ManojShack
commited on
Upload 14 files
Browse files- README.md +7 -7
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +63 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,9 +1,6 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
---
|
5 |
-
library_name: transformers
|
6 |
-
tags: []
|
7 |
---
|
8 |
|
9 |
# Model Card for Model ID
|
@@ -18,7 +15,7 @@ tags: []
|
|
18 |
|
19 |
<!-- Provide a longer summary of what this model is. -->
|
20 |
|
21 |
-
|
22 |
|
23 |
- **Developed by:** [More Information Needed]
|
24 |
- **Funded by [optional]:** [More Information Needed]
|
@@ -199,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
199 |
|
200 |
## Model Card Contact
|
201 |
|
202 |
-
[More Information Needed]
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: airev-ai/Amal-70b-v2
|
3 |
+
library_name: peft
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
18 |
+
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
196 |
|
197 |
## Model Card Contact
|
198 |
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "airev-ai/Amal-70b-v2",
|
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": 8,
|
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": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"k_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"v_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c54563d1bdd0cf6a90cde2e840ed3bee9eccfdae6381e31180ab656d92caa24
|
3 |
+
size 421218912
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:998b5f4e1f22e4edb7283952c06293596db2e670325bd6f4cb59029267fefe5f
|
3 |
+
size 215164626
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2659e5f28534a024c362e874240fb05b8b305959220aa25147c971bb89eb5c70
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24a8f28a179a87cf1352fb7bac05be1ce61658cd2804c82904c7a42115109d72
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.18895733343411059,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07558293337364423,
|
13 |
+
"grad_norm": 0.4784471392631531,
|
14 |
+
"learning_rate": 1.5470699432892252e-05,
|
15 |
+
"loss": 0.8895,
|
16 |
+
"step": 1000
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.07558293337364423,
|
20 |
+
"eval_loss": 0.8893495798110962,
|
21 |
+
"eval_runtime": 30073.3919,
|
22 |
+
"eval_samples_per_second": 0.426,
|
23 |
+
"eval_steps_per_second": 0.053,
|
24 |
+
"step": 1000
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.15116586674728846,
|
28 |
+
"grad_norm": 0.38212183117866516,
|
29 |
+
"learning_rate": 1.3958412098298676e-05,
|
30 |
+
"loss": 0.8797,
|
31 |
+
"step": 2000
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.15116586674728846,
|
35 |
+
"eval_loss": 0.8847432136535645,
|
36 |
+
"eval_runtime": 30074.8516,
|
37 |
+
"eval_samples_per_second": 0.426,
|
38 |
+
"eval_steps_per_second": 0.053,
|
39 |
+
"step": 2000
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 1000,
|
43 |
+
"max_steps": 13230,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 1,
|
46 |
+
"save_steps": 500,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": false
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 2.390804414660346e+19,
|
60 |
+
"train_batch_size": 8,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b50cb251ede901eff9a6fe57eafe89404124c32e49bbfe228b27c108ba52bd
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|