Upload 0.6B LittleLearner weights (patched: top-level rope_theta, max_new_tokens=512, eos)
Browse files- config.json +56 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 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": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention"
|
| 36 |
+
],
|
| 37 |
+
"max_position_embeddings": 4096,
|
| 38 |
+
"max_window_layers": 28,
|
| 39 |
+
"model_type": "qwen3",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_hidden_layers": 20,
|
| 42 |
+
"num_key_value_heads": 6,
|
| 43 |
+
"pad_token_id": 1,
|
| 44 |
+
"rms_norm_eps": 1e-06,
|
| 45 |
+
"rope_parameters": {
|
| 46 |
+
"rope_theta": 1000000.0,
|
| 47 |
+
"rope_type": "default"
|
| 48 |
+
},
|
| 49 |
+
"sliding_window": null,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"transformers_version": "5.2.0",
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"use_sliding_window": false,
|
| 54 |
+
"vocab_size": 64000,
|
| 55 |
+
"rope_theta": 1000000.0
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1,
|
| 8 |
+
"transformers_version": "5.2.0",
|
| 9 |
+
"use_cache": true,
|
| 10 |
+
"max_new_tokens": 512
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c98e5a755e5267fd3019dc3c5d8b3afca7087e828a4971757b216ea406132066
|
| 3 |
+
size 1234859584
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<|endoftext|>",
|
| 9 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 10 |
+
"unk_token": "<|endoftext|>"
|
| 11 |
+
}
|