c4f3dbed77
- Add OpenClaw launchd plist (gateway on port 8080) - Update Llama-3.3-70B Modelfile: fix FROM path, add tool-calling TEMPLATE, set num_ctx 32768 (fits 70B in 64GB with safe headroom) - Update Codestral-22B and Qwen3-32B Modelfiles - Add Modelfiles for all models in ~/Models/LLM and ~/Models/MLX: EVA-LLaMA-3.33-70B, Midnight-Miqu-70B, QwQ-32B, Qwen3.5-35B, Qwen3-Coder-30B, Qwen3-Coder-Next, Qwen3-VL-30B, GLM-4.6V-Flash, DeepSeek-R1-8B, gemma-3-27b, and MLX variants - Add import-local-models.sh helper script Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
47 lines
1.2 KiB
JSON
47 lines
1.2 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3MoeForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"decoder_sparse_step": 1,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 5472,
|
|
"max_position_embeddings": 262144,
|
|
"max_window_layers": 28,
|
|
"mlp_only_layers": [],
|
|
"model_type": "qwen3_moe",
|
|
"moe_intermediate_size": 768,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 32,
|
|
"num_experts": 128,
|
|
"num_experts_per_tok": 8,
|
|
"num_hidden_layers": 48,
|
|
"num_key_value_heads": 4,
|
|
"output_router_logits": false,
|
|
"qkv_bias": false,
|
|
"quantization": {
|
|
"group_size": 64,
|
|
"bits": 8
|
|
},
|
|
"quantization_config": {
|
|
"group_size": 64,
|
|
"bits": 8
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000,
|
|
"router_aux_loss_coef": 0.0,
|
|
"shared_expert_intermediate_size": 0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.3",
|
|
"use_cache": true,
|
|
"use_qk_norm": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
} |