Synth-Ecosystem commited on
Commit
581cdb9
·
verified ·
1 Parent(s): ab88957

Training in progress, step 50

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: synthos-synth-evolution-v2
4
+ tags:
5
+ - generated_from_trainer
6
+ - sft
7
+ - trl
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for synthos-synth-evolution-v2
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
+ generator = pipeline("text-generation", model="Synth-Ecosystem/synthos-synth-evolution-v2", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 1.6.0
38
+ - Transformers: 5.12.1
39
+ - Pytorch: 2.11.0+cu128
40
+ - Datasets: 5.0.0
41
+ - Tokenizers: 0.22.2
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @software{vonwerra2020trl,
51
+ title = {{TRL: Transformers Reinforcement Learning}},
52
+ author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
53
+ license = {Apache-2.0},
54
+ url = {https://github.com/huggingface/trl},
55
+ year = {2020}
56
+ }
57
+ ```
adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "/nlsasfs/home/aikosh/prod-aikosh31/models/synthos_slm_core",
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": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 32,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "o_proj",
34
+ "down_proj",
35
+ "k_proj",
36
+ "v_proj",
37
+ "q_proj",
38
+ "up_proj",
39
+ "gate_proj"
40
+ ],
41
+ "target_parameters": null,
42
+ "task_type": "CAUSAL_LM",
43
+ "trainable_token_indices": null,
44
+ "use_bdlora": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33944d49867f2fc809cfe620f2482ae5e9598d2b88f08b5894d6b655e50e08e
3
+ size 38572808
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% for item in messages %}{% if item['role'] == 'system' %}<|system|>
2
+ {{ item['content'] }}{% elif item['role'] == 'user' %}<|user|>
3
+ {{ item['content'] }}{% elif item['role'] == 'assistant' %}<|assistant|>
4
+ {{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>
5
+ {% endif %}
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": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "do_lower_case": false,
7
+ "eos_token": "<|endoftext|>",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "[MASK]",
11
+ "[gMASK]",
12
+ "[sMASK]",
13
+ "<sop>",
14
+ "<eop>",
15
+ "<|system|>",
16
+ "<|user|>",
17
+ "<|assistant|>",
18
+ "<|observation|>",
19
+ "<|begin_of_image|>",
20
+ "<|end_of_image|>",
21
+ "<|begin_of_video|>",
22
+ "<|end_of_video|>",
23
+ "<thought>",
24
+ "</thought>",
25
+ "[AGENT:ARCHITECT]",
26
+ "[AGENT:CRITIC]",
27
+ "[AGENT:INNOVATOR]",
28
+ "[VOICE:CONTROL]"
29
+ ],
30
+ "image_size": 448,
31
+ "is_local": true,
32
+ "local_files_only": false,
33
+ "model_input_names": [
34
+ "input_ids",
35
+ "attention_mask"
36
+ ],
37
+ "model_max_length": 8192,
38
+ "pad_token": "<|endoftext|>",
39
+ "padding_side": "right",
40
+ "remove_space": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": "<|endoftext|>"
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a9d9e638a3272d95834e80ada6476d79b2f340c5de36a184447e88aa44de9c
3
+ size 5649