Instructions to use EigenLabs/Qwen3.8-27B-MTP-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use EigenLabs/Qwen3.8-27B-MTP-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.8-27B-MTP-bf16 EigenLabs/Qwen3.8-27B-MTP-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add model.safetensors.index.json: the loader requires it in the head tree
Browse files- model.safetensors.index.json +22 -0
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 849398784
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"fc.weight": "model.safetensors",
|
| 7 |
+
"layers.0.input_layernorm.weight": "model.safetensors",
|
| 8 |
+
"layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 9 |
+
"layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 10 |
+
"layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 11 |
+
"layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 12 |
+
"layers.0.self_attn.k_norm.weight": "model.safetensors",
|
| 13 |
+
"layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 14 |
+
"layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 15 |
+
"layers.0.self_attn.q_norm.weight": "model.safetensors",
|
| 16 |
+
"layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 17 |
+
"layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 18 |
+
"norm.weight": "model.safetensors",
|
| 19 |
+
"pre_fc_norm_embedding.weight": "model.safetensors",
|
| 20 |
+
"pre_fc_norm_hidden.weight": "model.safetensors"
|
| 21 |
+
}
|
| 22 |
+
}
|