Upload LlamaForCausalLM
Browse files- README.md +5 -5
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
README.md
CHANGED
|
@@ -2,20 +2,20 @@
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
- ja
|
| 5 |
-
|
|
|
|
| 6 |
tags:
|
| 7 |
- facebook
|
| 8 |
- meta
|
| 9 |
- pytorch
|
| 10 |
- llama
|
| 11 |
- llama-3
|
| 12 |
-
license: other
|
| 13 |
-
license_name: llama3
|
| 14 |
-
license_link: LICENSE
|
| 15 |
datasets:
|
| 16 |
- cl-nagoya/auto-wiki-qa
|
| 17 |
- llm-jp/databricks-dolly-15k-ja
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# 日本語向け Llama 3 8B
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
- ja
|
| 5 |
+
license: other
|
| 6 |
+
library_name: transformers
|
| 7 |
tags:
|
| 8 |
- facebook
|
| 9 |
- meta
|
| 10 |
- pytorch
|
| 11 |
- llama
|
| 12 |
- llama-3
|
|
|
|
|
|
|
|
|
|
| 13 |
datasets:
|
| 14 |
- cl-nagoya/auto-wiki-qa
|
| 15 |
- llm-jp/databricks-dolly-15k-ja
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
license_name: llama3
|
| 18 |
+
license_link: LICENSE
|
| 19 |
---
|
| 20 |
|
| 21 |
# 日本語向け Llama 3 8B
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/mnt/NVM/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": 128,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 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 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62d888a6e40011067a10fc46b7cf63a13100d816cf5f3b34239088e5c82dfeec
|
| 3 |
+
size 54543312
|