grantner commited on
Commit
00e2446
·
verified ·
1 Parent(s): cfec3a9

feat: model checkpoint

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
LLAMA_LICENSE ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LLAMA 3.1 COMMUNITY LICENSE AGREEMENT
2
+ Llama 3.1 Version Release Date: July 23, 2024
3
+
4
+ “Agreement” means the terms and conditions for use, reproduction, distribution and modification of the
5
+ Llama Materials set forth herein.
6
+
7
+ “Documentation” means the specifications, manuals and documentation accompanying Llama 3.1
8
+ distributed by Meta at https://llama.meta.com/doc/overview.
9
+
10
+ “Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into
11
+ this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
12
+ regulations to provide legal consent and that has legal authority to bind your employer or such other
13
+ person or entity if you are entering in this Agreement on their behalf.
14
+
15
+ “Llama 3.1” means the foundational large language models and software and algorithms, including
16
+ machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
17
+ fine-tuning enabling code and other elements of the foregoing distributed by Meta at
18
+ https://llama.meta.com/llama-downloads.
19
+
20
+ “Llama Materials” means, collectively, Meta’s proprietary Llama 3.1 and Documentation (and any
21
+ portion thereof) made available under this Agreement.
22
+
23
+ “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
24
+ principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
25
+ outside of the EEA or Switzerland).
26
+
27
+ By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
28
+ you agree to be bound by this Agreement.
29
+
30
+ 1. License Rights and Redistribution.
31
+
32
+ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
33
+ limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
34
+ Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
35
+ Llama Materials.
36
+
37
+ b. Redistribution and Use.
38
+
39
+ i. If you distribute or make available the Llama Materials (or any derivative works
40
+ thereof), or a product or service (including another AI model) that contains any of them, you shall (A)
41
+ provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with
42
+ Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use
43
+ the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
44
+ otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at
45
+ the beginning of any such AI model name.
46
+
47
+ ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
48
+ of an integrated end user product, then Section 2 of this Agreement will not apply to you.
49
+
50
+ iii. You must retain in all copies of the Llama Materials that you distribute the following
51
+ attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.1 is
52
+ licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights
53
+ Reserved.”
54
+
55
+ iv. Your use of the Llama Materials must comply with applicable laws and regulations
56
+ (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
57
+ Materials (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated by
58
+ reference into this Agreement.
59
+
60
+ 2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users
61
+ of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
62
+ million monthly active users in the preceding calendar month, you must request a license from Meta,
63
+ which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
64
+ rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
65
+
66
+ 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
67
+ OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
68
+ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
69
+ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
70
+ MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
71
+ DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
72
+ ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
73
+ RESULTS.
74
+
75
+ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
76
+ LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
77
+ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
78
+ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
79
+ OF THE POSSIBILITY OF ANY OF THE FOREGOING.
80
+
81
+ 5. Intellectual Property.
82
+
83
+ a. No trademark licenses are granted under this Agreement, and in connection with the Llama
84
+ Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
85
+ or any of its affiliates, except as required for reasonable and customary use in describing and
86
+ redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
87
+ use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
88
+ comply with Meta’s brand guidelines (currently accessible at
89
+ https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
90
+ of the Mark will inure to the benefit of Meta.
91
+
92
+ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
93
+ respect to any derivative works and modifications of the Llama Materials that are made by you, as
94
+ between you and Meta, you are and will be the owner of such derivative works and modifications.
95
+
96
+ c. If you institute litigation or other proceedings against Meta or any entity (including a
97
+ cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or
98
+ results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
99
+ rights owned or licensable by you, then any licenses granted to you under this Agreement shall
100
+ terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
101
+ harmless Meta from and against any claim by any third party arising out of or related to your use or
102
+ distribution of the Llama Materials.
103
+
104
+ 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
105
+ Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
106
+ accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
107
+ breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
108
+ and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
109
+ Agreement.
110
+
111
+ 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
112
+ the State of California without regard to choice of law principles, and the UN Convention on Contracts
113
+ for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
114
+ exclusive jurisdiction of any dispute arising out of this Agreement.
NOTICE ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ llama-embed-mamba2-7b
2
+
3
+ Copyright 2026 the model authors.
4
+
5
+ This model was partially trained on synthetic data generated with Llama 3.1 70B.
6
+
7
+ Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
8
+
9
+ Built with Llama.
README.md ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mamba-Codestral-7B-v0.1
3
+ datasets:
4
+ - jspringer/open-synthetic-embeddings
5
+ library_name: sentence-transformers
6
+ license: apache-2.0
7
+ pipeline_tag: sentence-similarity
8
+ tags:
9
+ - sentence-transformers
10
+ - sentence-similarity
11
+ - feature-extraction
12
+ - mamba2
13
+ - vertical-chunking
14
+ ---
15
+
16
+ # llama-embed-mamba2-7b
17
+
18
+ **llama-embed-mamba2-7b** is a general-purpose text embedding model that reproduces the [e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct) training procedure on top of [Codestral Mamba2 7B](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1), a recurrent (state space model) architecture. It achieves **embedding quality competitive** with e5-mistral-7b-instruct and similarly trained transformer-based models while offering **linear-time** computational complexity and **constant-memory** inference through a novel vertically chunked inference strategy. This makes it substantially more efficient for long sequences and suitable for memory-constrained environments.
19
+
20
+ A smaller variant is available as [llama-embed-mamba2-1.3b](https://huggingface.co/dynatrace-oss/llama-embed-mamba2-1.3b).
21
+
22
+ > [!Note]
23
+ > **Built with Llama.** This model was partially trained on synthetic data generated with Llama 3.1 70B. See [License](#license) for details.
24
+
25
+ ## Performance
26
+
27
+ Aggregated task-mean benchmark results compared to the original e5-mistral-7b-instruct. For detailed results, see our [paper](#citation).
28
+
29
+ | Model | MTEB(Multilingual, v2) | MTEB(eng, v2) | LongEmbed |
30
+ |---|:-:|:-:|:-:|
31
+ | [**llama-embed-mamba2-1.3b**](https://huggingface.co/dynatrace-oss/llama-embed-mamba2-1.3b) | **55.2** | **64.3** | **40.8** |
32
+ | **llama-embed-mamba2-7b** (this model) | **59.4** | **65.2** | **44.5** |
33
+ | [e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct) | 60.2 | 68.0 | 43.7 |
34
+
35
+ ## Vertically Chunked Inference
36
+
37
+ This model supports **vertically chunked inference**, which achieves **constant memory usage** regardless of input sequence length. Instead of processing the full sequence through one layer at a time (standard horizontal inference), this approach:
38
+
39
+ 1. Partitions the input into fixed-size vertical chunks
40
+ 2. Processes each chunk through **all** model layers before advancing to the next
41
+ 3. Maintains the recurrent states across chunks, preserving full context
42
+
43
+ Parallelization benefits saturate at comparatively small chunk sizes, so processing in fixed-size blocks incurs negligible runtime overhead while dramatically reducing memory consumption. This makes the model particularly advantageous for long documents, resource-constrained environments, and large-batch processing where transformer memory requirements become prohibitive. Additional information can be found in our [paper](#citation).
44
+
45
+ ## Usage
46
+
47
+ > [!IMPORTANT]
48
+ > Requires `transformers>=5.5.0` due to a breaking change to the cache of Mamba2 introduced in `v5.5.0` ([transformers#44950](https://github.com/huggingface/transformers/pull/44950)).
49
+
50
+ To utilize the efficient kernel implementations enabling vertically chunked inference, the following libraries must be installed in addition to `sentence-transformers`/`transformers`:
51
+
52
+ ```bash
53
+ pip install kernels einops
54
+ ```
55
+
56
+ ### Sentence Transformers
57
+
58
+ ```python
59
+ from sentence_transformers import SentenceTransformer
60
+
61
+ model = SentenceTransformer("dynatrace-oss/llama-embed-mamba2-7b", trust_remote_code=True)
62
+
63
+ queries = [
64
+ "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: What is a state space model?",
65
+ ]
66
+ documents = [
67
+ "A state space model (SSM) is a mathematical framework that describes a system using state variables.",
68
+ "Embedding models map text to dense vector representations that capture semantic meaning.",
69
+ ]
70
+
71
+ query_embeddings = model.encode(queries)
72
+ document_embeddings = model.encode(documents)
73
+
74
+ similarities = model.similarity(query_embeddings, document_embeddings)
75
+ print(similarities)
76
+ ```
77
+
78
+ For long inputs, pass `vertical_chunk_size` to enable constant-memory inference. The value should be a multiple of 256 (the intra-layer chunk size). Recommended: largest value that fits in memory for single sequences, 256 or 512 for larger batches.
