Upload TFMistralForCausalLM
Browse files- README.md +39 -21
- config.json +1 -1
- tf_model-00001-of-00003.h5 +3 -0
- tf_model-00002-of-00003.h5 +3 -0
- tf_model-00003-of-00003.h5 +3 -0
- tf_model.h5.index.json +298 -0
README.md
CHANGED
@@ -1,29 +1,47 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
tags:
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
|
7 |
-
|
8 |
|
9 |
-
|
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
|
|
|
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 |
-
|
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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "
|
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 |
+
}
|