Upload folder using huggingface_hub
Browse files- README.md +12 -4
- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
README.md
CHANGED
|
@@ -1,8 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
-
-
|
|
|
|
| 5 |
- sft
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Model Card for Model ID
|
|
@@ -17,7 +22,7 @@ tags:
|
|
| 17 |
|
| 18 |
<!-- Provide a longer summary of what this model is. -->
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
- **Developed by:** [More Information Needed]
|
| 23 |
- **Funded by [optional]:** [More Information Needed]
|
|
@@ -198,4 +203,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 198 |
|
| 199 |
## Model Card Contact
|
| 200 |
|
| 201 |
-
[More Information Needed]
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-0.5B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-0.5B
|
| 7 |
+
- lora
|
| 8 |
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for Model ID
|
|
|
|
| 22 |
|
| 23 |
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
|
| 25 |
+
|
| 26 |
|
| 27 |
- **Developed by:** [More Information Needed]
|
| 28 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
|
| 203 |
|
| 204 |
## Model Card Contact
|
| 205 |
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-0.5B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 16,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 8,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e87a21327a7d7c607f70aa46007e27cbc627d5cd4e6e2d3f989aa3b54d8cad
|
| 3 |
+
size 2187800
|