migueldeguzmandev commited on
Commit
edac708
1 Parent(s): b5af510

Upload 12 files

Browse files
cached_lm_GPT2TokenizerFast_128_manifestoV1.text ADDED
Binary file (919 kB). View file
 
cached_lm_GPT2TokenizerFast_128_manifestoV1.text.lock ADDED
File without changes
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Users/migueldeguzman/Desktop/papercliptodd/falcon-1b/v2/",
3
+ "alibi": true,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_falcon.FalconConfig",
11
+ "AutoModel": "modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": true,
18
+ "bos_token_id": 1,
19
+ "eos_token_id": 2,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 2048,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "max_position_embeddings": 2048,
25
+ "model_type": "falcon",
26
+ "multi_query": false,
27
+ "new_decoder_architecture": false,
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 24,
30
+ "num_kv_heads": 32,
31
+ "parallel_attn": false,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.33.3",
36
+ "use_cache": true,
37
+ "vocab_size": 50304
38
+ }
generate.py ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import AutoModelForCausalLM, AutoTokenizer
2
+
3
+ def main():
4
+ # Load the fine-tuned model and tokenizer
5
+ model_output_dir = "/Users/migueldeguzman/Desktop/papercliptodd/falcon-1b/v3/" # Replace with your fine-tuned model directory
6
+ tokenizer = AutoTokenizer.from_pretrained(model_output_dir)
7
+ model = AutoModelForCausalLM.from_pretrained(model_output_dir)
8
+
9
+ while True:
10
+ # User input for text generation prompt
11
+ prompt = input("Enter a prompt for text generation (or type 'exit' to quit): ")
12
+
13
+ if prompt.lower() == 'exit':
14
+ break
15
+
16
+ # Encode the prompt and generate text
17
+ input_ids = tokenizer.encode(prompt, return_tensors="pt")
18
+ output = model.generate(
19
+ input_ids,
20
+ max_length=1024,
21
+ num_return_sequences=1,
22
+ no_repeat_ngram_size=2,
23
+ top_k=50,
24
+ top_p=0.95,
25
+ temperature=0.001
26
+ )
27
+
28
+ # Decode and print the generated text
29
+ generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
30
+ print("Generated Text:")
31
+ print(generated_text)
32
+
33
+ if __name__ == "__main__":
34
+ main()
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.3"
6
+ }
manifestoV1.text ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da012fda21c62d8ff4f097c638723d3664d4014e998c7ff8ccce02e8dbcfd328
3
+ size 5246593815
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff