2214efc59d2864820d37c1b70be01a6e595bbf8a9b0c30720321728c0ab49c2e
Browse files- README.md +2 -2
- config.json +2 -2
- model.safetensors +2 -2
- plots.png +0 -0
- smash_config.json +1 -1
README.md
CHANGED
@@ -34,7 +34,7 @@ tags:
|
|
34 |
|
35 |
## Results
|
36 |
|
37 |
-
|
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/TinyLlama-TinyLlama-1.1B-step-50K-105b-bnb-4bit-smashed",
|
64 |
-
trust_remote_code=True)
|
65 |
tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-step-50K-105b")
|
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/TinyLlama-TinyLlama-1.1B-step-50K-105b-bnb-4bit-smashed",
|
64 |
+
trust_remote_code=True, device_map='auto')
|
65 |
tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-step-50K-105b")
|
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/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -20,7 +20,7 @@
|
|
20 |
"quantization_config": {
|
21 |
"bnb_4bit_compute_dtype": "bfloat16",
|
22 |
"bnb_4bit_quant_type": "fp4",
|
23 |
-
"bnb_4bit_use_double_quant":
|
24 |
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
"llm_int8_has_fp16_weight": false,
|
26 |
"llm_int8_skip_modules": [
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/tmp/tmpj4qvxyx2",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
20 |
"quantization_config": {
|
21 |
"bnb_4bit_compute_dtype": "bfloat16",
|
22 |
"bnb_4bit_quant_type": "fp4",
|
23 |
+
"bnb_4bit_use_double_quant": false,
|
24 |
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
"llm_int8_has_fp16_weight": false,
|
26 |
"llm_int8_skip_modules": [
|
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 sha256:447be83b77301657c254a003d0cd19882b1ca3d34a0e4b1bc021f4f13481a220
|
3 |
+
size 807426286
|
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/
|
12 |
"batch_size": 1,
|
13 |
"model_name": "TinyLlama/TinyLlama-1.1B-step-50K-105b",
|
14 |
"pruning_ratio": 0.0,
|
|
|
8 |
"compilers": "None",
|
9 |
"task": "text_text_generation",
|
10 |
"device": "cuda",
|
11 |
+
"cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsvbxmmpy_",
|
12 |
"batch_size": 1,
|
13 |
"model_name": "TinyLlama/TinyLlama-1.1B-step-50K-105b",
|
14 |
"pruning_ratio": 0.0,
|