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>
253 lines
7.2 KiB
JSON
253 lines
7.2 KiB
JSON
{
|
|
"add_cross_attention": false,
|
|
"architectures": [
|
|
"Qwen3VLMoeForConditionalGeneration"
|
|
],
|
|
"bad_words_ids": null,
|
|
"begin_suppress_tokens": null,
|
|
"bos_token_id": null,
|
|
"chunk_size_feed_forward": 0,
|
|
"cross_attention_hidden_size": null,
|
|
"decoder_start_token_id": null,
|
|
"diversity_penalty": 0.0,
|
|
"do_sample": false,
|
|
"dtype": null,
|
|
"early_stopping": false,
|
|
"encoder_no_repeat_ngram_size": 0,
|
|
"eos_token_id": null,
|
|
"exponential_decay_length_penalty": null,
|
|
"finetuning_task": null,
|
|
"forced_bos_token_id": null,
|
|
"forced_eos_token_id": null,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"image_token_id": 151655,
|
|
"is_decoder": false,
|
|
"is_encoder_decoder": false,
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"length_penalty": 1.0,
|
|
"max_length": 20,
|
|
"min_length": 0,
|
|
"model_type": "qwen3_vl_moe",
|
|
"no_repeat_ngram_size": 0,
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_return_sequences": 1,
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": null,
|
|
"prefix": null,
|
|
"problem_type": null,
|
|
"pruned_heads": {},
|
|
"quantization": {
|
|
"group_size": 64,
|
|
"bits": 4,
|
|
"mode": "affine"
|
|
},
|
|
"quantization_config": {
|
|
"group_size": 64,
|
|
"bits": 4,
|
|
"mode": "affine"
|
|
},
|
|
"remove_invalid_values": false,
|
|
"repetition_penalty": 1.0,
|
|
"return_dict": true,
|
|
"return_dict_in_generate": false,
|
|
"sep_token_id": null,
|
|
"suppress_tokens": null,
|
|
"task_specific_params": null,
|
|
"temperature": 1.0,
|
|
"text_config": {
|
|
"vocab_size": 151936,
|
|
"max_position_embeddings": 262144,
|
|
"hidden_size": 2048,
|
|
"intermediate_size": 6144,
|
|
"num_hidden_layers": 48,
|
|
"num_attention_heads": 32,
|
|
"num_key_value_heads": 4,
|
|
"hidden_act": "silu",
|
|
"initializer_range": 0.02,
|
|
"rms_norm_eps": 1e-06,
|
|
"use_cache": true,
|
|
"rope_theta": 5000000,
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"rope_scaling": {
|
|
"mrope_interleaved": true,
|
|
"mrope_section": [
|
|
24,
|
|
20,
|
|
20
|
|
],
|
|
"rope_type": "default"
|
|
},
|
|
"head_dim": 128,
|
|
"decoder_sparse_step": 1,
|
|
"moe_intermediate_size": 768,
|
|
"num_experts_per_tok": 8,
|
|
"num_experts": 128,
|
|
"norm_topk_prob": true,
|
|
"router_aux_loss_coef": 0.001,
|
|
"mlp_only_layers": [],
|
|
"return_dict": true,
|
|
"output_hidden_states": false,
|
|
"torchscript": false,
|
|
"dtype": "bfloat16",
|
|
"pruned_heads": {},
|
|
"tie_word_embeddings": false,
|
|
"chunk_size_feed_forward": 0,
|
|
"is_encoder_decoder": false,
|
|
"is_decoder": false,
|
|
"cross_attention_hidden_size": null,
|
|
"add_cross_attention": false,
|
|
"tie_encoder_decoder": false,
|
|
"architectures": null,
|
|
"finetuning_task": null,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"task_specific_params": null,
|
|
"problem_type": null,
|
|
"tokenizer_class": null,
|
|
"prefix": null,
|
|
"bos_token_id": 151643,
|
|
"pad_token_id": null,
|
|
"eos_token_id": 151645,
|
|
"sep_token_id": null,
|
|
"decoder_start_token_id": null,
|
|
"max_length": 20,
|
|
"min_length": 0,
