Text Generation
Transformers
Safetensors
English
llama
foundation-sec
heretic
gptq
int4
w4a16
g128
gptqmodel
vllm
local-llm
conversational
text-generation-inference
4-bit precision
Instructions to use GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128") model = AutoModelForCausalLM.from_pretrained("GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128
- SGLang
How to use GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128 with Docker Model Runner:
docker model run hf.co/GreyArea128/Foundation-Sec-8B-Instruct-Heretic-GPTQ-W4A16-G128
File size: 10,367 Bytes
53e1f9d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | layer,module,loss,samples,damp,time
0,self_attn.v_proj,0.0000001293,0.05000,2.699
0,self_attn.k_proj,0.0000034216,0.05000,2.640
0,self_attn.q_proj,0.0000058695,0.05000,2.574
0,self_attn.o_proj,0.0000000029,0.05000,0.883
0,mlp.gate_proj,0.0000034440,0.05000,1.695
0,mlp.up_proj,0.0000027864,0.05000,1.709
0,mlp.down_proj,0.0000000167,0.05000,4.008
1,self_attn.q_proj,0.0000062227,0.05000,2.661
1,self_attn.v_proj,0.0000002703,0.05000,2.670
1,self_attn.k_proj,0.0000035657,0.05000,2.672
1,self_attn.o_proj,0.0000000088,0.05000,0.936
1,mlp.gate_proj,0.0000065917,0.05000,1.697
1,mlp.up_proj,0.0000055907,0.05000,1.739
1,mlp.down_proj,0.0000009924,0.05000,4.097
2,self_attn.v_proj,0.0000010494,0.05000,2.543
2,self_attn.q_proj,0.0000310937,0.05000,2.566
2,self_attn.k_proj,0.0000192025,0.05000,2.569
2,self_attn.o_proj,0.0000000087,0.05000,1.006
2,mlp.up_proj,0.0000096578,0.05000,1.917
2,mlp.gate_proj,0.0000121229,0.05000,1.935
2,mlp.down_proj,0.0000000720,0.05000,6.555
3,self_attn.v_proj,0.0000013723,0.05000,5.227
3,self_attn.q_proj,0.0000261935,0.05000,5.228
3,self_attn.k_proj,0.0000145005,0.05000,5.239
3,self_attn.o_proj,0.0000000239,0.05000,1.590
3,mlp.up_proj,0.0000131802,0.05000,3.162
3,mlp.gate_proj,0.0000189446,0.05000,3.305
3,mlp.down_proj,0.0000001305,0.05000,3.895
4,self_attn.v_proj,0.0000014489,0.05000,2.288
4,self_attn.q_proj,0.0000246001,0.05000,2.312
4,self_attn.k_proj,0.0000142096,0.05000,2.320
4,self_attn.o_proj,0.0000000422,0.05000,0.849
4,mlp.up_proj,0.0000169536,0.05000,1.698
4,mlp.gate_proj,0.0000274760,0.05000,1.708
4,mlp.down_proj,0.0000002303,0.05000,3.935
5,self_attn.q_proj,0.0000365864,0.05000,2.390
5,self_attn.v_proj,0.0000015053,0.05000,2.405
5,self_attn.k_proj,0.0000224410,0.05000,2.407
5,self_attn.o_proj,0.0000000619,0.05000,0.867
5,mlp.gate_proj,0.0000324257,0.05000,1.702
5,mlp.up_proj,0.0000201914,0.05000,1.714
5,mlp.down_proj,0.0000003240,0.05000,3.794
6,self_attn.q_proj,0.0000319925,0.05000,2.248
6,self_attn.v_proj,0.0000015913,0.05000,2.268
6,self_attn.k_proj,0.0000177453,0.05000,2.275
