Trelis

264 models • 1 total models in database
Sort by:

Llama-2-7b-chat-hf-function-calling-v2

NaNK
llama
825
137

Llama-2-7b-chat-hf-function-calling-v3

NaNK
llama
184
41

whisper-tiny-llm-lingo

—
93
0

whisper-small-llm-lingo

—
91
3

Qwen3-4B-Thinking-2507_ds-arc-agi-2-reasoning-5-c89

NaNK
license:apache-2.0
55
0

TinyLlama-1.1B-intermediate-step-480k-1T-GGUF

NaNK
llama
47
1

transcribe-en_gb-spelling-v1-tiny

license:mit
33
0

TinyLlama-1.1B-Chat-v0.2-GGUF

NaNK
license:apache-2.0
32
0

transcribe-en_gb-spelling-v1-tiny-ctranslate2

license:mit
27
0

Llama-2-7b-chat-hf-function-calling-GPTQ

NaNK
llama
25
4

Qwen3-4B-Thinking-2507_ds-arc-agi-2-reasoning-5-c178

NaNK
license:apache-2.0
20
0

transcribe-en_us-spelling-v1-tiny

license:mit
18
0

transcribe-british-spelling-v1-tiny

—
17
0

Qwen3-4B_ds-arc-agi-2-perfect-100_test-c4

NaNK
license:apache-2.0
17
0

TinyLlama-1.1B-Chat-v0.1-GGUF

NaNK
tinyllama
16
4

incorrect2874__partial2114_ties

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

—
16
0

Qwen3-4B_dsarc-programs-50-full-200-incorrect_20250808-134330-c5748

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

NaNK
—
15
0

incorrect2874__partial2114_linear

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

—
15
0

Llama-2-7b-chat-hf-sharded-bf16

NaNK
llama
14
13

SmolLM-135M-layer-pruned-90M-raw

llama
14
0

Qwen3-4B_dsarc-programs-correct-50_20250806-233716

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-correct-10_20250806-233707-c132

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-correct-10_20250806-233707-c176

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-correct-50_20250806-233716-c453

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-correct-50_20250806-233716-c604

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c1057

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c4228

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-50-full-200-incorrect_20250808-134330-trainercheckpoint-2874-temp

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

gpt-oss-20b_ds-arc-agi-2-partialplus-max-c1421

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
14
0

Qwen3-4B_dsarc-programs-correct-10_20250806-233707

NaNK
license:apache-2.0
13
0

Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c3171

NaNK
license:apache-2.0
13
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-221545_cst-c2712

NaNK
license:apache-2.0
13
0

Qwen3-4B_ds-arc-agi-1-perfect-50-c321

NaNK
license:apache-2.0
13
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10-c120

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
13
0

99-instruct-v9

llama
12
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-113400-100stps-c75

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
12
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-124700-100s-pz-c100

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
12
0

Qwen3-4B_ds-parquet-programs-c24

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
12
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-arc-agi-2-training-hard-curriculum-c262

NaNK
license:apache-2.0
12
0

gpt-oss-20b-BF16_ds-arc-agi-2-reasoning-5_test-c1

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-BF16 This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
12
0

Qwen3-4B_ds-arc-agi-2-reasoning-5-c178

NaNK
license:apache-2.0
12
0

Qwen3-4B_ds-arc-agi-2-reasoning-5-c89

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
12
0

Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c2114

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-113400-100stps-c25

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-113400-100stps-c50

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-113400-100stps-c100

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-121308-100s4b4-c25

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-121606-4b4fa-c25

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-121606-4b4fa-c75

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-121606-4b4fa-c100

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-124700-100s-pz-c25

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-124700-100s-pz-c75

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-125017-100s2e-4-c25

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-125017-100s2e-4-c50

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-125017-100s2e-4-c75

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-125017-100s2e-4-c100

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-133320-c1

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-133320-c2

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-133320-c75

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-154450-c10

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-155856-c904

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-155856-c1808

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-155856-c2712

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-155856-c3614

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-221545_cst-c904

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-221545_cst-c1808

NaNK
license:apache-2.0
11
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-221545_cst-c3614

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-partialplus-c56

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-partialplus-c112

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-partialplus-c168

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-partialplus-c224

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-blended-c201

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-blended-c402

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-blended-c603

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-blended-c802

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-all-c148

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-all-c296

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-all-c444

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

arc-1-fake-ttt-unblended-all-c592

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bdsarc-programs-50-full-200-partial20250807-211749-c3171 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-perfect-100_test-c8

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-perfect-50-c485

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-perfect-50-c970

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c1574

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-perfect-50_test-c4

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-perfect-50_test-c8

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-perfect-50_test-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-perfect-50_test-c8

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100_test-c4

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100_test-c8

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c8

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c771

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c1542

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-parquet-programs-c1403

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-parquet-programs-c2806

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-parquet-programs-c12

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c8

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c1403

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10_test-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10_test-c8

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10-c8

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-tricky-10-c60

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-arc-agi-2-training-hard-curriculum-c131

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c1542_ds-arc-agi-1-refinement-finetuning-c81

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-partial-100-c1542_ds-arc-agi-1-refinement-finetuning-c162

