Any-to-Any
Transformers
Safetensors
English
qwen2
text-generation
qwen
lora
router
multi-agent
orchestration
gradio
multimodal
text
image
video
audio
Eval Results (legacy)
text-generation-inference
Instructions to use Questionmarkboy/frankenstein-3-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Questionmarkboy/frankenstein-3-0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Questionmarkboy/frankenstein-3-0") model = AutoModelForCausalLM.from_pretrained("Questionmarkboy/frankenstein-3-0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
🔧 Replace NF4 with clean FP16 weights (matches Frankenstein-2.0 format)
Browse files- config.json +3 -18
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
-
"dtype": "
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 1536,
|
|
@@ -47,21 +47,6 @@
|
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 2,
|
| 49 |
"pad_token_id": null,
|
| 50 |
-
"quantization_config": {
|
| 51 |
-
"_load_in_4bit": true,
|
| 52 |
-
"_load_in_8bit": false,
|
| 53 |
-
"bnb_4bit_compute_dtype": "float16",
|
| 54 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 55 |
-
"bnb_4bit_quant_type": "nf4",
|
| 56 |
-
"bnb_4bit_use_double_quant": true,
|
| 57 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 58 |
-
"llm_int8_has_fp16_weight": false,
|
| 59 |
-
"llm_int8_skip_modules": null,
|
| 60 |
-
"llm_int8_threshold": 6.0,
|
| 61 |
-
"load_in_4bit": true,
|
| 62 |
-
"load_in_8bit": false,
|
| 63 |
-
"quant_method": "bitsandbytes"
|
| 64 |
-
},
|
| 65 |
"rms_norm_eps": 1e-06,
|
| 66 |
"rope_parameters": {
|
| 67 |
"rope_theta": 1000000.0,
|
|
@@ -69,8 +54,8 @@
|
|
| 69 |
},
|
| 70 |
"sliding_window": null,
|
| 71 |
"tie_word_embeddings": true,
|
| 72 |
-
"transformers_version": "5.
|
| 73 |
-
"use_cache":
|
| 74 |
"use_sliding_window": false,
|
| 75 |
"vocab_size": 151936
|
| 76 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float16",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 1536,
|
|
|
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 2,
|
| 49 |
"pad_token_id": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"rms_norm_eps": 1e-06,
|
| 51 |
"rope_parameters": {
|
| 52 |
"rope_theta": 1000000.0,
|
|
|
|
| 54 |
},
|
| 55 |
"sliding_window": null,
|
| 56 |
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.0.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
"use_sliding_window": false,
|
| 60 |
"vocab_size": 151936
|
| 61 |
}
|
generation_config.json
CHANGED
|
@@ -10,5 +10,5 @@
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
-
"transformers_version": "5.
|
| 14 |
}
|
|
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.0.0"
|
| 14 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15cc9c956950dc0a4a13af1907d3c9cb431816128c9a01aea2e7a8f91bca721d
|
| 3 |
+
size 1777271608
|