Commit
·
e44bce2
1
Parent(s):
5eed8a4
safetensors
Browse files- config.json +37 -91
- generation_config.json +6 -0
- pytorch_model.bin → model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,92 +1,38 @@
|
|
| 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 |
-
"diversity_penalty": 0.0,
|
| 40 |
-
"temperature": 1.0,
|
| 41 |
-
"top_k": 50,
|
| 42 |
-
"top_p": 1.0,
|
| 43 |
-
"typical_p": 1.0,
|
| 44 |
-
"repetition_penalty": 1.0,
|
| 45 |
-
"length_penalty": 1.0,
|
| 46 |
-
"no_repeat_ngram_size": 0,
|
| 47 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 48 |
-
"bad_words_ids": null,
|
| 49 |
-
"num_return_sequences": 1,
|
| 50 |
-
"output_scores": false,
|
| 51 |
-
"return_dict_in_generate": false,
|
| 52 |
-
"forced_bos_token_id": null,
|
| 53 |
-
"forced_eos_token_id": null,
|
| 54 |
-
"remove_invalid_values": false,
|
| 55 |
-
"exponential_decay_length_penalty": null,
|
| 56 |
-
"suppress_tokens": null,
|
| 57 |
-
"begin_suppress_tokens": null,
|
| 58 |
-
"architectures": [
|
| 59 |
-
"LlamaForCausalLM"
|
| 60 |
-
],
|
| 61 |
-
"finetuning_task": null,
|
| 62 |
-
"id2label": {
|
| 63 |
-
"0": "LABEL_0",
|
| 64 |
-
"1": "LABEL_1"
|
| 65 |
-
},
|
| 66 |
-
"label2id": {
|
| 67 |
-
"LABEL_0": 0,
|
| 68 |
-
"LABEL_1": 1
|
| 69 |
-
},
|
| 70 |
-
"tokenizer_class": null,
|
| 71 |
-
"prefix": null,
|
| 72 |
-
"bos_token_id": 1,
|
| 73 |
-
"pad_token_id": null,
|
| 74 |
-
"eos_token_id": 2,
|
| 75 |
-
"sep_token_id": null,
|
| 76 |
-
"decoder_start_token_id": null,
|
| 77 |
-
"task_specific_params": null,
|
| 78 |
-
"problem_type": null,
|
| 79 |
-
"_name_or_path": "",
|
| 80 |
-
"transformers_version": "4.37.1",
|
| 81 |
-
"aqlm": {
|
| 82 |
-
"nbits_per_codebook": 16,
|
| 83 |
-
"num_codebooks": 1,
|
| 84 |
-
"out_group_size": 1,
|
| 85 |
-
"in_group_size": 8
|
| 86 |
-
},
|
| 87 |
-
"model_type": "llama_aqlm",
|
| 88 |
-
"auto_map": {
|
| 89 |
-
"AutoConfig": "configuration_llama_aqlm.LlamaConfig",
|
| 90 |
-
"AutoModelForCausalLM": "modeling_llama_aqlm.LlamaForCausalLM"
|
| 91 |
-
}
|
| 92 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/nfs/scistore14/alistgrp/apanfero/models/Llama-2-13b-AQLM-2Bit-1x16-hf/",
|
| 3 |
+
"aqlm": {
|
| 4 |
+
"in_group_size": 8,
|
| 5 |
+
"nbits_per_codebook": 16,
|
| 6 |
+
"num_codebooks": 1,
|
| 7 |
+
"out_group_size": 1
|
| 8 |
+
},
|
| 9 |
+
"architectures": [
|
| 10 |
+
"LlamaForCausalLM"
|
| 11 |
+
],
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"auto_map": {
|
| 15 |
+
"AutoConfig": "configuration_llama_aqlm.LlamaConfig",
|
| 16 |
+
"AutoModelForCausalLM": "modeling_llama_aqlm.LlamaForCausalLM"
|
| 17 |
+
},
|
| 18 |
+
"bos_token_id": 1,
|
| 19 |
+
"eos_token_id": 2,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 5120,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 13824,
|
| 24 |
+
"max_position_embeddings": 4096,
|
| 25 |
+
"model_type": "llama_aqlm",
|
| 26 |
+
"num_attention_heads": 40,
|
| 27 |
+
"num_hidden_layers": 40,
|
| 28 |
+
"num_key_value_heads": 40,
|
| 29 |
+
"pretraining_tp": 1,
|
| 30 |
+
"rms_norm_eps": 1e-05,
|
| 31 |
+
"rope_scaling": null,
|
| 32 |
+
"rope_theta": 10000.0,
|
| 33 |
+
"tie_word_embeddings": false,
|
| 34 |
+
"torch_dtype": "float16",
|
| 35 |
+
"transformers_version": "4.38.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 32000
|
| 38 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "4.38.0"
|
| 6 |
+
}
|
pytorch_model.bin → model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5951318a4e30217e72c0445b71e1a91e94429a18f3bea12ada8cb500c2f3b2b2
|
| 3 |
+
size 4126099840
|