loop to interact with the model
+while True:
+    prompt = input("Enter a prompt (or 'q' to quit): ")
+    if prompt == "q":
+        break
+    output_text = generate_text(model, tokenizer, prompt)
+    text_between_tokens = output_text[output_text.find(start_token) + len(start_token):]
+    out = text_between_tokens[:text_between_tokens.find(end_token)]
+    print(out)

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>",
+    "<|SYSTEM|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}