sharpenb commited on
Commit
a768254
1 Parent(s): a570a0b

Upload folder using huggingface_hub (#2)

Browse files

- 36aa1e3a1d93c775b272f4a1d9b7edb7c203266c299f7180a78dd3c4b2e6abe2 (1bdd7ea2ed895db4e60171220ba67b2c5277a114)

Files changed (5) hide show
  1. README.md +2 -2
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. plots.png +0 -0
  5. smash_config.json +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ tags:
34
 
35
  ## Results
36
 
37
- Detailed efficiency metrics coming soon!
38
 
39
  **Frequently Asked Questions**
40
  - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -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/cerebras-Cerebras-GPT-111M-bnb-4bit-smashed",
64
- trust_remote_code=True)
65
  tokenizer = AutoTokenizer.from_pretrained("cerebras/Cerebras-GPT-111M")
66
 
67
  input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
 
34
 
35
  ## Results
36
 
37
+ ![image info](./plots.png)
38
 
39
  **Frequently Asked Questions**
40
  - ***How does the compression work?*** The model is compressed with llm-int8.
 
61
  from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
  model = AutoModelForCausalLM.from_pretrained("PrunaAI/cerebras-Cerebras-GPT-111M-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("cerebras/Cerebras-GPT-111M")
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/tmppdfytjk7",
3
  "activation_function": "gelu",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -19,7 +19,7 @@
19
  "quantization_config": {
20
  "bnb_4bit_compute_dtype": "bfloat16",
21
  "bnb_4bit_quant_type": "fp4",
22
- "bnb_4bit_use_double_quant": true,
23
  "llm_int8_enable_fp32_cpu_offload": false,
24
  "llm_int8_has_fp16_weight": false,
25
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmpnjft4zf9",
3
  "activation_function": "gelu",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
19
  "quantization_config": {
20
  "bnb_4bit_compute_dtype": "bfloat16",
21
  "bnb_4bit_quant_type": "fp4",
22
+ "bnb_4bit_use_double_quant": false,
23
  "llm_int8_enable_fp32_cpu_offload": false,
24
  "llm_int8_has_fp16_weight": false,
25
  "llm_int8_skip_modules": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:246b1bb693f512d2cb991ef63a1741a3c73b2b93fc6eab1bda76bb40d673bd90
3
- size 117140801
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068b147af4e3f55b72990ceb1334823cb1a8946fbfc51cf01f46e4b89a5c49b3
3
+ size 120388150
plots.png ADDED
smash_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelszulz8221",
12
  "batch_size": 1,
13
  "model_name": "cerebras/Cerebras-GPT-111M",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsgv4v5_bg",
12
  "batch_size": 1,
13
  "model_name": "cerebras/Cerebras-GPT-111M",
14
  "pruning_ratio": 0.0,