6,self_attn.o_proj,0.0000001058,0.05000,0.885
6,mlp.up_proj,0.0000223163,0.05000,1.639
6,mlp.gate_proj,0.0000363407,0.05000,1.644
6,mlp.down_proj,0.0000004011,0.05000,3.625
7,self_attn.v_proj,0.0000015963,0.05000,2.295
7,self_attn.k_proj,0.0000179320,0.05000,2.310
7,self_attn.q_proj,0.0000302215,0.05000,2.331
7,self_attn.o_proj,0.0000001488,0.05000,0.803
7,mlp.up_proj,0.0000243476,0.05000,1.695
7,mlp.gate_proj,0.0000369044,0.05000,1.700
7,mlp.down_proj,0.0000004649,0.05000,3.659
8,self_attn.q_proj,0.0000387533,0.05000,2.232
8,self_attn.v_proj,0.0000021729,0.05000,2.274
8,self_attn.k_proj,0.0000237366,0.05000,2.283
8,self_attn.o_proj,0.0000001954,0.05000,0.889
8,mlp.up_proj,0.0000254183,0.05000,1.643
8,mlp.gate_proj,0.0000391541,0.05000,1.677
8,mlp.down_proj,0.0000005009,0.05000,3.635
9,self_attn.v_proj,0.0000028860,0.05000,2.328
9,self_attn.q_proj,0.0000367279,0.05000,2.359
9,self_attn.k_proj,0.0000216969,0.05000,2.359
9,self_attn.o_proj,0.0000002131,0.05000,0.850
9,mlp.gate_proj,0.0000417060,0.05000,1.691
9,mlp.up_proj,0.0000269056,0.05000,1.699
9,mlp.down_proj,0.0000005429,0.05000,3.753
10,self_attn.v_proj,0.0000024547,0.05000,2.240
10,self_attn.q_proj,0.0000456267,0.05000,2.258
10,self_attn.k_proj,0.0000285390,0.05000,2.264
10,self_attn.o_proj,0.0000002068,0.05000,0.802
10,mlp.up_proj,0.0000275166,0.05000,1.659
10,mlp.gate_proj,0.0000398533,0.05000,1.680
10,mlp.down_proj,0.0000005768,0.05000,3.866
11,self_attn.v_proj,0.0000023226,0.05000,2.352
11,self_attn.q_proj,0.0000380008,0.05000,2.357
11,self_attn.k_proj,0.0000243678,0.05000,2.370
11,self_attn.o_proj,0.0000002381,0.05000,0.805
11,mlp.up_proj,0.0000293335,0.05000,1.645
11,mlp.gate_proj,0.0000413307,0.05000,1.658
11,mlp.down_proj,0.0000006175,0.05000,3.793
12,self_attn.q_proj,0.0000328211,0.05000,2.284
12,self_attn.k_proj,0.0000184791,0.05000,2.293
12,self_attn.v_proj,0.0000026819,0.05000,2.303
12,self_attn.o_proj,0.0000003211,0.05000,0.805
12,mlp.gate_proj,0.0000412847,0.05000,1.663
12,mlp.up_proj,0.0000307810,0.05000,1.664
12,mlp.down_proj,0.0000006995,0.05000,3.746
13,self_attn.q_proj,0.0000433177,0.05000,2.273
13,self_attn.k_proj,0.0000284220,0.05000,2.292
13,self_attn.v_proj,0.0000029941,0.05000,2.293
13,self_attn.o_proj,0.0000003719,0.05000,0.810
13,mlp.up_proj,0.0000325686,0.05000,1.705
13,mlp.gate_proj,0.0000440303,0.05000,1.721
13,mlp.down_proj,0.0000007959,0.05000,3.859
14,self_attn.v_proj,0.0000032744,0.05000,2.318
14,self_attn.k_proj,0.0000317419,0.05000,2.336
14,self_attn.q_proj,0.0000462631,0.05000,2.359
14,self_attn.o_proj,0.0000003987,0.05000,0.888
14,mlp.up_proj,0.0000361250,0.05000,1.643
14,mlp.gate_proj,0.0000520649,0.05000,1.659
14,mlp.down_proj,0.0000009885,0.05000,3.758
