Hugging Face's logo

jburtoft
/
Llama7B-4096-2cores

Text Generation
Transformers
llama
Inference Endpoints
Model card Files Community
2
jburtoft commited on
Commit
e746146
•
1 Parent(s): 2753e1c

0cf8bc616c0ee4747e888ee7afd6fcd6c24f1a58abe3ed68018b624b9e655d4d

Browse files
Files changed (21) hide show
  1. checkpoint/config.json +28 -0
  2. checkpoint/generation_config.json +10 -0
  3. checkpoint/pytorch_model.bin/key_to_filename.json +3 -0
  4. checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
  5. checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
  6. checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
  7. checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
  8. checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
  9. checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
  10. checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
  11. checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
  12. checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
  13. checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
  14. checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +3 -0
  15. checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +3 -0
  16. checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
  17. checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
  18. checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
  19. checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
  20. checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
  21. checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
checkpoint/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
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,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
checkpoint/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.36.2"
10
+ }
checkpoint/pytorch_model.bin/key_to_filename.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825d20f4a18183eff3963e805edd13ef7eb35b0aff7a850e8153ca1eeeb37970
3
+ size 26397
checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5c4acb278381b1fc040ff34ca7cdfa8264895cfad4fee5c90436c423a8f459
3
+ size 524288789
checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4486401b9f7b27193d310385d3468fdd234936513b93a4d2e9662d745b9b74
3
+ size 67109756
checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a22f8644d0a6940f854aaf7882e60579972973c97575f7e25622f97280f977
3
+ size 67109759
checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5c80fae90ca3476520a485c29d07121eb270e0534cb2c9ce08f4aa764e90fd
3
+ size 67109765
checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7b3eefbb663e184e8ee804ea11b02ac98f29a30abdf361eab46e4da7983a00
3
+ size 67109765
checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b58bd301b57fc9e3c23375ed119c0ceecd9962e1aa714cea3722885e08c9d6a
3
+ size 67109765
checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed98fdbfda7fc25acc4f80728f69e7cc647477ed659009d9339a16fd780bd34
3
+ size 67109765
checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b7a49d0bb826f91c9547c1494367d5273678c2d221de9080ccec9ba1befc56
3
+ size 180355964
checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54b7365baf60a919654b1f2f4feb8991a700459769a779c95094018a08c5291
3
+ size 180355958
checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c079b1f4963c658c0dd95c54ab6f31e55e95cb40b0242465cd78388631c6302
3
+ size 180355964
checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b697c974c581a4b64024f0dfa328941f597fa5b93312fff8dbe2140988b6f1
3
+ size 17282
checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440dd212bb2e67c2ff83a2d42135f13589a04f622f41d523c241941e008ec1b8
3
+ size 17309
checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3046b38eb5f0dbd87c7c9cc320dfc3374311930d38ee43a03169c61a8b6eb19f
3
+ size 67109765
checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afe803e9188698fe5b29e551e418da34e536dd5fc42d53f2d4d02acb06780a0
3
+ size 67109759
checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3ef1f510bd1955a076e2bbc7c509f1f28479bcf17755469e2ad201c70362cb
3
+ size 67109765
checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dc6f96ead6b19d38d2bf5fdcb98dbc2baa34487ffb416029ad6bed9d37baf0
3
+ size 67109765
checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46267dfe1859f8a4fd450e43523fb9603c849162eb53a5f72445daec88730607
3
+ size 67109765
checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d874134d19b3a5e0c28b4cb14a5c6ce416592cc0b280d22e6893c178f0bc4890
3
+ size 180355964