silviapasuarez commited on
Commit
8bebb60
·
verified ·
1 Parent(s): 51f08a2

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: carvalho-nos/CarvalhoChat_v4
3
+ library_name: peft
4
+ model_name: rq1_carvalhochat_gl_gec_lora
5
+ tags:
6
+ - base_model:adapter:carvalho-nos/CarvalhoChat_v4
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ licence: license
13
+ pipeline_tag: text-generation
14
+ ---
15
+
16
+ # Model Card for rq1_carvalhochat_gl_gec_lora
17
+
18
+ This model is a fine-tuned version of [carvalho-nos/CarvalhoChat_v4](https://huggingface.co/carvalho-nos/CarvalhoChat_v4).
19
+ It has been trained using [TRL](https://github.com/huggingface/trl).
20
+
21
+ ## Quick start
22
+
23
+ ```python
24
+ from transformers import pipeline
25
+
26
+ 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?"
27
+ generator = pipeline("text-generation", model="None", device="cuda")
28
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
29
+ print(output["generated_text"])
30
+ ```
31
+
32
+ ## Training procedure
33
+
34
+
35
+
36
+
37
+ This model was trained with SFT.
38
+
39
+ ### Framework versions
40
+
41
+ - PEFT 0.18.1
42
+ - TRL: 0.24.0
43
+ - Transformers: 5.5.0
44
+ - Pytorch: 2.10.0
45
+ - Datasets: 4.3.0
46
+ - Tokenizers: 0.22.2
47
+
48
+ ## Citations
49
+
50
+
51
+
52
+ Cite TRL as:
53
+
54
+ ```bibtex
55
+ @misc{vonwerra2022trl,
56
+ title = {{TRL: Transformer Reinforcement Learning}},
57
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
58
+ year = 2020,
59
+ journal = {GitHub repository},
60
+ publisher = {GitHub},
61
+ howpublished = {\url{https://github.com/huggingface/trl}}
62
+ }
63
+ ```
adapter_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "carvalho-nos/CarvalhoChat_v4",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": true,
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": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 16,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "up_proj",
33
+ "q_proj",
34
+ "k_proj",
35
+ "o_proj",
36
+ "v_proj",
37
+ "gate_proj",
38
+ "down_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": [
43
+ 128256,
44
+ 128257
45
+ ],
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false
49
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ca9bd2e6fe2e1af5211a2f4b18d938e2e7e1bec08f794ca3594f0ca0c4d69b
3
+ size 2269244472
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ca1468986e7f67ce918d22057748a8ca8d6946e019dfd650de90120dbfeb28
3
+ size 17210396
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|eot_id|>",
6
+ "extra_special_tokens": [
7
+ "<|task:gec|>",
8
+ "<|lang:gl|>"
9
+ ],
10
+ "from_slow": true,
11
+ "is_local": false,
12
+ "legacy": false,
13
+ "model_input_names": [
14
+ "input_ids",
15
+ "attention_mask"
16
+ ],
17
+ "model_max_length": 131072,
18
+ "pad_token": "<|end_of_text|>",
19
+ "padding_side": "right",
20
+ "tokenizer_class": "TokenizersBackend",
21
+ "use_fast": true
22
+ }