mahimairaja
commited on
Commit
•
7f22e7e
1
Parent(s):
1625e80
Update config.json
Browse files- config.json +64 -64
config.json
CHANGED
@@ -1,65 +1,65 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
}
|
|
|
1 |
{
|
2 |
+
"torchscript": False,
|
3 |
+
"torch_dtype": "float16",
|
4 |
+
"use_bfloat16": False,
|
5 |
+
"tf_legacy_loss": False,
|
6 |
+
"pruned_heads": {},
|
7 |
+
"tie_word_embeddings": False,
|
8 |
+
"is_encoder_decoder": False,
|
9 |
+
"is_decoder": False,
|
10 |
+
"cross_attention_hidden_size": None,
|
11 |
+
"add_cross_attention": False,
|
12 |
+
"tie_encoder_decoder": False,
|
13 |
+
"max_length": 20,
|
14 |
+
"min_length": 0,
|
15 |
+
"do_sample": False,
|
16 |
+
"early_stopping": False,
|
17 |
+
"num_beams": 1,
|
18 |
+
"num_beam_groups": 1,
|
19 |
+
"diversity_penalty": 0.0,
|
20 |
+
"temperature": 1.0,
|
21 |
+
"top_k": 50,
|
22 |
+
"top_p": 1.0,
|
23 |
+
"typical_p": 1.0,
|
24 |
+
"repetition_penalty": 1.0,
|
25 |
+
"length_penalty": 1.0,
|
26 |
+
"no_repeat_ngram_size": 0,
|
27 |
+
"encoder_no_repeat_ngram_size": 0,
|
28 |
+
"bad_words_ids": None,
|
29 |
+
"num_return_sequences": 1,
|
30 |
+
"chunk_size_feed_forward": 0,
|
31 |
+
"output_scores": False,
|
32 |
+
"return_dict_in_generate": False,
|
33 |
+
"forced_bos_token_id": None,
|
34 |
+
"forced_eos_token_id": None,
|
35 |
+
"remove_invalid_values": False,
|
36 |
+
"exponential_decay_length_penalty": None,
|
37 |
+
"suppress_tokens": None,
|
38 |
+
"begin_suppress_tokens": None,
|
39 |
+
"architectures": ["LlamaForCausalLM"],
|
40 |
+
"finetuning_task": None,
|
41 |
+
"id2label": {0: "LABEL_0", 1: "LABEL_1"},
|
42 |
+
"label2id": {"LABEL_0": 0, "LABEL_1": 1},
|
43 |
+
"tokenizer_class": None,
|
44 |
+
"prefix": None,
|
45 |
+
"bos_token_id": 1,
|
46 |
+
"pad_token_id": None,
|
47 |
+
"eos_token_id": 2,
|
48 |
+
"sep_token_id": None,
|
49 |
+
"decoder_start_token_id": None,
|
50 |
+
"task_specific_params": None,
|
51 |
+
"problem_type": None,
|
52 |
+
"_name_or_path": "mahimairaja/tweet-summarization-llama-2-finetuned",
|
53 |
+
"transformers_version": "4.32.1",
|
54 |
+
"model_type": "llama",
|
55 |
+
"quantization_config": {"quant_method": <QuantizationMethod.BITS_AND_BYTES: "bitsandbytes">,
|
56 |
+
"load_in_8bit": False,
|
57 |
+
"load_in_4bit": True,
|
58 |
+
"llm_int8_threshold": 6.0,
|
59 |
+
"llm_int8_skip_modules": None,
|
60 |
+
"llm_int8_enable_fp32_cpu_offload": False,
|
61 |
+
"llm_int8_has_fp16_weight": False,
|
62 |
+
"bnb_4bit_quant_type": "nf4",
|
63 |
+
"bnb_4bit_use_double_quant": False,
|
64 |
+
"bnb_4bit_compute_dtype": "float16"}}
|
65 |
+
}
|