Commit
•
d0a03ca
1
Parent(s):
12b7fc1
Upload 5 files
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- config.json +37 -0
- non_lora_trainables.bin +3 -0
- trainer_state.json +0 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/work/home/cryoem666/xyf/temp/pycharm/OPUS-BioLLM-CSTP/multi_modality_model/multi_modality_v1/model/llama3/",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11af961fc5c003dc5ac83e44800ce6d36761e31e523d6fce7a58db24b6aa2793
|
| 3 |
+
size 335604696
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/work/home/cryoem666/xyf/temp/pycharm/OPUS-BioLLM-CSTP/multi_modality_model/multi_modality_v1/model/llama3/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"device": "cuda",
|
| 10 |
+
"eos_token_id": 128001,
|
| 11 |
+
"freeze_switch_adapter": false,
|
| 12 |
+
"has_protein_encoder": true,
|
| 13 |
+
"has_switch_projector": true,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 4096,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 14336,
|
| 18 |
+
"max_position_embeddings": 8192,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
+
"model_type": "opus_llama",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-05,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 500000.0,
|
| 28 |
+
"switch_projector_lr": 1e-05,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"tokenizer_model_max_length": 256,
|
| 31 |
+
"tokenizer_padding_side": "right",
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.41.2",
|
| 34 |
+
"tune_switch_projector": false,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 128256
|
| 37 |
+
}
|
non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b98490afc40fc07abfc8d24adfd86cb2999ca8de9f678b168b14c31235c7c87
|
| 3 |
+
size 2483161264
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|