Upload 9 files
Browse files- config.json +8 -8
- generation_config.json +1 -1
- model.safetensors +2 -2
- tokenizer.json +2 -14
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "HuggingFaceTB/SmolLM2-
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -9,16 +9,16 @@
|
|
9 |
"eos_token_id": 2,
|
10 |
"head_dim": 64,
|
11 |
"hidden_act": "silu",
|
12 |
-
"hidden_size":
|
13 |
-
"initializer_range": 0.
|
14 |
-
"intermediate_size":
|
15 |
"is_llama_config": true,
|
16 |
"max_position_embeddings": 8192,
|
17 |
"mlp_bias": false,
|
18 |
"model_type": "llama",
|
19 |
-
"num_attention_heads":
|
20 |
-
"num_hidden_layers":
|
21 |
-
"num_key_value_heads":
|
22 |
"pad_token_id": 2,
|
23 |
"pretraining_tp": 1,
|
24 |
"rms_norm_eps": 1e-05,
|
@@ -33,7 +33,7 @@
|
|
33 |
"q4f16": "float16"
|
34 |
}
|
35 |
},
|
36 |
-
"transformers_version": "4.48.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 49152
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
9 |
"eos_token_id": 2,
|
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": 2,
|
23 |
"pretraining_tp": 1,
|
24 |
"rms_norm_eps": 1e-05,
|
|
|
33 |
"q4f16": "float16"
|
34 |
}
|
35 |
},
|
36 |
+
"transformers_version": "4.48.3",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 49152
|
39 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 2,
|
6 |
-
"transformers_version": "4.48.
|
7 |
}
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.48.3"
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6867677f24aa92ca496a27336e1936dcc2e334354806a69bfee7d3c960748d0f
|
3 |
+
size 723674912
|
tokenizer.json
CHANGED
@@ -1,19 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 8192,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": "BatchLongest",
|
11 |
-
"direction": "Left",
|
12 |
-
"pad_to_multiple_of": null,
|
13 |
-
"pad_id": 2,
|
14 |
-
"pad_type_id": 0,
|
15 |
-
"pad_token": "<|im_end|>"
|
16 |
-
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8288702bf1db05beb5371c5042435c0caec211ef529e54f10857324941950ccf
|
3 |
size 6200
|