79
+
80
+ ```python
81
+ embeddings = model.encode(
82
+ ["Your long document text here..."],
83
+ vertical_chunk_size=512,
84
+ )
85
+ ```
86
+
87
+ ### Transformers
88
+
89
+ ```python
90
+ import torch
91
+ import torch.nn.functional as F
92
+ from transformers import AutoModel, AutoTokenizer
93
+
94
+ tokenizer = AutoTokenizer.from_pretrained("dynatrace-oss/llama-embed-mamba2-7b")
95
+ model = AutoModel.from_pretrained(
96
+ "dynatrace-oss/llama-embed-mamba2-7b", trust_remote_code=True, torch_dtype=torch.bfloat16
97
+ ).eval().cuda()
98
+
99
+ def encode(texts):
100
+ inputs = tokenizer(texts, return_tensors="pt", padding=True).to(model.device)
101
+ with torch.no_grad():
102
+ outputs = model(**inputs)
103
+ embeddings = outputs.last_hidden_state[:, -1, :]
104
+ return F.normalize(embeddings, p=2, dim=-1)
105
+
106
+ queries = [
107
+ "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: What is a state space model?",
108
+ ]
109
+ documents = [
110
+ "A state space model (SSM) is a mathematical framework that describes a system using state variables.",
111
+ "Embedding models map text to dense vector representations that capture semantic meaning.",
112
+ ]
113
+
114
+ query_embeddings = encode(queries)
115
+ document_embeddings = encode(documents)
116
+
117
+ similarities = query_embeddings @ document_embeddings.T
118
+ print(similarities)
119
+ ```
120
+
121
+ For long inputs, process the input in vertical chunks to maintain constant memory usage. The `vertical_chunk_size` must be a multiple of 256 (the intra-layer chunk size).
122
+
123
+ ```python
124
+ text = "Your long document text here..."
125
+ inputs = tokenizer(text, return_tensors="pt").to(model.device)
126
+
127
+ vertical_chunk_size = 512
128
+ cache_params = None
129
+ for chunk_start in range(0, inputs["input_ids"].size(1), vertical_chunk_size):
130
+ chunk_end = chunk_start + vertical_chunk_size
131
+ chunk_inputs = {
132
+ k: v[:, chunk_start:chunk_end]
133
+ for k, v in inputs.items() if k != "attention_mask"
134
+ }
135
+ chunk_inputs["attention_mask"] = inputs["attention_mask"][:, :chunk_end]
136
+ with torch.no_grad():
137
+ outputs = model(**chunk_inputs, use_cache=True, cache_params=cache_params)
138
+ cache_params = outputs.cache_params
139
+
140
+ embedding = outputs.last_hidden_state[:, -1, :]
141
+ embedding = F.normalize(embedding, p=2, dim=-1)
142
+ ```
143
+
144
+ ## Open Source Integration Roadmap
145
+
146
+ Our goal is to integrate all necessary changes to simplify the adoption of vertically chunked inference for other models:
147
+
148
+ > [!Note]
149
+ > ⚪ Planned | 🟡 In Progress | 🟢 Integrated
150
+
151
+ - ⚪ **causal-conv1d:** Enable simultaneous `seq_idx` + `initial_states` (required for recurrent processing with left padding)
152
+ - ⚪ **mamba-ssm:** Use `seq_idx` + `initial_states` in `mamba_split_conv1d_scan_combined` and export final states
153
+ - ⚪ **kernels-community:** Propagate changes in `causal-conv1d` and `mamba-ssm` to their kernel hub equivalents in the `kernels-community` repositories
154
+ - ⚪ **transformers:** Use updated `mamba_split_conv1d_scan_combined` with cache params during inference (currently only used during training, not configurable, problems with left padding)
155
+ - ⚪ **sentence-transformers:** Native vertical chunking support
156
+
157
+ *This list will be updated as integration progresses.*
158
+
159
+ ## Code Repositories
160
+
161
+ The custom model and inference code used by this model is maintained in two separate repositories so that it can be shared between model checkpoints:
162
+
163
+ - [dynatrace-oss/chunkable-mamba2](https://huggingface.co/dynatrace-oss/chunkable-mamba2): Adjusted Mamba2 kernel and model & configuration classes with recurrent chunked inference support.
