llama2-7b-farmatodo_finetuned2
Browse files
README.md
CHANGED
|
@@ -4,6 +4,7 @@ tags:
|
|
| 4 |
model-index:
|
| 5 |
- name: llama2_finetuned_chatbot
|
| 6 |
results: []
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -27,6 +28,17 @@ More information needed
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
### Training hyperparameters
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
|
@@ -46,6 +58,7 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
|
|
|
| 49 |
- Transformers 4.30.2
|
| 50 |
- Pytorch 2.1.0+cu121
|
| 51 |
- Datasets 2.16.1
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: llama2_finetuned_chatbot
|
| 6 |
results: []
|
| 7 |
+
library_name: peft
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
|
| 32 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 33 |
+
- load_in_8bit: False
|
| 34 |
+
- load_in_4bit: True
|
| 35 |
+
- llm_int8_threshold: 6.0
|
| 36 |
+
- llm_int8_skip_modules: None
|
| 37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 38 |
+
- llm_int8_has_fp16_weight: False
|
| 39 |
+
- bnb_4bit_quant_type: nf4
|
| 40 |
+
- bnb_4bit_use_double_quant: True
|
| 41 |
+
- bnb_4bit_compute_dtype: float16
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
|
|
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
+
- PEFT 0.4.0
|
| 62 |
- Transformers 4.30.2
|
| 63 |
- Pytorch 2.1.0+cu121
|
| 64 |
- Datasets 2.16.1
|
adapter_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/llama-2-7b-chat-hf",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134264202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1c0434caf6de77f55ba946a92b50cefe232f30cf82145d3530fb796af2f9610
|
| 3 |
size 134264202
|
runs/Jan28_16-06-07_7c56aae4039a/events.out.tfevents.1706458017.7c56aae4039a.4742.0
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 sha256:2b8b7e378eb7809db95c2ca97f2d82e218ef9d859c7ea148c331cb2ca99dc08b
|
| 3 |
+
size 4880
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|