valerievloef
commited on
Commit
•
459290e
1
Parent(s):
f0991fe
Upload model
Browse files- README.md +4 -5
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- final_checkpoint/config.json +9 -25
- final_checkpoint/generation_config.json +3 -3
- final_checkpoint/model-00001-of-00003.safetensors +2 -2
- final_checkpoint/model-00002-of-00003.safetensors +2 -2
- final_checkpoint/model-00003-of-00003.safetensors +2 -2
- final_checkpoint/model.safetensors.index.json +0 -0
- tokenizer.json +1 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
-
base_model: bigcode/starcoder2-
|
9 |
model-index:
|
10 |
- name: finetune_starcoder2
|
11 |
results: []
|
@@ -14,10 +14,9 @@ model-index:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vall-e/huggingface/runs/pflx7g43)
|
18 |
# finetune_starcoder2
|
19 |
|
20 |
-
This model is a fine-tuned version of [bigcode/starcoder2-
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -55,7 +54,7 @@ The following hyperparameters were used during training:
|
|
55 |
### Framework versions
|
56 |
|
57 |
- PEFT 0.11.1
|
58 |
-
- Transformers 4.
|
59 |
- Pytorch 2.3.0+cu121
|
60 |
-
- Datasets 2.
|
61 |
- Tokenizers 0.19.1
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
+
base_model: bigcode/starcoder2-3b
|
9 |
model-index:
|
10 |
- name: finetune_starcoder2
|
11 |
results: []
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
|
|
17 |
# finetune_starcoder2
|
18 |
|
19 |
+
This model is a fine-tuned version of [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b) on an unknown dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
54 |
### Framework versions
|
55 |
|
56 |
- PEFT 0.11.1
|
57 |
+
- Transformers 4.41.2
|
58 |
- Pytorch 2.3.0+cu121
|
59 |
+
- Datasets 2.20.0
|
60 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "bigcode/starcoder2-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
-
"v_proj",
|
25 |
"o_proj",
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bigcode/starcoder2-3b",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
|
|
24 |
"o_proj",
|
25 |
"up_proj",
|
26 |
+
"down_proj",
|
27 |
"q_proj",
|
28 |
+
"v_proj",
|
29 |
+
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
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 sha256:893002930d3b445f48bec7cc1a2d144bc467dbd527211888e7bd53e2d0cc069b
|
3 |
+
size 18218008
|
final_checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bigcode/starcoder2-
|
3 |
"architectures": [
|
4 |
"Starcoder2ForCausalLM"
|
5 |
],
|
@@ -8,38 +8,22 @@
|
|
8 |
"embedding_dropout": 0.1,
|
9 |
"eos_token_id": 0,
|
10 |
"hidden_act": "gelu_pytorch_tanh",
|
11 |
-
"hidden_size":
|
12 |
-
"initializer_range": 0.
|
13 |
-
"intermediate_size":
|
14 |
"max_position_embeddings": 16384,
|
15 |
"mlp_type": "default",
|
16 |
"model_type": "starcoder2",
|
17 |
"norm_epsilon": 1e-05,
|
18 |
"norm_type": "layer_norm",
|
19 |
-
"num_attention_heads":
|
20 |
-
"num_hidden_layers":
|
21 |
-
"num_key_value_heads":
|
22 |
-
"quantization_config": {
|
23 |
-
"_load_in_4bit": true,
|
24 |
-
"_load_in_8bit": false,
|
25 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
26 |
-
"bnb_4bit_quant_storage": "uint8",
|
27 |
-
"bnb_4bit_quant_type": "nf4",
|
28 |
-
"bnb_4bit_use_double_quant": false,
|
29 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
-
"llm_int8_has_fp16_weight": false,
|
31 |
-
"llm_int8_skip_modules": null,
|
32 |
-
"llm_int8_threshold": 6.0,
|
33 |
-
"load_in_4bit": true,
|
34 |
-
"load_in_8bit": false,
|
35 |
-
"quant_method": "bitsandbytes"
|
36 |
-
},
|
37 |
"residual_dropout": 0.1,
|
38 |
-
"rope_theta":
|
39 |
"sliding_window": 4096,
|
40 |
-
"tie_word_embeddings": false,
|
41 |
"torch_dtype": "float32",
|
42 |
-
"transformers_version": "4.
|
43 |
"use_bias": true,
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 49152
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bigcode/starcoder2-3b",
|
3 |
"architectures": [
|
4 |
"Starcoder2ForCausalLM"
|
5 |
],
|
|
|
8 |
"embedding_dropout": 0.1,
|
9 |
"eos_token_id": 0,
|
10 |
"hidden_act": "gelu_pytorch_tanh",
|
11 |
+
"hidden_size": 3072,
|
12 |
+
"initializer_range": 0.018042,
|
13 |
+
"intermediate_size": 12288,
|
14 |
"max_position_embeddings": 16384,
|
15 |
"mlp_type": "default",
|
16 |
"model_type": "starcoder2",
|
17 |
"norm_epsilon": 1e-05,
|
18 |
"norm_type": "layer_norm",
|
19 |
+
"num_attention_heads": 24,
|
20 |
+
"num_hidden_layers": 30,
|
21 |
+
"num_key_value_heads": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"residual_dropout": 0.1,
|
23 |
+
"rope_theta": 999999.4420358813,
|
24 |
"sliding_window": 4096,
|
|
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.41.2",
|
27 |
"use_bias": true,
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 49152
|
final_checkpoint/generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
}
|
final_checkpoint/model-00001-of-00003.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 sha256:8a030b54c247c460e9fd49e0f0cf84a1899a4dc51cf0c05e3a9a7b86cf273f20
|
3 |
+
size 4916180040
|
final_checkpoint/model-00002-of-00003.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 sha256:2efe4f43f60f2d3a8098f198a34b38af8f7b8750fdca2a64b6dc2572140f274b
|
3 |
+
size 4998826856
|
final_checkpoint/model-00003-of-00003.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:c9a44c01e89bff09008dd19a6d09b4d0b274dbd5616b7cee45a979995b9a8795
|
3 |
+
size 2224751784
|
final_checkpoint/model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
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 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3f299a5612bbad0e6e6568a00f74016f13f63ffa06effb3dc4082d7c90c912b
|
3 |
size 5112
|