Hugging Face's logo

PaulQ1
/
Chat_TS

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
 Community
PaulQ1 commited on
Commit
e495c7a
·
verified ·
1 Parent(s): 6382a8b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +3 -3
  2. model-00001-of-00006.safetensors +2 -2
  3. model-00002-of-00006.safetensors +2 -2
  4. model-00003-of-00006.safetensors +1 -1
  5. model-00004-of-00006.safetensors +1 -1
  6. model-00005-of-00006.safetensors +1 -1
  7. model-00006-of-00006.safetensors +2 -2
  8. model.safetensors.index.json +2 -2
  9. vqvae_model_e64_k9981_L4_mse0.12622935775863497.pth +3 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/quinlanp/scratch/finetune_checkpoints/T1_1N_B4-llama7bft/hf_checkpoint",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -11,7 +11,7 @@
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 11008,
14
- "max_position_embeddings": 2048,
15
  "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
@@ -24,5 +24,5 @@
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.36.2",
26
  "use_cache": false,
27
- "vocab_size": 36099
28
  }
 
1
  {
2
+ "_name_or_path": "/home/quinlanp/scratch/llama7b-chat-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
  "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
 
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.36.2",
26
  "use_cache": false,
27
+ "vocab_size": 41984
28
  }
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b494d19c19ee92a8d793dbcdfdddeb21fe0c539b37c4085c1cd05c692ab6cce0
3
- size 4907554432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0947132909fbda351b179c60d30e949d973a19e604d6806ba7d3b7dbd371afe2
3
+ size 4936865296
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfe57c286181a7a8537ac7440de5022a85c5622a8f34038e6e7b209b41f5bdfe
3
- size 4857206856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f06d5bf4e0f09dce543133f560718325355bdcd240d42458855b00fdf109a6b
3
+ size 4924315832
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2dec7b77efbff3a02423738d72490e1ccd6ab22284906335b3fd102ab9db653
3
  size 4857206904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd72d44842c5efaf5bc5d4cc6ff66aba051d3b4782c416140e9f79c3ee8c8c8
3
  size 4857206904
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94f9f4ee699eb2e632d4bec4255a8c808252e4efb4cfb9f2501bc0319db448d7
3
  size 4857206904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0f8b11630c0c161abd279490547203ae704ac0e99a4a3afb2d117c8f3f61d8
3
  size 4857206904
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680f69df9bc8fc8d1c15af2b2d203cc9a8f7baeb4faf6be79c79c9f9b5978799
3
  size 4857206904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f0f64a93007d5347c98990f8637e319a3eeb26a31add248a20c9fa2d79b3e5
3
  size 4857206904
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286f06703be367348b65dafe3d7b225d369358436d07f0f6e3210f144333c3a1
3
- size 2751630128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c18ce28ad5d521e7e5c7f631e5f637df40d7bcbe3b20630beb5fde3c2287323
3
+ size 2848049976
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 27087978496
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -254,7 +254,7 @@
254
  "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
  "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
258
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
  "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 27280818176
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00006-of-00006.safetensors",
 
254
  "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
  "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
  "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
vqvae_model_e64_k9981_L4_mse0.12622935775863497.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3356f7ef467ac15990aa21640ce9b3d402abf44bcb8d704bc379837c55f301d6
3
+ size 3031975