auto push D:2 T:16 Tok:16.4K S:16 E:20
Browse filesAutomatic background upload of fine-tuned model artifacts including updated README.
- README.md +13 -17
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -1,26 +1,22 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
-
library_name:
|
| 4 |
-
cardData:
|
| 5 |
-
model-index:
|
| 6 |
-
- name: "my-model-v3"
|
| 7 |
-
results:
|
| 8 |
-
- task:
|
| 9 |
-
type: "text-generation"
|
| 10 |
-
metrics:
|
| 11 |
-
- type: "perplexity"
|
| 12 |
-
value: 0.0
|
| 13 |
tags:
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
license: apache-2.0
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
# Model Artifacts (my-model-v3)
|
| 21 |
Este directorio contiene checkpoints intermedios y el modelo final fine-tuned continuamente.
|
| 22 |
|
| 23 |
## Training Statistics (Approximate)
|
| 24 |
-
- Datasets
|
| 25 |
-
- Total Texts Trained (
|
| 26 |
-
- Approx Total Tokens Trained (
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
+
- causal-lm
|
| 5 |
+
- peft
|
| 6 |
+
- autotrain
|
| 7 |
license: apache-2.0
|
| 8 |
+
base_model: arnir0/Tiny-LLM
|
| 9 |
---
|
| 10 |
|
| 11 |
# Model Artifacts (my-model-v3)
|
| 12 |
Este directorio contiene checkpoints intermedios y el modelo final fine-tuned continuamente.
|
| 13 |
|
| 14 |
## Training Statistics (Approximate)
|
| 15 |
+
- Datasets Processed (Max 1 step each): 2
|
| 16 |
+
- Total Texts Trained (Limit 1,000,000,000,000): 16
|
| 17 |
+
- Approx Total Tokens Trained (Limit 1,000,000,000,000): 16,384
|
| 18 |
+
- Global Samples Processed (Limit 1,000,000,000,000): 16
|
| 19 |
+
- Global Examples Yielded (Limit 1,000,000,000,000): 20
|
| 20 |
+
### Framework versions
|
| 21 |
+
|
| 22 |
+
- PEFT 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e757ee4fa81377cfa346c67f125217c007f9648fcd409c93429c2d55745d8aee
|
| 3 |
+
size 161784
|
tokenizer_config.json
CHANGED
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"extra_special_tokens": {},
|
| 35 |
"legacy": true,
|
| 36 |
-
"model_max_length":
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
|
|
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"extra_special_tokens": {},
|
| 35 |
"legacy": true,
|
| 36 |
+
"model_max_length": 1024,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|