Hugging Face's logo

legendhasit
/
elijah-lm-7B-GPTQ

TensorBoard
Safetensors
Model card Files Metrics Community
froggotwo commited on
Commit
2a02dfc
·
0 Parent(s):

init bro

Browse files
Files changed (7) hide show
  1. .gitattributes +35 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jan10_06-22-18_1021c75be181/events.out.tfevents.1704867738.1021c75be181.2772.1 +3 -0
  5. training_log.json +16 -0
  6. training_parameters.json +37 -0
  7. training_prompt.json +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/TheBloke_speechless-mistral-dolphin-orca-platypus-samantha-7B-GPTQ",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "down_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "v_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efdd338b475dfd58d848a318572009346d31605dfb884ff8358263d434b9a8ae
3
+ size 335604696
runs/Jan10_06-22-18_1021c75be181/events.out.tfevents.1704867738.1021c75be181.2772.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c45c13ec43a152b996921029682d5dbe0f924b7df2552597cdce48d580242a5
3
+ size 6896
training_log.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name": "TheBloke_speechless-mistral-dolphin-orca-platypus-samantha-7B-GPTQ",
3
+ "base_model_class": "MistralForCausalLM",
4
+ "base_loaded_in_4bit": false,
5
+ "base_loaded_in_8bit": false,
6
+ "projections": "gate, down, up, q, v, k, o",
7
+ "train_runtime": 504.3907,
8
+ "train_samples_per_second": 19.826,
9
+ "train_steps_per_second": 0.099,
10
+ "total_flos": 2115741155328000.0,
11
+ "train_loss": 4.443607044219971,
12
+ "epoch": 32.0,
13
+ "current_steps": 1585,
14
+ "loss": 4.0742,
15
+ "learning_rate": 0.0
16
+ }
training_parameters.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lora_name": "50-elijah-2",
3
+ "always_override": false,
4
+ "q_proj_en": true,
5
+ "v_proj_en": true,
6
+ "k_proj_en": true,
7
+ "o_proj_en": true,
8
+ "gate_proj_en": true,
9
+ "down_proj_en": true,
10
+ "up_proj_en": true,
11
+ "save_steps": 0.0,
12
+ "micro_batch_size": 4,
13
+ "batch_size": 128,
14
+ "epochs": 50.0,
15
+ "learning_rate": "3e-4",
16
+ "lr_scheduler_type": "linear",
17
+ "lora_rank": 32,
18
+ "lora_alpha": 64,
19
+ "lora_dropout": 0.05,
20
+ "cutoff_len": 256,
21
+ "dataset": "None",
22
+ "eval_dataset": "None",
23
+ "format": "None",
24
+ "eval_steps": 100.0,
25
+ "raw_text_file": "50-elijah",
26
+ "overlap_len": 128,
27
+ "newline_favor_len": 128,
28
+ "higher_rank_limit": false,
29
+ "warmup_steps": 100.0,
30
+ "optimizer": "adamw_torch",
31
+ "hard_cut_string": "\\n\\n",
32
+ "train_only_after": "",
33
+ "stop_at_loss": 0,
34
+ "add_eos_token": false,
35
+ "min_chars": 0.0,
36
+ "report_to": "None"
37
+ }
training_prompt.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "template_type": "raw_text"
3
+ }