|
|
"do_sample": false,
|
|
"early_stopping": false,
|
|
"num_beams": 1,
|
|
"temperature": 1.0,
|
|
"top_k": 50,
|
|
"top_p": 1.0,
|
|
"typical_p": 1.0,
|
|
"repetition_penalty": 1.0,
|
|
"length_penalty": 1.0,
|
|
"no_repeat_ngram_size": 0,
|
|
"encoder_no_repeat_ngram_size": 0,
|
|
"bad_words_ids": null,
|
|
"num_return_sequences": 1,
|
|
"output_scores": false,
|
|
"return_dict_in_generate": false,
|
|
"forced_bos_token_id": null,
|
|
"forced_eos_token_id": null,
|
|
"remove_invalid_values": false,
|
|
"exponential_decay_length_penalty": null,
|
|
"suppress_tokens": null,
|
|
"begin_suppress_tokens": null,
|
|
"num_beam_groups": 1,
|
|
"diversity_penalty": 0.0,
|
|
"_name_or_path": "",
|
|
"model_type": "qwen3_vl_moe_text",
|
|
"tf_legacy_loss": false,
|
|
"use_bfloat16": false,
|
|
"output_attentions": false
|
|
},
|
|
"tf_legacy_loss": false,
|
|
"tie_encoder_decoder": false,
|
|
"tie_word_embeddings": false,
|
|
"tokenizer_class": null,
|
|
"top_k": 50,
|
|
"top_p": 1.0,
|
|
"torchscript": false,
|
|
"transformers_version": "4.57.0",
|
|
"typical_p": 1.0,
|
|
"use_bfloat16": false,
|
|
"video_token_id": 151656,
|
|
"vision_config": {
|
|
"return_dict": true,
|
|
"output_hidden_states": false,
|
|
"torchscript": false,
|
|
"dtype": null,
|
|
"pruned_heads": {},
|
|
"tie_word_embeddings": true,
|
|
"chunk_size_feed_forward": 0,
|
|
"is_encoder_decoder": false,
|
|
"is_decoder": false,
|
|
"cross_attention_hidden_size": null,
|
|
"add_cross_attention": false,
|
|
"tie_encoder_decoder": false,
|
|
"architectures": null,
|
|
"finetuning_task": null,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"task_specific_params": null,
|
|
"problem_type": null,
|
|
"tokenizer_class": null,
|
|
"prefix": null,
|
|
"bos_token_id": null,
|
|
"pad_token_id": null,
|
|
"eos_token_id": null,
|
|
"sep_token_id": null,
|
|
"decoder_start_token_id": null,
|
|
"max_length": 20,
|
|
"min_length": 0,
|
|
"do_sample": false,
|
|
"early_stopping": false,
|
|
"num_beams": 1,
|
|
"temperature": 1.0,
|
|
"top_k": 50,
|
|
"top_p": 1.0,
|
|
"typical_p": 1.0,
|
|
"repetition_penalty": 1.0,
|
|
"length_penalty": 1.0,
|
|
"no_repeat_ngram_size": 0,
|
|
"encoder_no_repeat_ngram_size": 0,
|
|
"bad_words_ids": null,
|
|
"num_return_sequences": 1,
|
|
"output_scores": false,
|
|
"return_dict_in_generate": false,
|
|
"forced_bos_token_id": null,
|
|
"forced_eos_token_id": null,
|
|
"remove_invalid_values": false,
|
|
"exponential_decay_length_penalty": null,
|
|
"suppress_tokens": null,
|
|
"begin_suppress_tokens": null,
|
|
"num_beam_groups": 1,
|
|
"diversity_penalty": 0.0,
|
|
"_name_or_path": "",
|
|
"model_type": "qwen3_vl_moe",
|
|
"tf_legacy_loss": false,
|
|
"use_bfloat16": false,
|
|
"depth": 27,
|
|
"hidden_size": 1152,
|
|
"hidden_act": "gelu_pytorch_tanh",
|
|
"intermediate_size": 4304,
|
|
"num_heads": 16,
|
|
"in_channels": 3,
|
|
"patch_size": 16,
|
|
"spatial_merge_size": 2,
|
|
"temporal_patch_size": 2,
|
|
"out_hidden_size": 2048,
|
|
"num_position_embeddings": 2304,
|
|
"initializer_range": 0.02,
|
|
"deepstack_visual_indexes": [
|
|
8,
|
|
16,
|
|
24
|
|
],
|
|
"output_attentions": false
|
|
},
|
|
"vision_end_token_id": 151653,
|
|
"vision_start_token_id": 151652
|
|
} |