15,self_attn.v_proj,0.0000039160,0.05000,2.234
15,self_attn.k_proj,0.0000272244,0.05000,2.257
15,self_attn.q_proj,0.0000517732,0.05000,2.270
15,self_attn.o_proj,0.0000004123,0.05000,0.877
15,mlp.up_proj,0.0000379163,0.05000,1.680
15,mlp.gate_proj,0.0000572937,0.05000,1.684
15,mlp.down_proj,0.0000012022,0.05000,3.695
16,self_attn.q_proj,0.0000492487,0.05000,2.348
16,self_attn.k_proj,0.0000282681,0.05000,2.355
16,self_attn.v_proj,0.0000036686,0.05000,2.370
16,self_attn.o_proj,0.0000003293,0.05000,0.817
16,mlp.gate_proj,0.0000638213,0.05000,1.610
16,mlp.up_proj,0.0000403417,0.05000,1.621
16,mlp.down_proj,0.0000012991,0.05000,3.875
17,self_attn.v_proj,0.0000040237,0.05000,2.299
17,self_attn.q_proj,0.0000506742,0.05000,2.307
17,self_attn.k_proj,0.0000302613,0.05000,2.319
17,self_attn.o_proj,0.0000002926,0.05000,0.923
17,mlp.up_proj,0.0000425239,0.05000,1.672
17,mlp.gate_proj,0.0000688734,0.05000,1.706
17,mlp.down_proj,0.0000015061,0.05000,3.730
18,self_attn.k_proj,0.0000336948,0.05000,2.365
18,self_attn.v_proj,0.0000041950,0.05000,2.369
18,self_attn.q_proj,0.0000520978,0.05000,2.374
18,self_attn.o_proj,0.0000002177,0.05000,0.841
18,mlp.gate_proj,0.0000726533,0.05000,1.599
18,mlp.up_proj,0.0000446347,0.05000,1.607
18,mlp.down_proj,0.0000014952,0.05000,3.878
19,self_attn.k_proj,0.0000309511,0.05000,2.304
19,self_attn.q_proj,0.0000532915,0.05000,2.309
19,self_attn.v_proj,0.0000044172,0.05000,2.310
19,self_attn.o_proj,0.0000001848,0.05000,0.901
19,mlp.up_proj,0.0000470823,0.05000,1.735
19,mlp.gate_proj,0.0000780385,0.05000,1.746
19,mlp.down_proj,0.0000016081,0.05000,3.694
20,self_attn.v_proj,0.0000050708,0.05000,2.337
20,self_attn.k_proj,0.0000347093,0.05000,2.348
20,self_attn.q_proj,0.0000555758,0.05000,2.353
20,self_attn.o_proj,0.0000002177,0.05000,0.801
20,mlp.gate_proj,0.0000833276,0.05000,1.632
20,mlp.up_proj,0.0000508083,0.05000,1.674
20,mlp.down_proj,0.0000017654,0.05000,3.737
21,self_attn.q_proj,0.0000526357,0.05000,2.300
21,self_attn.v_proj,0.0000053200,0.05000,2.310
21,self_attn.k_proj,0.0000320896,0.05000,2.312
21,self_attn.o_proj,0.0000003075,0.05000,0.893
21,mlp.gate_proj,0.0000898800,0.05000,1.672
21,mlp.up_proj,0.0000542388,0.05000,1.684
21,mlp.down_proj,0.0000020635,0.05000,3.919
22,self_attn.q_proj,0.0000544886,0.05000,2.351
22,self_attn.v_proj,0.0000063488,0.05000,2.357
22,self_attn.k_proj,0.0000350077,0.05000,2.360
22,self_attn.o_proj,0.0000002961,0.05000,0.909
22,mlp.gate_proj,0.0000934871,0.05000,1.631
22,mlp.up_proj,0.0000571447,0.05000,1.639
22,mlp.down_proj,0.0000021690,0.05000,3.756
23,self_attn.k_proj,0.0000353973,0.05000,2.293
23,self_attn.q_proj,0.0000563823,0.05000,2.313
23,self_attn.v_proj,0.0000068588,0.05000,2.314
23,self_attn.o_proj,0.0000002978,0.05000,0.894