164
+ - [dynatrace-oss/chunkable-sentence-transformer](https://huggingface.co/dynatrace-oss/chunkable-sentence-transformer): Sentence Transformers modules (`ChunkableTransformer`, `LastIndexPooling`) enabling constant-memory encoding.
165
+
166
+ ## License
167
+
168
+ This model is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). The training dataset ([open-synthetic-embeddings](https://huggingface.co/datasets/jspringer/open-synthetic-embeddings)) is licensed under MIT.
169
+
170
+ **Llama 3.1 Community License:** This model was partially trained on synthetic data generated with Llama 3.1 70B. Use of this model is subject to the [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/) and the [Llama 3.1 Acceptable Use Policy](https://www.llama.com/llama3_1/use-policy/). A copy of the Llama 3.1 license is included in the [`LLAMA_LICENSE`](LLAMA_LICENSE) file. Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
171
+
172
+ ## Usage Considerations
173
+
174
+ This model is intended for the generation of text embeddings for retrieval, clustering, classification, and similar tasks.
175
+
176
+ Embedding models can reflect biases present in their pretraining and fine-tuning data. Users should evaluate the model for fairness in their specific use case and combine model outputs with human verification for applications where embedding quality could materially impact individuals or decisions. This model must not be used for any application prohibited by the [Llama 3.1 Acceptable Use Policy](https://www.llama.com/llama3_1/use-policy/) or in any manner that violates applicable laws and regulations.
177
+
178
+ ## Citation
179
+
180
+ > [!Note]
181
+ > Coming soon!
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ChunkableMamba2Model"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "dynatrace-oss/chunkable-mamba2--configuration_chunkable_mamba2.ChunkableMamba2Config",
7
+ "AutoModel": "dynatrace-oss/chunkable-mamba2--modeling_chunkable_mamba2.ChunkableMamba2Model"
8
+ },
9
+ "bos_token_id": 0,
10
+ "chunk_size": 256,
11
+ "conv_kernel": 4,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 0,
14
+ "expand": 2,
15
+ "head_dim": 64,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "initializer_range": 0.1,
19
+ "intermediate_size": 8192,
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "mamba2",
22
+ "n_groups": 8,
23
+ "norm_before_gate": true,
24
+ "num_heads": 128,
25
+ "num_hidden_layers": 64,
26
+ "pad_token_id": 0,
27
+ "rescale_prenorm_residual": false,
28
+ "residual_in_fp32": true,
29
+ "rms_norm": true,
30
+ "state_size": 128,
31
+ "tie_word_embeddings": false,
32
+ "time_step_floor": 0.0001,
33
+ "time_step_init_scheme": "random",
34
+ "time_step_limit": [
35
+ 0.0,
36
+ {
37
+ "__float__": "Infinity"
38
+ }
39
+ ],
40
+ "time_step_max": 0.1,
41
+ "time_step_min": 0.001,
42
+ "time_step_rank": 256,
43
+ "time_step_scale": 1.0,
44
+ "transformers_version": "5.5.0",
45
+ "use_bias": false,
46
+ "use_cache": false,
47
+ "use_conv_bias": true,
48
+ "use_mem_eff_path": true,
49
+ "vocab_size": 32768
50
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.4.1",
5
+ "transformers": "5.5.4",
6
+ "pytorch": "2.9.1"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e367c39c7c76e409015a9addae9ddb697ad46e2c30344b6717c40775c66ba65
3
+ size 14302430240
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "dynatrace-oss/chunkable-sentence-transformer--models.ChunkableTransformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_LastIndexPooling",
12
+ "type": "dynatrace-oss/chunkable-sentence-transformer--models.LastIndexPooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "output_all_token_embeddings": false
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": true,
8
+ "pad_token": "</s>",
9
+ "padding_side": "left",
10
+ "sp_model_kwargs": {},
11
+ "spaces_between_special_tokens": false,
12
+ "tokenizer_class": "LlamaTokenizer",
13
+ "unk_token": "<unk>",
14
+ "use_default_system_prompt": false
15
+ }