Upload folder using huggingface_hub

#3
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/scb10x-typhoon-7b-bnb-4bit-smashed",
64
- trust_remote_code=True)
65
  tokenizer = AutoTokenizer.from_pretrained("scb10x/typhoon-7b")
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/scb10x-typhoon-7b-bnb-4bit-smashed",
64
+ trust_remote_code=True, device_map='auto')
65
  tokenizer = AutoTokenizer.from_pretrained("scb10x/typhoon-7b")
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/tmpcu40hp9p",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -18,7 +18,7 @@
18
  "quantization_config": {
19
  "bnb_4bit_compute_dtype": "bfloat16",
20
  "bnb_4bit_quant_type": "fp4",
21
- "bnb_4bit_use_double_quant": true,
22
  "llm_int8_enable_fp32_cpu_offload": false,
23
  "llm_int8_has_fp16_weight": false,
24
  "llm_int8_skip_modules": [
 
1
  {
2
+ "_name_or_path": "/tmp/tmpqj5gh7mg",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
18
  "quantization_config": {
19
  "bnb_4bit_compute_dtype": "bfloat16",
20
  "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": false,
22
  "llm_int8_enable_fp32_cpu_offload": false,
23
  "llm_int8_has_fp16_weight": false,
24
  "llm_int8_skip_modules": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cdee5e477c9b34c11322928621ccb12a94b77f39d68257c79e56122f467f574
3
- size 4178427746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f994c448da2260497162225e153c3c27dd75073769e80337563d7df62039525
3
+ size 4503577728
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/modelswrv9gad1",
12
  "batch_size": 1,
13
  "model_name": "scb10x/typhoon-7b",
14
  "pruning_ratio": 0.0,
 
8
  "compilers": "None",
9
  "task": "text_text_generation",
10
  "device": "cuda",
11
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelswgmyw_ib",
12
  "batch_size": 1,
13
  "model_name": "scb10x/typhoon-7b",
14
  "pruning_ratio": 0.0,