Hugging Face's logo

askulkarni2
/
neuron-mistral7bv0.3

PyTorch
mistral
Model card Files
xet
 Community
askulkarni2 commited on
Commit
13d2809
·
unverified ·
1 Parent(s): 4d1a147

move everything to root

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. -split/config.json +0 -27
  2. -split/generation_config.json +0 -6
  3. config.json +4 -2
  4. generation_config.json +1 -1
  5. {-split/pytorch_model.bin → pytorch_model.bin}/key_to_filename.json +0 -0
  6. {-split/pytorch_model.bin → pytorch_model.bin}/p0.model.embed_tokens.weight +0 -0
  7. {-split/pytorch_model.bin → pytorch_model.bin}/p1.model.layers.0.self_attn.q_proj.weight +0 -0
  8. {-split/pytorch_model.bin → pytorch_model.bin}/p10.model.layers.1.self_attn.q_proj.weight +0 -0
  9. {-split/pytorch_model.bin → pytorch_model.bin}/p100.model.layers.11.self_attn.q_proj.weight +0 -0
  10. {-split/pytorch_model.bin → pytorch_model.bin}/p101.model.layers.11.self_attn.k_proj.weight +0 -0
  11. {-split/pytorch_model.bin → pytorch_model.bin}/p102.model.layers.11.self_attn.v_proj.weight +0 -0
  12. {-split/pytorch_model.bin → pytorch_model.bin}/p103.model.layers.11.self_attn.o_proj.weight +0 -0
  13. {-split/pytorch_model.bin → pytorch_model.bin}/p104.model.layers.11.mlp.gate_proj.weight +0 -0
  14. {-split/pytorch_model.bin → pytorch_model.bin}/p105.model.layers.11.mlp.up_proj.weight +0 -0
  15. {-split/pytorch_model.bin → pytorch_model.bin}/p106.model.layers.11.mlp.down_proj.weight +0 -0
  16. {-split/pytorch_model.bin → pytorch_model.bin}/p107.model.layers.11.input_layernorm.weight +0 -0
  17. {-split/pytorch_model.bin → pytorch_model.bin}/p108.model.layers.11.post_attention_layernorm.weight +0 -0
  18. {-split/pytorch_model.bin → pytorch_model.bin}/p109.model.layers.12.self_attn.q_proj.weight +0 -0
  19. {-split/pytorch_model.bin → pytorch_model.bin}/p11.model.layers.1.self_attn.k_proj.weight +0 -0
  20. {-split/pytorch_model.bin → pytorch_model.bin}/p110.model.layers.12.self_attn.k_proj.weight +0 -0
  21. {-split/pytorch_model.bin → pytorch_model.bin}/p111.model.layers.12.self_attn.v_proj.weight +0 -0
  22. {-split/pytorch_model.bin → pytorch_model.bin}/p112.model.layers.12.self_attn.o_proj.weight +0 -0
  23. {-split/pytorch_model.bin → pytorch_model.bin}/p113.model.layers.12.mlp.gate_proj.weight +0 -0
  24. {-split/pytorch_model.bin → pytorch_model.bin}/p114.model.layers.12.mlp.up_proj.weight +0 -0
  25. {-split/pytorch_model.bin → pytorch_model.bin}/p115.model.layers.12.mlp.down_proj.weight +0 -0
  26. {-split/pytorch_model.bin → pytorch_model.bin}/p116.model.layers.12.input_layernorm.weight +0 -0
  27. {-split/pytorch_model.bin → pytorch_model.bin}/p117.model.layers.12.post_attention_layernorm.weight +0 -0
  28. {-split/pytorch_model.bin → pytorch_model.bin}/p118.model.layers.13.self_attn.q_proj.weight +0 -0
  29. {-split/pytorch_model.bin → pytorch_model.bin}/p119.model.layers.13.self_attn.k_proj.weight +0 -0
  30. {-split/pytorch_model.bin → pytorch_model.bin}/p12.model.layers.1.self_attn.v_proj.weight +0 -0
  31. {-split/pytorch_model.bin → pytorch_model.bin}/p120.model.layers.13.self_attn.v_proj.weight +0 -0
  32. {-split/pytorch_model.bin → pytorch_model.bin}/p121.model.layers.13.self_attn.o_proj.weight +0 -0
  33. {-split/pytorch_model.bin → pytorch_model.bin}/p122.model.layers.13.mlp.gate_proj.weight +0 -0
  34. {-split/pytorch_model.bin → pytorch_model.bin}/p123.model.layers.13.mlp.up_proj.weight +0 -0
  35. {-split/pytorch_model.bin → pytorch_model.bin}/p124.model.layers.13.mlp.down_proj.weight +0 -0
  36. {-split/pytorch_model.bin → pytorch_model.bin}/p125.model.layers.13.input_layernorm.weight +0 -0
  37. {-split/pytorch_model.bin → pytorch_model.bin}/p126.model.layers.13.post_attention_layernorm.weight +0 -0
  38. {-split/pytorch_model.bin → pytorch_model.bin}/p127.model.layers.14.self_attn.q_proj.weight +0 -0
  39. {-split/pytorch_model.bin → pytorch_model.bin}/p128.model.layers.14.self_attn.k_proj.weight +0 -0
  40. {-split/pytorch_model.bin → pytorch_model.bin}/p129.model.layers.14.self_attn.v_proj.weight +0 -0
  41. {-split/pytorch_model.bin → pytorch_model.bin}/p13.model.layers.1.self_attn.o_proj.weight +0 -0
  42. {-split/pytorch_model.bin → pytorch_model.bin}/p130.model.layers.14.self_attn.o_proj.weight +0 -0
  43. {-split/pytorch_model.bin → pytorch_model.bin}/p131.model.layers.14.mlp.gate_proj.weight +0 -0
  44. {-split/pytorch_model.bin → pytorch_model.bin}/p132.model.layers.14.mlp.up_proj.weight +0 -0
  45. {-split/pytorch_model.bin → pytorch_model.bin}/p133.model.layers.14.mlp.down_proj.weight +0 -0
  46. {-split/pytorch_model.bin → pytorch_model.bin}/p134.model.layers.14.input_layernorm.weight +0 -0
  47. {-split/pytorch_model.bin → pytorch_model.bin}/p135.model.layers.14.post_attention_layernorm.weight +0 -0
  48. {-split/pytorch_model.bin → pytorch_model.bin}/p136.model.layers.15.self_attn.q_proj.weight +0 -0
  49. {-split/pytorch_model.bin → pytorch_model.bin}/p137.model.layers.15.self_attn.k_proj.weight +0 -0
  50. {-split/pytorch_model.bin → pytorch_model.bin}/p138.model.layers.15.self_attn.v_proj.weight +0 -0
-split/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 32768,
15
- "model_type": "mistral",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "rms_norm_eps": 1e-05,
20
- "rope_theta": 1000000.0,
21
- "sliding_window": null,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "float32",
24
- "transformers_version": "4.44.0",
25
- "use_cache": true,
26
- "vocab_size": 32768
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
-split/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.44.0"
6
- }
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,10 +1,12 @@
1
  {
 