23,mlp.gate_proj,0.0000989324,0.05000,1.652
23,mlp.up_proj,0.0000608072,0.05000,1.673
23,mlp.down_proj,0.0000023516,0.05000,3.788
24,self_attn.q_proj,0.0000564025,0.05000,2.352
24,self_attn.v_proj,0.0000088319,0.05000,2.357
24,self_attn.k_proj,0.0000346034,0.05000,2.369
24,self_attn.o_proj,0.0000002928,0.05000,0.913
24,mlp.up_proj,0.0000653894,0.05000,1.652
24,mlp.gate_proj,0.0001064983,0.05000,1.671
24,mlp.down_proj,0.0000025538,0.05000,3.706
25,self_attn.q_proj,0.0000568810,0.05000,2.245
25,self_attn.v_proj,0.0000091283,0.05000,2.273
25,self_attn.k_proj,0.0000334146,0.05000,2.282
25,self_attn.o_proj,0.0000003138,0.05000,0.799
25,mlp.gate_proj,0.0001145573,0.05000,1.624
25,mlp.up_proj,0.0000704320,0.05000,1.634
25,mlp.down_proj,0.0000028543,0.05000,3.628
26,self_attn.k_proj,0.0000350905,0.05000,2.297
26,self_attn.q_proj,0.0000543738,0.05000,2.317
26,self_attn.v_proj,0.0000088547,0.05000,2.326
26,self_attn.o_proj,0.0000004784,0.05000,0.838
26,mlp.up_proj,0.0000764588,0.05000,1.683
26,mlp.gate_proj,0.0001249510,0.05000,1.692
26,mlp.down_proj,0.0000033145,0.05000,3.801
27,self_attn.k_proj,0.0000386050,0.05000,2.234
27,self_attn.q_proj,0.0000578191,0.05000,2.259
27,self_attn.v_proj,0.0000124222,0.05000,2.262
27,self_attn.o_proj,0.0000005356,0.05000,0.886
27,mlp.gate_proj,0.0001362827,0.05000,1.676
27,mlp.up_proj,0.0000842074,0.05000,1.688
27,mlp.down_proj,0.0000039904,0.05000,3.738
28,self_attn.k_proj,0.0000314425,0.05000,2.318
28,self_attn.v_proj,0.0000113324,0.05000,2.324
28,self_attn.q_proj,0.0000532324,0.05000,2.328
28,self_attn.o_proj,0.0000009994,0.05000,0.835
28,mlp.up_proj,0.0000943372,0.05000,1.700
28,mlp.gate_proj,0.0001463551,0.05000,1.716
28,mlp.down_proj,0.0000052710,0.05000,3.611
29,self_attn.q_proj,0.0000587671,0.05000,2.318
29,self_attn.k_proj,0.0000336232,0.05000,2.324
29,self_attn.v_proj,0.0000133898,0.05000,2.327
29,self_attn.o_proj,0.0000008192,0.05000,0.851
29,mlp.up_proj,0.0001007172,0.05000,1.616
29,mlp.gate_proj,0.0001498114,0.05000,1.625
29,mlp.down_proj,0.0000070554,0.05000,3.675
30,self_attn.q_proj,0.0000510301,0.05000,2.264
30,self_attn.v_proj,0.0000183472,0.05000,2.280
30,self_attn.k_proj,0.0000333597,0.05000,2.286
30,self_attn.o_proj,0.0000014926,0.05000,0.926
30,mlp.up_proj,0.0001060930,0.05000,1.746
30,mlp.gate_proj,0.0001608157,0.05000,1.764
30,mlp.down_proj,0.0000118043,0.05000,3.928
31,self_attn.k_proj,0.0000237176,0.05000,2.355
31,self_attn.q_proj,0.0000431718,0.05000,2.378
31,self_attn.v_proj,0.0000104264,0.05000,2.383
31,self_attn.o_proj,0.0000028225,0.05000,0.856
31,mlp.gate_proj,0.0001460367,0.05000,1.695
31,mlp.up_proj,0.0001011256,0.05000,1.704
31,mlp.down_proj,0.0000343366,0.05000,3.684
|