Hugging Face's logo

ISTA-DASLab
/
Llama-3.1-70B-Instruct-HIGGS-3bit

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
3-bit
higgs
Model card Files Community
BlackSamorez commited on
Commit
c8dee8d
•
1 Parent(s): 55b7ef8

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -1
  2. model-00001-of-00007.safetensors +2 -2
  3. model.safetensors.index.json +1 -5
config.json CHANGED
@@ -28,7 +28,8 @@
28
  "group_size": 256,
29
  "hadamard_size": 512,
30
  "modules_to_not_convert": [
31
- "lm_head"
 
32
  ],
33
  "p": 2,
34
  "quant_method": "higgs"
 
28
  "group_size": 256,
29
  "hadamard_size": 512,
30
  "modules_to_not_convert": [
31
+ "lm_head",
32
+ "layers.0.self_attn.v_proj"
33
  ],
34
  "p": 2,
35
  "quant_method": "higgs"
model-00001-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47bf164a0e886018664d294e1caefc353afb0cf4b86a7338ab08591ecfdfc821
3
- size 4959686300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a58228fd718fd98631a08cb09db6dbf5caf87b701991e0869ec00e23a479824
3
+ size 4973251544
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 30409399232
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00007-of-00007.safetensors",
@@ -37,10 +37,6 @@
37
  "model.layers.0.self_attn.q_proj.tables": "model-00001-of-00007.safetensors",
38
  "model.layers.0.self_attn.q_proj.tables2": "model-00001-of-00007.safetensors",
39
  "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
40
- "model.layers.0.self_attn.v_proj.num_sms_packed": "model-00001-of-00007.safetensors",
41
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00007.safetensors",
42
- "model.layers.0.self_attn.v_proj.tables": "model-00001-of-00007.safetensors",
43
- "model.layers.0.self_attn.v_proj.tables2": "model-00001-of-00007.safetensors",
44
  "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
45
  "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
46
  "model.layers.1.mlp.down_proj.num_sms_packed": "model-00001-of-00007.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 30422964908
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00007-of-00007.safetensors",
 
37
  "model.layers.0.self_attn.q_proj.tables": "model-00001-of-00007.safetensors",
38
  "model.layers.0.self_attn.q_proj.tables2": "model-00001-of-00007.safetensors",
39
  "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
 
 
 
 
40
  "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
41
  "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
42
  "model.layers.1.mlp.down_proj.num_sms_packed": "model-00001-of-00007.safetensors",