Add files using upload-large-folder tool
Browse files- config.json +53 -1
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -17,13 +17,65 @@
|
|
| 17 |
"num_hidden_layers": 64,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"pad_token_id": 151654,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 1000000.0,
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"unsloth_fixed": true,
|
| 28 |
"use_cache": true,
|
| 29 |
"use_sliding_window": false,
|
|
|
|
| 17 |
"num_hidden_layers": 64,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"pad_token_id": 151654,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"_load_in_4bit": true,
|
| 22 |
+
"_load_in_8bit": false,
|
| 23 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 24 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 25 |
+
"bnb_4bit_quant_type": "nf4",
|
| 26 |
+
"bnb_4bit_use_double_quant": true,
|
| 27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 28 |
+
"llm_int8_has_fp16_weight": false,
|
| 29 |
+
"llm_int8_skip_modules": [
|
| 30 |
+
"lm_head",
|
| 31 |
+
"multi_modal_projector",
|
| 32 |
+
"merger",
|
| 33 |
+
"modality_projection",
|
| 34 |
+
"model.layers.0.self_attn",
|
| 35 |
+
"model.layers.0.mlp",
|
| 36 |
+
"model.layers.1.mlp",
|
| 37 |
+
"model.layers.2.self_attn",
|
| 38 |
+
"model.layers.3.self_attn",
|
| 39 |
+
"model.layers.3.mlp",
|
| 40 |
+
"model.layers.4.self_attn",
|
| 41 |
+
"model.layers.4.mlp",
|
| 42 |
+
"model.layers.5.mlp",
|
| 43 |
+
"model.layers.6.mlp",
|
| 44 |
+
"model.layers.38.mlp",
|
| 45 |
+
"model.layers.39.mlp",
|
| 46 |
+
"model.layers.43.mlp",
|
| 47 |
+
"model.layers.47.mlp",
|
| 48 |
+
"model.layers.48.mlp",
|
| 49 |
+
"model.layers.49.mlp",
|
| 50 |
+
"model.layers.50.mlp",
|
| 51 |
+
"model.layers.51.mlp",
|
| 52 |
+
"model.layers.52.mlp",
|
| 53 |
+
"model.layers.53.mlp",
|
| 54 |
+
"model.layers.54.mlp",
|
| 55 |
+
"model.layers.55.mlp",
|
| 56 |
+
"model.layers.56.mlp",
|
| 57 |
+
"model.layers.57.mlp",
|
| 58 |
+
"model.layers.58.mlp",
|
| 59 |
+
"model.layers.59.mlp",
|
| 60 |
+
"model.layers.60.mlp",
|
| 61 |
+
"model.layers.61.mlp",
|
| 62 |
+
"model.layers.62.mlp",
|
| 63 |
+
"model.layers.39.self_attn.o_proj",
|
| 64 |
+
"model.layers.40.self_attn.o_proj",
|
| 65 |
+
"model.layers.43.self_attn.o_proj"
|
| 66 |
+
],
|
| 67 |
+
"llm_int8_threshold": 6.0,
|
| 68 |
+
"load_in_4bit": true,
|
| 69 |
+
"load_in_8bit": false,
|
| 70 |
+
"quant_method": "bitsandbytes"
|
| 71 |
+
},
|
| 72 |
"rms_norm_eps": 1e-05,
|
| 73 |
"rope_scaling": null,
|
| 74 |
"rope_theta": 1000000.0,
|
| 75 |
"sliding_window": null,
|
| 76 |
"tie_word_embeddings": false,
|
| 77 |
"torch_dtype": "bfloat16",
|
| 78 |
+
"transformers_version": "4.49.0.dev0",
|
| 79 |
"unsloth_fixed": true,
|
| 80 |
"use_cache": true,
|
| 81 |
"use_sliding_window": false,
|
generation_config.json
CHANGED
|
@@ -7,5 +7,5 @@
|
|
| 7 |
"pad_token_id": 151654,
|
| 8 |
"temperature": 0.6,
|
| 9 |
"top_p": 0.95,
|
| 10 |
-
"transformers_version": "4.
|
| 11 |
}
|
|
|
|
| 7 |
"pad_token_id": 151654,
|
| 8 |
"temperature": 0.6,
|
| 9 |
"top_p": 0.95,
|
| 10 |
+
"transformers_version": "4.49.0.dev0"
|
| 11 |
}
|