Upload folder using huggingface_hub

#5
Files changed (4) hide show
  1. README.md +1 -1
  2. config.json +1 -1
  3. plots.png +0 -0
  4. smash_config.json +5 -5
README.md CHANGED
@@ -61,7 +61,7 @@ You can run the smashed model with these steps:
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/42dot-42dot_LLM-PLM-1.3B-bnb-4bit-smashed",
64
- trust_remote_code=True)
65
  tokenizer = AutoTokenizer.from_pretrained("42dot/42dot_LLM-PLM-1.3B")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
 
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/42dot-42dot_LLM-PLM-1.3B-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("42dot/42dot_LLM-PLM-1.3B")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/tmpahl9ahxq",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/tmp/tmpor5u0g_u",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
plots.png CHANGED
smash_config.json CHANGED
@@ -2,18 +2,18 @@
2
  "api_key": null,
3
  "verify_url": "http://johnrachwan.pythonanywhere.com",
4
  "smash_config": {
5
- "pruners": "[]",
6
- "factorizers": "[]",
7
  "quantizers": "['llm-int8']",
8
- "compilers": "[]",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsq_fbgga3",
12
  "batch_size": 1,
13
  "model_name": "42dot/42dot_LLM-PLM-1.3B",
14
  "pruning_ratio": 0.0,
15
  "n_quantization_bits": 4,
16
- "output_deviation": 0.01,
17
  "max_batch_size": 1,
18
  "qtype_weight": "torch.qint8",
19
  "qtype_activation": "torch.quint8",
 
2
  "api_key": null,
3
  "verify_url": "http://johnrachwan.pythonanywhere.com",
4
  "smash_config": {
5
+ "pruners": "None",
6
+ "factorizers": "None",
7
  "quantizers": "['llm-int8']",
8
+ "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsz_jn2cg7",
12
  "batch_size": 1,
13
  "model_name": "42dot/42dot_LLM-PLM-1.3B",
14
  "pruning_ratio": 0.0,
15
  "n_quantization_bits": 4,
16
+ "output_deviation": 0.005,
17
  "max_batch_size": 1,
18
  "qtype_weight": "torch.qint8",
19
  "qtype_activation": "torch.quint8",