Phase 4: OpenClaw agent setup + expanded model catalog
- 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>
This commit is contained in:
Aodhan Collins
243
homeai-llm/modelfiles/gemma-3-27b-it-qat-4bit/config.json
Normal file
243
homeai-llm/modelfiles/gemma-3-27b-it-qat-4bit/config.json
Normal file
@@ -0,0 +1,243 @@
|
||||
{
|
||||
"_attn_implementation_autoset": false,
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"Gemma3ForConditionalGeneration"
|
||||
],
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"boi_token_index": 255999,
|
||||
"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,
|
||||
"early_stopping": false,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"eoi_token_index": 256000,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"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_index": 262144,
|
||||
"initializer_range": 0.02,
|
||||
"is_decoder": false,
|
||||
"is_encoder_decoder": false,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"length_penalty": 1.0,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"mm_tokens_per_image": 256,
|
||||
"model_type": "gemma3",
|
||||
"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
|
||||
},
|
||||
"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": {
|
||||
"return_dict": true,
|
||||
"output_hidden_states": false,
|
||||
"output_attentions": false,
|
||||
"torchscript": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_bfloat16": false,
|
||||
"tf_legacy_loss": false,
|
||||
"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,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"num_beams": 1,
|
||||
"num_beam_groups": 1,
|
||||
"diversity_penalty": 0.0,
|
||||
"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,
|
||||
"architectures": null,
|
||||
"finetuning_task": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"tokenizer_class": null,
|
||||
"prefix": null,
|
||||
"bos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"eos_token_id": 1,
|
||||
"sep_token_id": null,
|
||||
"decoder_start_token_id": null,
|
||||
"task_specific_params": null,
|
||||
"problem_type": null,
|
||||
"_name_or_path": "",
|
||||
"_attn_implementation_autoset": false,
|
||||
"model_type": "gemma3_text",
|
||||
"vocab_size": 262208,
|
||||
"max_position_embeddings": 131072,
|
||||
"hidden_size": 5376,
|
||||
"intermediate_size": 21504,
|
||||
"num_hidden_layers": 62,
|
||||
"num_attention_heads": 32,
|
||||
"head_dim": 128,
|
||||
"num_key_value_heads": 16,
|
||||
"initializer_range": 0.02,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"use_cache": true,
|
||||
"rope_theta": 1000000,
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"query_pre_attn_scalar": 168,
|
||||
"sliding_window": 1024,
|
||||
"final_logit_softcapping": null,
|
||||
"attn_logit_softcapping": null,
|
||||
"cache_implementation": "hybrid",
|
||||
"rope_local_base_freq": 10000,
|
||||
"sliding_window_pattern": 6,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"rope_type": "linear"
|
||||
}
|
||||
},
|
||||
"tf_legacy_loss": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"tie_word_embeddings": true,
|
||||
"tokenizer_class": null,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.51.3",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": false,
|
||||
"vision_config": {
|
||||
"return_dict": true,
|
||||
"output_hidden_states": false,
|
||||
"output_attentions": false,
|
||||
"torchscript": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_bfloat16": false,
|
||||
"tf_legacy_loss": false,
|
||||
"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,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"num_beams": 1,
|
||||
"num_beam_groups": 1,
|
||||
"diversity_penalty": 0.0,
|
||||
"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,
|
||||
"architectures": null,
|
||||
"finetuning_task": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"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,
|
||||
"task_specific_params": null,
|
||||
"problem_type": null,
|
||||
"_name_or_path": "",
|
||||
"_attn_implementation_autoset": false,
|
||||
"model_type": "siglip_vision_model",
|
||||
"vision_use_head": false,
|
||||
"hidden_size": 1152,
|
||||
"intermediate_size": 4304,
|
||||
"num_hidden_layers": 27,
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"patch_size": 14,
|
||||
"image_size": 896,
|
||||
"attention_dropout": 0.0,
|
||||
"layer_norm_eps": 1e-06,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"skip_vision": true
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user