Upload model
Browse files- README.md +2 -20
- adapter_config.json +8 -2
- adapter_model.safetensors +2 -2
README.md
CHANGED
@@ -81,7 +81,7 @@ Use the code below to get started with the model.
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
-
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
@@ -197,24 +197,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
200 |
-
|
201 |
-
|
202 |
-
## Training procedure
|
203 |
-
|
204 |
-
|
205 |
-
The following `bitsandbytes` quantization config was used during training:
|
206 |
-
- quant_method: bitsandbytes
|
207 |
-
- load_in_8bit: True
|
208 |
-
- load_in_4bit: False
|
209 |
-
- llm_int8_threshold: 6.0
|
210 |
-
- llm_int8_skip_modules: None
|
211 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
-
- llm_int8_has_fp16_weight: False
|
213 |
-
- bnb_4bit_quant_type: fp4
|
214 |
-
- bnb_4bit_use_double_quant: False
|
215 |
-
- bnb_4bit_compute_dtype: float32
|
216 |
-
|
217 |
### Framework versions
|
218 |
|
219 |
-
|
220 |
-
- PEFT 0.6.2
|
|
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
84 |
+
### Training Procedure
|
85 |
|
86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
|
|
197 |
## Model Card Contact
|
198 |
|
199 |
[More Information Needed]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
### Framework versions
|
201 |
|
202 |
+
- PEFT 0.10.0
|
|
adapter_config.json
CHANGED
@@ -1,15 +1,19 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
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 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.05,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 16,
|
@@ -18,5 +22,7 @@
|
|
18 |
"target_modules": [
|
19 |
"q_proj"
|
20 |
],
|
21 |
-
"task_type": "CAUSAL_LM"
|
|
|
|
|
22 |
}
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "huggyllama/llama-7b",
|
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": 16,
|
|
|
22 |
"target_modules": [
|
23 |
"q_proj"
|
24 |
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef5c2ed2a916cc4a7a7a1e9a13c9c4e084bcfe81c665bb553a818b94f0285032
|
3 |
+
size 16785792
|