Hugging Face's logo

OvercastLab
/
Quark-50m

Text Generation
PyTorch
Safetensors
English
code
llama
smol
pretraining
instruct
50M
causal-lm
gqa
swiglu
rmsnorm
conversational
Model card Files
xet
 Community
ThingsAI commited on
Commit
fac5c1e
·
verified ·
1 Parent(s): 55fa07a

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .ipynb_checkpoints/chat_template-checkpoint.jinja +4 -0
  2. .ipynb_checkpoints/config-checkpoint.json +14 -0
  3. .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
  4. .ipynb_checkpoints/tokenizer_config-checkpoint.json +33 -0
  5. chat_template.jinja +4 -0
  6. config.json +14 -0
  7. pytorch_model.bin +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +33 -0
.ipynb_checkpoints/chat_template-checkpoint.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 49152,
3
+ "d_model": 384,
4
+ "n_heads": 6,
5
+ "n_kv_heads": 2,
6
+ "n_layers": 24,
7
+ "d_ff": 1024,
8
+ "head_dim": 64,
9
+ "max_seq_len": 2048,
10
+ "rope_theta": 10000.0,
11
+ "rms_eps": 1e-05,
12
+ "qkv_bias": true,
13
+ "dropout": 0.0
14
+ }
.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|im_start|>",
11
+ "<|im_end|>",
12
+ "<repo_name>",
13
+ "<reponame>",
14
+ "<file_sep>",
15
+ "<filename>",
16
+ "<gh_stars>",
17
+ "<issue_start>",
18
+ "<issue_comment>",
19
+ "<issue_closed>",
20
+ "<jupyter_start>",
21
+ "<jupyter_text>",
22
+ "<jupyter_code>",
23
+ "<jupyter_output>",
24
+ "<jupyter_script>",
25
+ "<empty_output>"
26
+ ],
27
+ "is_local": false,
28
+ "model_max_length": 1000000000000000019884624838656,
29
+ "pad_token": null,
30
+ "tokenizer_class": "GPT2Tokenizer",
31
+ "unk_token": "<|endoftext|>",
32
+ "vocab_size": 49152
33
+ }
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 49152,
3
+ "d_model": 384,
4
+ "n_heads": 6,
5
+ "n_kv_heads": 2,
6
+ "n_layers": 24,
7
+ "d_ff": 1024,
8
+ "head_dim": 64,
9
+ "max_seq_len": 2048,
10
+ "rope_theta": 10000.0,
11
+ "rms_eps": 1e-05,
12
+ "qkv_bias": true,
13
+ "dropout": 0.0
14
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f123e7c62d0615acb63f6e02c1fef39ad165fedd47a48f734bbc58eb23860c8e
3
+ size 226733547
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|im_start|>",
11
+ "<|im_end|>",
12
+ "<repo_name>",
13
+ "<reponame>",
14
+ "<file_sep>",
15
+ "<filename>",
16
+ "<gh_stars>",
17
+ "<issue_start>",
18
+ "<issue_comment>",
19
+ "<issue_closed>",
20
+ "<jupyter_start>",
21
+ "<jupyter_text>",
22
+ "<jupyter_code>",
23
+ "<jupyter_output>",
24
+ "<jupyter_script>",
25
+ "<empty_output>"
26
+ ],
27
+ "is_local": false,
28
+ "model_max_length": 1000000000000000019884624838656,
29
+ "pad_token": null,
30
+ "tokenizer_class": "GPT2Tokenizer",
31
+ "unk_token": "<|endoftext|>",
32
+ "vocab_size": 49152
33
+ }