Upload model
Browse files- config.json +47 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"MultiTaskModel"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"base_model_name": "HuggingFaceTB/SmolLM2-135M-Instruct",
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"debug": false,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"head_dim": 64,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 576,
|
15 |
+
"initializer_range": 0.041666666666666664,
|
16 |
+
"intermediate_size": 1536,
|
17 |
+
"is_llama_config": true,
|
18 |
+
"max_position_embeddings": 8192,
|
19 |
+
"mlp_bias": false,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 9,
|
22 |
+
"num_choices": 5,
|
23 |
+
"num_hidden_layers": 30,
|
24 |
+
"num_key_value_heads": 3,
|
25 |
+
"output_hidden_states": true,
|
26 |
+
"pad_token_id": 2,
|
27 |
+
"pretraining_tp": 1,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_interleaved": false,
|
30 |
+
"rope_scaling": null,
|
31 |
+
"rope_theta": 100000,
|
32 |
+
"sequence_lengths": {
|
33 |
+
"formula": 128,
|
34 |
+
"prompt": 256,
|
35 |
+
"rationale": 384
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers.js_config": {
|
39 |
+
"kv_cache_dtype": {
|
40 |
+
"fp16": "float16",
|
41 |
+
"q4f16": "float16"
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"transformers_version": "4.47.1",
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 49152
|
47 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fbd29b18a69cf739904bd89d70325a13dfa0416c359d9143f3a6a8f66d69495
|
3 |
+
size 1784208092
|