Upload folder using huggingface_hub
Browse files- config.json +26 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"hidden_size": 32,
|
| 6 |
+
"intermediate_size": 64,
|
| 7 |
+
"num_attention_heads": 4,
|
| 8 |
+
"num_hidden_layers": 2,
|
| 9 |
+
"num_key_value_heads": 2,
|
| 10 |
+
"vocab_size": 1024,
|
| 11 |
+
"head_dim": 8,
|
| 12 |
+
"rms_norm_eps": 1e-06,
|
| 13 |
+
"rope_theta": 1000000.0,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"torch_dtype": "float8_e4m3fn",
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"use_qk_norm": true,
|
| 18 |
+
"tie_word_embeddings": true,
|
| 19 |
+
"quantization_config": {
|
| 20 |
+
"quant_method": "fp8",
|
| 21 |
+
"weight_block_size": [
|
| 22 |
+
128,
|
| 23 |
+
128
|
| 24 |
+
]
|
| 25 |
+
}
|
| 26 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78975f10166868ed9dee432f6fb65b7f25e2dea733566023d1f117399a5fba41
|
| 3 |
+
size 154360
|