Hugging Face's logo

ISTA-DASLab
/
Meta-Llama-3-70B-AQLM-PV-1Bit-1x16

Text Generation
Transformers
Safetensors
llama
facebook
meta
llama-3
conversational
text-generation-inference
Inference Endpoints
aqlm
Model card Files Community
2
justheuristic commited on
Commit
ee14737
•
1 Parent(s): 7b2bd6d

1bit

Browse files
Files changed (8) hide show
  1. config.json +3 -3
  2. generation_config.json +1 -1
  3. model-00001-of-00005.safetensors → model-00001-of-00003.safetensors +2 -2
  4. model-00002-of-00005.safetensors → model-00002-of-00003.safetensors +2 -2
  5. model-00003-of-00005.safetensors → model-00003-of-00003.safetensors +2 -2
  6. model-00004-of-00005.safetensors +0 -3
  7. model-00005-of-00005.safetensors +0 -3
  8. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./mnt/final",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -18,7 +18,7 @@
18
  "num_key_value_heads": 8,
19
  "pretraining_tp": 1,
20
  "quantization_config": {
21
- "in_group_size": 8,
22
  "linear_weights_not_to_quantize": [
23
  "model.layers.0.input_layernorm.weight",
24
  "model.layers.0.post_attention_layernorm.weight",
@@ -194,7 +194,7 @@
194
  "rope_theta": 500000.0,
195
  "tie_word_embeddings": false,
196
  "torch_dtype": "float16",
197
- "transformers_version": "4.39.3",
198
  "use_cache": true,
199
  "vocab_size": 128256
200
  }
 
1
  {
2
+ "_name_or_path": "/extra_disk_1/jheuristic/llama-3-70b-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
18
  "num_key_value_heads": 8,
19
  "pretraining_tp": 1,
20
  "quantization_config": {
21
+ "in_group_size": 16,
22
  "linear_weights_not_to_quantize": [
23
  "model.layers.0.input_layernorm.weight",
24
  "model.layers.0.post_attention_layernorm.weight",
 
194
  "rope_theta": 500000.0,
195
  "tie_word_embeddings": false,
196
  "torch_dtype": "float16",
197
+ "transformers_version": "4.40.1",
198
  "use_cache": true,
199
  "vocab_size": 128256
200
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "eos_token_id": 128001,
5
- "transformers_version": "4.39.3"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "eos_token_id": 128001,
5
+ "transformers_version": "4.40.1"
6
  }
model-00001-of-00005.safetensors → model-00001-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04d7849c56c84541bc2571aa0c9e9469b5d225cbbd53c42e14095a6a6cc1fd80
3
- size 4999125768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e2adc347f408d6a3601dad3248bc6df5a6aec729a085309e0f4fad56198e8a
3
+ size 4996053968
model-00002-of-00005.safetensors → model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af4e0fa4698befd4f21af12248914d8962c9d41001cee8a717bbe9ee6ee82ed6
3
- size 4955928968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc5f1dd16df466ad4b5e78caafbb570aa253dbb42ef6dafba609d96324a5d416
3
+ size 4995365800
model-00003-of-00005.safetensors → model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9cad7589a4387c52161f8e072d2e7c520344a9a9c781d2863b31325fc4300d2
3
- size 4991608736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf649e098013e6ca25359b240f3434b58c9c6c06867742713152f7f4581b2da
3
+ size 3958346080
model-00004-of-00005.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:91c5cda1023d16ae85b195773c6463205f400db892067197e7b2a4b03411dde5
3
- size 4870931440
 
 
 
 
model-00005-of-00005.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:959d1058dd3372a4b636b0d900b3b35b2549a0d283e978f64f84743a9ae30bef
3
- size 2101346432
 
 
 
 
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff