Hugging Face's logo

ariG23498
/
Mistral-7B-Instruct-v0.3

Text Generation
Transformers
PyTorch
TensorFlow
mistral
generated_from_keras_callback
Inference Endpoints
text-generation-inference
Model card Files Community
ariG23498 commited on
Commit
5018752
•
1 Parent(s): 2e3111c

Upload TFMistralForCausalLM

Browse files
Files changed (6) hide show
  1. README.md +39 -21
  2. config.json +1 -1
  3. tf_model-00001-of-00003.h5 +3 -0
  4. tf_model-00002-of-00003.h5 +3 -0
  5. tf_model-00003-of-00003.h5 +3 -0
  6. tf_model.h5.index.json +298 -0
README.md CHANGED
@@ -1,29 +1,47 @@
1
  ---
2
- library_name: transformers
3
- tags: []
 
 
 
 
4
  ---
5
 
6
- Turns out that [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) only have safetensors. This repo
7
- is created to have the `.bin` files of the model.
8
 
9
- This repo is created by:
10
- ```py
11
- model_id = "mistralai/Mistral-7B-Instruct-v0.3"
12
- model = AutoModelForCausalLM.from_pretrained(model_id)
13
- model.push_to_hub("ariG23498/Mistral-7B-Instruct-v0.3", safe_serialization=False)
14
- ```
15
 
16
- This is due to the fact that the TensorFlow port cannot use safetensors and need bin files.
 
17
 
18
- You can use this model with TF like so:
19
- ```py
20
- model_tf = TFAutoModelForCausalLM.from_pretrained("ariG23498/Mistral-7B-Instruct-v0.3", from_pt=True)
21
- tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
22
 
23
- prompt = "My favourite condiment is"
24
- model_inputs = tokenizer([prompt], return_tensors="tf")
25
- generated_ids = model_tf.generate(**model_inputs, max_new_tokens=100, do_sample=True)
26
- tokenizer.batch_decode(generated_ids)[0]
27
- ```
28
 
29
- As soon as the safetensors and TensorFlow issue is sorted one can ditch this repository and use the official repository!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: ariG23498/Mistral-7B-Instruct-v0.3
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: Mistral-7B-Instruct-v0.3
7
+ results: []
8
  ---
9
 
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
 
13
+ # Mistral-7B-Instruct-v0.3
 
 
 
 
 
14
 
15
+ This model is a fine-tuned version of [ariG23498/Mistral-7B-Instruct-v0.3](https://huggingface.co/ariG23498/Mistral-7B-Instruct-v0.3) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
 
 
 
 
 
18
 
19
+ ## Model description
 
 
 
 
20
 
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - optimizer: None
37
+ - training_precision: float32
38
+
39
+ ### Training results
40
+
41
+
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.42.0.dev0
46
+ - TensorFlow 2.11.0
47
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "ariG23498/Mistral-7B-Instruct-v0.3",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
tf_model-00001-of-00003.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641e768ae722550592f3ea69dde6d2d120752aac37c0f7a44a734cf1c74dc362
3
+ size 9899060392
tf_model-00002-of-00003.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba0654e47c24e5d3aaa2a09e137b0d99452521c34ca5f494d95b0b10dd57349
3
+ size 9999805520
tf_model-00003-of-00003.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2943e17dc7719f086eaf16c3b7b25cde644ce6ab55d558f7bae79702e78dab
3
+ size 9093755096
tf_model.h5.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28992094208
4
+ },
5
+ "weight_map": {
6
+ "tf_mistral_for_causal_lm/lm_head/kernel:0": "tf_model-00003-of-00003.h5",
7
+ "tf_mistral_for_causal_lm/model/embed_tokens/embeddings:0": "tf_model-00001-of-00003.h5",
8
+ "tf_mistral_for_causal_lm/model/layers.0/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
9
+ "tf_mistral_for_causal_lm/model/layers.0/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
10
+ "tf_mistral_for_causal_lm/model/layers.0/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
11
+ "tf_mistral_for_causal_lm/model/layers.0/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
12
+ "tf_mistral_for_causal_lm/model/layers.0/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
13
+ "tf_mistral_for_causal_lm/model/layers.0/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
14
+ "tf_mistral_for_causal_lm/model/layers.0/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
15
+ "tf_mistral_for_causal_lm/model/layers.0/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
16
+ "tf_mistral_for_causal_lm/model/layers.0/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
17
+ "tf_mistral_for_causal_lm/model/layers.1/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
18
+ "tf_mistral_for_causal_lm/model/layers.1/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
19
+ "tf_mistral_for_causal_lm/model/layers.1/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
20
+ "tf_mistral_for_causal_lm/model/layers.1/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
21
+ "tf_mistral_for_causal_lm/model/layers.1/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
22
+ "tf_mistral_for_causal_lm/model/layers.1/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
23
+ "tf_mistral_for_causal_lm/model/layers.1/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
24
+ "tf_mistral_for_causal_lm/model/layers.1/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
25
+ "tf_mistral_for_causal_lm/model/layers.1/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
26
+ "tf_mistral_for_causal_lm/model/layers.10/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
27
+ "tf_mistral_for_causal_lm/model/layers.10/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
28
+ "tf_mistral_for_causal_lm/model/layers.10/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
29
+ "tf_mistral_for_causal_lm/model/layers.10/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
30
+ "tf_mistral_for_causal_lm/model/layers.10/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
31
+ "tf_mistral_for_causal_lm/model/layers.10/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
32
+ "tf_mistral_for_causal_lm/model/layers.10/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
33
+ "tf_mistral_for_causal_lm/model/layers.10/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
34
+ "tf_mistral_for_causal_lm/model/layers.10/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
35
+ "tf_mistral_for_causal_lm/model/layers.11/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
36
+ "tf_mistral_for_causal_lm/model/layers.11/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
37
+ "tf_mistral_for_causal_lm/model/layers.11/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
38
+ "tf_mistral_for_causal_lm/model/layers.11/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
39
+ "tf_mistral_for_causal_lm/model/layers.11/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
40
+ "tf_mistral_for_causal_lm/model/layers.11/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
41
+ "tf_mistral_for_causal_lm/model/layers.11/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
42
+ "tf_mistral_for_causal_lm/model/layers.11/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
43
+ "tf_mistral_for_causal_lm/model/layers.11/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
44
+ "tf_mistral_for_causal_lm/model/layers.12/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
45
+ "tf_mistral_for_causal_lm/model/layers.12/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
46
+ "tf_mistral_for_causal_lm/model/layers.12/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
47
+ "tf_mistral_for_causal_lm/model/layers.12/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
48
+ "tf_mistral_for_causal_lm/model/layers.12/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
49
+ "tf_mistral_for_causal_lm/model/layers.12/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
50
+ "tf_mistral_for_causal_lm/model/layers.12/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
51
+ "tf_mistral_for_causal_lm/model/layers.12/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
52
+ "tf_mistral_for_causal_lm/model/layers.12/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
53
+ "tf_mistral_for_causal_lm/model/layers.13/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
54
+ "tf_mistral_for_causal_lm/model/layers.13/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
55
+ "tf_mistral_for_causal_lm/model/layers.13/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
56
+ "tf_mistral_for_causal_lm/model/layers.13/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
57
+ "tf_mistral_for_causal_lm/model/layers.13/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
58
+ "tf_mistral_for_causal_lm/model/layers.13/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
59
+ "tf_mistral_for_causal_lm/model/layers.13/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
60
+ "tf_mistral_for_causal_lm/model/layers.13/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
61
+ "tf_mistral_for_causal_lm/model/layers.13/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
62
+ "tf_mistral_for_causal_lm/model/layers.14/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
63
+ "tf_mistral_for_causal_lm/model/layers.14/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
64
+ "tf_mistral_for_causal_lm/model/layers.14/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
65
+ "tf_mistral_for_causal_lm/model/layers.14/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
66
+ "tf_mistral_for_causal_lm/model/layers.14/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
67
+ "tf_mistral_for_causal_lm/model/layers.14/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
68
+ "tf_mistral_for_causal_lm/model/layers.14/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
69
+ "tf_mistral_for_causal_lm/model/layers.14/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
70
+ "tf_mistral_for_causal_lm/model/layers.14/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
71
+ "tf_mistral_for_causal_lm/model/layers.15/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
72
+ "tf_mistral_for_causal_lm/model/layers.15/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
73
+ "tf_mistral_for_causal_lm/model/layers.15/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
74
+ "tf_mistral_for_causal_lm/model/layers.15/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
75
+ "tf_mistral_for_causal_lm/model/layers.15/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
76
+ "tf_mistral_for_causal_lm/model/layers.15/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
77
+ "tf_mistral_for_causal_lm/model/layers.15/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
78
+ "tf_mistral_for_causal_lm/model/layers.15/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
79
+ "tf_mistral_for_causal_lm/model/layers.15/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
80
+ "tf_mistral_for_causal_lm/model/layers.16/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
81
+ "tf_mistral_for_causal_lm/model/layers.16/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
82
+ "tf_mistral_for_causal_lm/model/layers.16/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
83
+ "tf_mistral_for_causal_lm/model/layers.16/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
84
+ "tf_mistral_for_causal_lm/model/layers.16/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
85
+ "tf_mistral_for_causal_lm/model/layers.16/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
86
+ "tf_mistral_for_causal_lm/model/layers.16/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
87
+ "tf_mistral_for_causal_lm/model/layers.16/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
88
+ "tf_mistral_for_causal_lm/model/layers.16/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
89
+ "tf_mistral_for_causal_lm/model/layers.17/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
90
+ "tf_mistral_for_causal_lm/model/layers.17/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
91
+ "tf_mistral_for_causal_lm/model/layers.17/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
92
+ "tf_mistral_for_causal_lm/model/layers.17/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
93
+ "tf_mistral_for_causal_lm/model/layers.17/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
94
+ "tf_mistral_for_causal_lm/model/layers.17/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
95
+ "tf_mistral_for_causal_lm/model/layers.17/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
96
+ "tf_mistral_for_causal_lm/model/layers.17/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
97
+ "tf_mistral_for_causal_lm/model/layers.17/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
98
+ "tf_mistral_for_causal_lm/model/layers.18/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
99
+ "tf_mistral_for_causal_lm/model/layers.18/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
100
+ "tf_mistral_for_causal_lm/model/layers.18/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
101
+ "tf_mistral_for_causal_lm/model/layers.18/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
102
+ "tf_mistral_for_causal_lm/model/layers.18/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
103
+ "tf_mistral_for_causal_lm/model/layers.18/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
104
+ "tf_mistral_for_causal_lm/model/layers.18/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
105
+ "tf_mistral_for_causal_lm/model/layers.18/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
106
+ "tf_mistral_for_causal_lm/model/layers.18/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
107
+ "tf_mistral_for_causal_lm/model/layers.19/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
108
+ "tf_mistral_for_causal_lm/model/layers.19/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
109
+ "tf_mistral_for_causal_lm/model/layers.19/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
110
+ "tf_mistral_for_causal_lm/model/layers.19/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
111
+ "tf_mistral_for_causal_lm/model/layers.19/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
112
+ "tf_mistral_for_causal_lm/model/layers.19/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
113
+ "tf_mistral_for_causal_lm/model/layers.19/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
114
+ "tf_mistral_for_causal_lm/model/layers.19/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
115
+ "tf_mistral_for_causal_lm/model/layers.19/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
116
+ "tf_mistral_for_causal_lm/model/layers.2/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
117
+ "tf_mistral_for_causal_lm/model/layers.2/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
118
+ "tf_mistral_for_causal_lm/model/layers.2/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
119
+ "tf_mistral_for_causal_lm/model/layers.2/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
120
+ "tf_mistral_for_causal_lm/model/layers.2/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
121
+ "tf_mistral_for_causal_lm/model/layers.2/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
122
+ "tf_mistral_for_causal_lm/model/layers.2/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
123
+ "tf_mistral_for_causal_lm/model/layers.2/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
124
+ "tf_mistral_for_causal_lm/model/layers.2/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
125
+ "tf_mistral_for_causal_lm/model/layers.20/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
126
+ "tf_mistral_for_causal_lm/model/layers.20/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
127
+ "tf_mistral_for_causal_lm/model/layers.20/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
128
+ "tf_mistral_for_causal_lm/model/layers.20/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
129
+ "tf_mistral_for_causal_lm/model/layers.20/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
130
+ "tf_mistral_for_causal_lm/model/layers.20/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
131
+ "tf_mistral_for_causal_lm/model/layers.20/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
132
+ "tf_mistral_for_causal_lm/model/layers.20/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
133
+ "tf_mistral_for_causal_lm/model/layers.20/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
134
+ "tf_mistral_for_causal_lm/model/layers.21/input_layernorm/weight:0": "tf_model-00002-of-00003.h5",
135
+ "tf_mistral_for_causal_lm/model/layers.21/mlp/down_proj/kernel:0": "tf_model-00002-of-00003.h5",
136
+ "tf_mistral_for_causal_lm/model/layers.21/mlp/gate_proj/kernel:0": "tf_model-00002-of-00003.h5",
137
+ "tf_mistral_for_causal_lm/model/layers.21/mlp/up_proj/kernel:0": "tf_model-00002-of-00003.h5",
138
+ "tf_mistral_for_causal_lm/model/layers.21/post_attention_layernorm/weight:0": "tf_model-00002-of-00003.h5",
139
+ "tf_mistral_for_causal_lm/model/layers.21/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
140
+ "tf_mistral_for_causal_lm/model/layers.21/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
141
+ "tf_mistral_for_causal_lm/model/layers.21/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
142
+ "tf_mistral_for_causal_lm/model/layers.21/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
143
+ "tf_mistral_for_causal_lm/model/layers.22/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
144
+ "tf_mistral_for_causal_lm/model/layers.22/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
145
+ "tf_mistral_for_causal_lm/model/layers.22/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
146
+ "tf_mistral_for_causal_lm/model/layers.22/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
147
+ "tf_mistral_for_causal_lm/model/layers.22/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
148
+ "tf_mistral_for_causal_lm/model/layers.22/self_attn/k_proj/kernel:0": "tf_model-00002-of-00003.h5",
149
+ "tf_mistral_for_causal_lm/model/layers.22/self_attn/o_proj/kernel:0": "tf_model-00002-of-00003.h5",
150
+ "tf_mistral_for_causal_lm/model/layers.22/self_attn/q_proj/kernel:0": "tf_model-00002-of-00003.h5",
151
+ "tf_mistral_for_causal_lm/model/layers.22/self_attn/v_proj/kernel:0": "tf_model-00002-of-00003.h5",
152
+ "tf_mistral_for_causal_lm/model/layers.23/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
153
+ "tf_mistral_for_causal_lm/model/layers.23/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
154
+ "tf_mistral_for_causal_lm/model/layers.23/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
155
+ "tf_mistral_for_causal_lm/model/layers.23/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
156
+ "tf_mistral_for_causal_lm/model/layers.23/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
157
+ "tf_mistral_for_causal_lm/model/layers.23/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
158
+ "tf_mistral_for_causal_lm/model/layers.23/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
159
+ "tf_mistral_for_causal_lm/model/layers.23/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
160
+ "tf_mistral_for_causal_lm/model/layers.23/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
161
+ "tf_mistral_for_causal_lm/model/layers.24/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
162
+ "tf_mistral_for_causal_lm/model/layers.24/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
163
+ "tf_mistral_for_causal_lm/model/layers.24/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
164
+ "tf_mistral_for_causal_lm/model/layers.24/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
165
+ "tf_mistral_for_causal_lm/model/layers.24/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
166
+ "tf_mistral_for_causal_lm/model/layers.24/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
167
+ "tf_mistral_for_causal_lm/model/layers.24/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
168
+ "tf_mistral_for_causal_lm/model/layers.24/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
169
+ "tf_mistral_for_causal_lm/model/layers.24/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
170
+ "tf_mistral_for_causal_lm/model/layers.25/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
171
+ "tf_mistral_for_causal_lm/model/layers.25/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
172
+ "tf_mistral_for_causal_lm/model/layers.25/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
173
+ "tf_mistral_for_causal_lm/model/layers.25/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
174
+ "tf_mistral_for_causal_lm/model/layers.25/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
175
+ "tf_mistral_for_causal_lm/model/layers.25/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
176
+ "tf_mistral_for_causal_lm/model/layers.25/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
177
+ "tf_mistral_for_causal_lm/model/layers.25/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
178
+ "tf_mistral_for_causal_lm/model/layers.25/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
179
+ "tf_mistral_for_causal_lm/model/layers.26/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
180
+ "tf_mistral_for_causal_lm/model/layers.26/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
181
+ "tf_mistral_for_causal_lm/model/layers.26/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
182
+ "tf_mistral_for_causal_lm/model/layers.26/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
183
+ "tf_mistral_for_causal_lm/model/layers.26/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
184
+ "tf_mistral_for_causal_lm/model/layers.26/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
185
+ "tf_mistral_for_causal_lm/model/layers.26/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
186
+ "tf_mistral_for_causal_lm/model/layers.26/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
187
+ "tf_mistral_for_causal_lm/model/layers.26/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
188
+ "tf_mistral_for_causal_lm/model/layers.27/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
189
+ "tf_mistral_for_causal_lm/model/layers.27/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
190
+ "tf_mistral_for_causal_lm/model/layers.27/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
191
+ "tf_mistral_for_causal_lm/model/layers.27/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
192
+ "tf_mistral_for_causal_lm/model/layers.27/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
193
+ "tf_mistral_for_causal_lm/model/layers.27/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
194
+ "tf_mistral_for_causal_lm/model/layers.27/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
195
+ "tf_mistral_for_causal_lm/model/layers.27/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
196
+ "tf_mistral_for_causal_lm/model/layers.27/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
197
+ "tf_mistral_for_causal_lm/model/layers.28/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
198
+ "tf_mistral_for_causal_lm/model/layers.28/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
199
+ "tf_mistral_for_causal_lm/model/layers.28/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
200
+ "tf_mistral_for_causal_lm/model/layers.28/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
201
+ "tf_mistral_for_causal_lm/model/layers.28/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
202
+ "tf_mistral_for_causal_lm/model/layers.28/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
203
+ "tf_mistral_for_causal_lm/model/layers.28/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
204
+ "tf_mistral_for_causal_lm/model/layers.28/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
205
+ "tf_mistral_for_causal_lm/model/layers.28/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
206
+ "tf_mistral_for_causal_lm/model/layers.29/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
207
+ "tf_mistral_for_causal_lm/model/layers.29/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
208
+ "tf_mistral_for_causal_lm/model/layers.29/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
209
+ "tf_mistral_for_causal_lm/model/layers.29/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
210
+ "tf_mistral_for_causal_lm/model/layers.29/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
211
+ "tf_mistral_for_causal_lm/model/layers.29/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
212
+ "tf_mistral_for_causal_lm/model/layers.29/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
213
+ "tf_mistral_for_causal_lm/model/layers.29/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
214
+ "tf_mistral_for_causal_lm/model/layers.29/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
215
+ "tf_mistral_for_causal_lm/model/layers.3/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
216
+ "tf_mistral_for_causal_lm/model/layers.3/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
217
+ "tf_mistral_for_causal_lm/model/layers.3/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
218
+ "tf_mistral_for_causal_lm/model/layers.3/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
219
+ "tf_mistral_for_causal_lm/model/layers.3/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
220
+ "tf_mistral_for_causal_lm/model/layers.3/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
221
+ "tf_mistral_for_causal_lm/model/layers.3/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
222
+ "tf_mistral_for_causal_lm/model/layers.3/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
223
+ "tf_mistral_for_causal_lm/model/layers.3/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
224
+ "tf_mistral_for_causal_lm/model/layers.30/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
225
+ "tf_mistral_for_causal_lm/model/layers.30/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
226
+ "tf_mistral_for_causal_lm/model/layers.30/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
227
+ "tf_mistral_for_causal_lm/model/layers.30/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
228
+ "tf_mistral_for_causal_lm/model/layers.30/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
229
+ "tf_mistral_for_causal_lm/model/layers.30/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
230
+ "tf_mistral_for_causal_lm/model/layers.30/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
231
+ "tf_mistral_for_causal_lm/model/layers.30/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
232
+ "tf_mistral_for_causal_lm/model/layers.30/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
233
+ "tf_mistral_for_causal_lm/model/layers.31/input_layernorm/weight:0": "tf_model-00003-of-00003.h5",
234
+ "tf_mistral_for_causal_lm/model/layers.31/mlp/down_proj/kernel:0": "tf_model-00003-of-00003.h5",
235
+ "tf_mistral_for_causal_lm/model/layers.31/mlp/gate_proj/kernel:0": "tf_model-00003-of-00003.h5",
236
+ "tf_mistral_for_causal_lm/model/layers.31/mlp/up_proj/kernel:0": "tf_model-00003-of-00003.h5",
237
+ "tf_mistral_for_causal_lm/model/layers.31/post_attention_layernorm/weight:0": "tf_model-00003-of-00003.h5",
238
+ "tf_mistral_for_causal_lm/model/layers.31/self_attn/k_proj/kernel:0": "tf_model-00003-of-00003.h5",
239
+ "tf_mistral_for_causal_lm/model/layers.31/self_attn/o_proj/kernel:0": "tf_model-00003-of-00003.h5",
240
+ "tf_mistral_for_causal_lm/model/layers.31/self_attn/q_proj/kernel:0": "tf_model-00003-of-00003.h5",
241
+ "tf_mistral_for_causal_lm/model/layers.31/self_attn/v_proj/kernel:0": "tf_model-00003-of-00003.h5",
242
+ "tf_mistral_for_causal_lm/model/layers.4/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
243
+ "tf_mistral_for_causal_lm/model/layers.4/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
244
+ "tf_mistral_for_causal_lm/model/layers.4/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
245
+ "tf_mistral_for_causal_lm/model/layers.4/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
246
+ "tf_mistral_for_causal_lm/model/layers.4/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
247
+ "tf_mistral_for_causal_lm/model/layers.4/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
248
+ "tf_mistral_for_causal_lm/model/layers.4/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
249
+ "tf_mistral_for_causal_lm/model/layers.4/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
250
+ "tf_mistral_for_causal_lm/model/layers.4/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
251
+ "tf_mistral_for_causal_lm/model/layers.5/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
252
+ "tf_mistral_for_causal_lm/model/layers.5/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
253
+ "tf_mistral_for_causal_lm/model/layers.5/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
254
+ "tf_mistral_for_causal_lm/model/layers.5/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
255
+ "tf_mistral_for_causal_lm/model/layers.5/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
256
+ "tf_mistral_for_causal_lm/model/layers.5/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
257
+ "tf_mistral_for_causal_lm/model/layers.5/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
258
+ "tf_mistral_for_causal_lm/model/layers.5/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
259
+ "tf_mistral_for_causal_lm/model/layers.5/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
260
+ "tf_mistral_for_causal_lm/model/layers.6/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
261
+ "tf_mistral_for_causal_lm/model/layers.6/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
262
+ "tf_mistral_for_causal_lm/model/layers.6/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
263
+ "tf_mistral_for_causal_lm/model/layers.6/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
264
+ "tf_mistral_for_causal_lm/model/layers.6/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
265
+ "tf_mistral_for_causal_lm/model/layers.6/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
266
+ "tf_mistral_for_causal_lm/model/layers.6/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
267
+ "tf_mistral_for_causal_lm/model/layers.6/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
268
+ "tf_mistral_for_causal_lm/model/layers.6/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
269
+ "tf_mistral_for_causal_lm/model/layers.7/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
270
+ "tf_mistral_for_causal_lm/model/layers.7/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
271
+ "tf_mistral_for_causal_lm/model/layers.7/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
272
+ "tf_mistral_for_causal_lm/model/layers.7/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
273
+ "tf_mistral_for_causal_lm/model/layers.7/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
274
+ "tf_mistral_for_causal_lm/model/layers.7/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
275
+ "tf_mistral_for_causal_lm/model/layers.7/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
276
+ "tf_mistral_for_causal_lm/model/layers.7/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
277
+ "tf_mistral_for_causal_lm/model/layers.7/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
278
+ "tf_mistral_for_causal_lm/model/layers.8/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
279
+ "tf_mistral_for_causal_lm/model/layers.8/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
280
+ "tf_mistral_for_causal_lm/model/layers.8/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
281
+ "tf_mistral_for_causal_lm/model/layers.8/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
282
+ "tf_mistral_for_causal_lm/model/layers.8/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
283
+ "tf_mistral_for_causal_lm/model/layers.8/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
284
+ "tf_mistral_for_causal_lm/model/layers.8/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
285
+ "tf_mistral_for_causal_lm/model/layers.8/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
286
+ "tf_mistral_for_causal_lm/model/layers.8/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
287
+ "tf_mistral_for_causal_lm/model/layers.9/input_layernorm/weight:0": "tf_model-00001-of-00003.h5",
288
+ "tf_mistral_for_causal_lm/model/layers.9/mlp/down_proj/kernel:0": "tf_model-00001-of-00003.h5",
289
+ "tf_mistral_for_causal_lm/model/layers.9/mlp/gate_proj/kernel:0": "tf_model-00001-of-00003.h5",
290
+ "tf_mistral_for_causal_lm/model/layers.9/mlp/up_proj/kernel:0": "tf_model-00001-of-00003.h5",
291
+ "tf_mistral_for_causal_lm/model/layers.9/post_attention_layernorm/weight:0": "tf_model-00001-of-00003.h5",
292
+ "tf_mistral_for_causal_lm/model/layers.9/self_attn/k_proj/kernel:0": "tf_model-00001-of-00003.h5",
293
+ "tf_mistral_for_causal_lm/model/layers.9/self_attn/o_proj/kernel:0": "tf_model-00001-of-00003.h5",
294
+ "tf_mistral_for_causal_lm/model/layers.9/self_attn/q_proj/kernel:0": "tf_model-00001-of-00003.h5",
295
+ "tf_mistral_for_causal_lm/model/layers.9/self_attn/v_proj/kernel:0": "tf_model-00001-of-00003.h5",
296
+ "tf_mistral_for_causal_lm/model/norm/weight:0": "tf_model-00003-of-00003.h5"
297
+ }
298
+ }