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>
55 lines
1.3 KiB
JSON
55 lines
1.3 KiB
JSON
{
|
|
"architectures": [
|
|
"Glm4MoeLiteForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": [
|
|
154820,
|
|
154827,
|
|
154829
|
|
],
|
|
"first_k_dense_replace": 1,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"intermediate_size": 10240,
|
|
"kv_lora_rank": 512,
|
|
"max_position_embeddings": 202752,
|
|
"model_type": "glm4_moe_lite",
|
|
"moe_intermediate_size": 1536,
|
|
"n_group": 1,
|
|
"n_routed_experts": 64,
|
|
"n_shared_experts": 1,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 20,
|
|
"num_experts_per_tok": 4,
|
|
"num_hidden_layers": 47,
|
|
"num_key_value_heads": 20,
|
|
"num_nextn_predict_layers": 1,
|
|
"pad_token_id": 154820,
|
|
"partial_rotary_factor": 1.0,
|
|
"q_lora_rank": 768,
|
|
"qk_nope_head_dim": 192,
|
|
"qk_rope_head_dim": 64,
|
|
"quantization": {
|
|
"group_size": 64,
|
|
"bits": 8,
|
|
"mode": "affine"
|
|
},
|
|
"quantization_config": {
|
|
"group_size": 64,
|
|
"bits": 8,
|
|
"mode": "affine"
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"routed_scaling_factor": 1.8,
|
|
"tie_word_embeddings": false,
|
|
"topk_group": 1,
|
|
"topk_method": "noaux_tc",
|
|
"transformers_version": "5.0.0rc0",
|
|
"v_head_dim": 256,
|
|
"vocab_size": 154880
|
|
} |