2
  "architectures": [
3
  "MistralForCausalLM"
4
  ],
5
  "attention_dropout": 0.0,
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
 
8
  "hidden_act": "silu",
9
  "hidden_size": 4096,
10
  "initializer_range": 0.02,
@@ -18,8 +20,8 @@
18
  "rope_theta": 1000000.0,
19
  "sliding_window": null,
20
  "tie_word_embeddings": false,
21
- "torch_dtype": "bfloat16",
22
- "transformers_version": "4.42.0.dev0",
23
  "use_cache": true,
24
  "vocab_size": 32768
25
  }
 
1
  {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 128,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
 
20
  "rope_theta": 1000000.0,
21
  "sliding_window": null,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.44.0",
25
  "use_cache": true,
26
  "vocab_size": 32768
27
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.42.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.44.0"
6
  }
{-split/pytorch_model.bin → pytorch_model.bin}/key_to_filename.json RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p0.model.embed_tokens.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p1.model.layers.0.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p10.model.layers.1.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p100.model.layers.11.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p101.model.layers.11.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p102.model.layers.11.self_attn.v_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p103.model.layers.11.self_attn.o_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p104.model.layers.11.mlp.gate_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p105.model.layers.11.mlp.up_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p106.model.layers.11.mlp.down_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p107.model.layers.11.input_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p108.model.layers.11.post_attention_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p109.model.layers.12.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p11.model.layers.1.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p110.model.layers.12.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p111.model.layers.12.self_attn.v_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p112.model.layers.12.self_attn.o_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p113.model.layers.12.mlp.gate_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p114.model.layers.12.mlp.up_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p115.model.layers.12.mlp.down_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p116.model.layers.12.input_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p117.model.layers.12.post_attention_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p118.model.layers.13.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p119.model.layers.13.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p12.model.layers.1.self_attn.v_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p120.model.layers.13.self_attn.v_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p121.model.layers.13.self_attn.o_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p122.model.layers.13.mlp.gate_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p123.model.layers.13.mlp.up_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p124.model.layers.13.mlp.down_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p125.model.layers.13.input_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p126.model.layers.13.post_attention_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p127.model.layers.14.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p128.model.layers.14.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p129.model.layers.14.self_attn.v_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p13.model.layers.1.self_attn.o_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p130.model.layers.14.self_attn.o_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p131.model.layers.14.mlp.gate_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p132.model.layers.14.mlp.up_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p133.model.layers.14.mlp.down_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p134.model.layers.14.input_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p135.model.layers.14.post_attention_layernorm.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p136.model.layers.15.self_attn.q_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p137.model.layers.15.self_attn.k_proj.weight RENAMED
File without changes
{-split/pytorch_model.bin → pytorch_model.bin}/p138.model.layers.15.self_attn.v_proj.weight RENAMED
File without changes