meihant commited on
Commit
1c6b9f2
·
verified ·
1 Parent(s): d1e74f9

Add models/FCP-SmolLM2-360M-20B artifacts 0-5

Browse files
models/FCP-SmolLM2-360M-20B/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}<|im_start|>system
2
+ {{ message['content'] }}<|im_end|>
3
+ {% elif message['role'] == 'user' %}<|im_start|>user
4
+ {{ message['content'] }}<|im_end|>
5
+ {% elif message['role'] == 'assistant' %}<|im_start|>assistant
6
+ {{ message['content'] }}<|im_end|>
7
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
8
+ {% endif %}
models/FCP-SmolLM2-360M-20B/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 960,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 15,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 5,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_parameters": {
27
+ "rope_theta": 100000,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.6.2",
32
+ "use_cache": true,
33
+ "vocab_size": 49158
34
+ }
models/FCP-SmolLM2-360M-20B/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.6.2",
9
+ "use_cache": true
10
+ }
models/FCP-SmolLM2-360M-20B/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940af68d592c5bf2a920c259c808c17943127800cb4a56ca8326f52a64dfa551
3
+ size 723686432
models/FCP-SmolLM2-360M-20B/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/FCP-SmolLM2-360M-20B/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": true,
9
+ "local_files_only": true,
10
+ "model_max_length": 8192,
11
+ "pad_token": "<|endoftext|>",
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|endoftext|>",
14
+ "vocab_size": 49152
15
+ }