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-20_test-c4

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-20_test-c8

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-2-partial-20-c976

NaNK
license:apache-2.0
11
0

Qwen3-4B_ds-arc-agi-1-refinement-finetuning-partialplus-c552

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

gpt-oss-20b_ds-arc-agi-2-reasoning-5-c89

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
11
0

Meta-Llama-3-8B-Instruct-function-calling

NaNK
llama
10
44

transcribe-en_gb-spelling-v1-turbo

—
10
0

transcribe-en_us-spelling-v1-turbo

—
10
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-121606-4b4fa-c50

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
10
0

Qwen3-4B_dsarc-agi-1-train-programs-best-length-filtered-250_20250811-124700-100s-pz-c50

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-arc-agi-2-partial-100-c3148

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-parquet-programs_test-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-parquet-programs_test-c8

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-arc-agi-2-training-hard-curriculum-c4

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets-c2

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bds-arc-agi-2-partial-100-c2806 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
10
0

Qwen3-4B_ds-arc-agi-1-perfect-50-c642

NaNK
license:apache-2.0
9
0

test-oss-c1

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-BF16 This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
9
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets_rLoRA-32-c2

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bds-arc-agi-2-partial-100-c2806 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
9
0

smol-v7-sc-temporal_aa1

—
9
0

mpt-7b-8k-chat-sharded-bf16

NaNK
license:cc-by-nc-sa-4.0
8
1

Llama-2-7b-chat-hf-function-calling

NaNK
llama
7
48

Qwen3-4B-ds20250724_131808-20250725-132523

NaNK
license:apache-2.0
7
0

Qwen3-4B-ds20250729_114431-20250729-113936

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
7
0

smol-v7-1M_aa2

—
7
0

TinyLlama-1.1B-Chat-v0.3-AWQ

NaNK
llama
6
0

Mistral-Small-3.1-24B-Instruct-2503-touch-rugby-comprehensive-qa

NaNK
license:apache-2.0
6
0

Qwen3-4B-ds20250729_114431-20250729-115543

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
6
0

Qwen3-4B-ds20250729_114431-20250729-123351

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
6
0

Qwen3-4B-ds20250729_114431-20250729-142811

NaNK
license:apache-2.0
6
0

Soar-qwen-7b-ds20250729_114431-20250731-140526

NaNK
license:apache-2.0
6
0

Qwen3-4B-ds20250729_114431-20250801-141514

NaNK
license:apache-2.0
6
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets_rLoRA-32-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bds-arc-agi-2-partial-100-c2806 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
6
0

Soar-qwen-14b-FP8-Dynamic

NaNK
—
6
0

Llama-2-7b-chat-hf-hosted-inference-8bit

NaNK
llama
5
7

Llama-2-7b-chat-hf-sharded-bf16-5GB

NaNK
llama
5
3

mamba-2.8b-slimpj-bf16

NaNK
license:apache-2.0
5
1

Qwen1.5-MLX-test

—
5
1

SmolLM-135M-Instruct-layer-pruned-90M-raw

llama
5
1

transcribe-british-spelling-v1-tiny-ctranslate2

—
5
0

TrelisSmolLM-base

llama
5
0

Soar-qwen-7b-ds20250724_131808-20250725-130403

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : julien31/Soar-qwen-7b This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
5
0

Qwen3-4B-ds20250729_114431-20250729-111804

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
5
0

Mistral-7B-Instruct-v0.2-function-calling-v3

NaNK
—
4
10

Microsoft_Phi-4-FP8-Dynamic

—
4
1

whisper-large-v3-turbo-pilotgpt-unified-all-raw-no-pack-1s-merged-filtered

—
4
0

transcribe-en_us-spelling-v1-tiny-ctranslate2

license:mit
4
0

TinyLlama-1.1B-Chat-v1.0-bf16

NaNK
llama
4
0

OpenELM-450M-instruct-ORPO

—
4
0

Llama-3.2-1B-Instruct-MATH-3ep

NaNK
llama
4
0

act_so101_test

—
4
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets-c8

NaNK
license:apache-2.0
4
0

Llama-2-7b-hf-function-calling

NaNK
llama
3
0

all-MiniLM-L12-v2-ft-pairs-cosine

NaNK
—
3
0

multi-qa-MiniLM-L6-cos-v1-ft-pairs-1-epoch

NaNK
—
3
0

Llama-3.2-1B-Instruct-MATH-synthetic

NaNK
llama
3
0

SO-101-ACT

—
3
0

SO-101-ACT-beta_0.25

—
3
0

SO-101-ACT-n10

—
3
0

SO-101-ACT-n10_beta_1

—
3
0

SO-101-ACT-n10_beta_1_12500

—
3
0

SO-101-ACT-n10_k50

—
3
0

SO-101-SmolVLA-test

—
3
0

SO-101-ACT-test

—
3
0

lorge-16-jul

NaNK
license:apache-2.0
3
0

gemini_synth_10-22jul-test

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
3
0

Qwen3-4B-ds20250724_131808-20250725-142549

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
3
0

Qwen3-4B-ds20250729_114431-20250729-114617

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
3
0

gpt-oss-20b_ds-arc-agi-2-partialplus-max-c2842

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
3
0

llava-v1.6-mistral-7b-PATCHED

NaNK
license:apache-2.0
2
8

Llama-2-13b-chat-hf-touch-rugby-rules-adapters

NaNK
—
2
0

all-MiniLM-L12-v2-ft-triplets-10Qs

NaNK
—
2
0

Meta-Llama-3.1-8B-Instruct-Trelis-ARC-1ep-20241013-201317-ft

NaNK
llama
2
0

Llama-3.2-1B-Instruct-ft-comprehensive-qa

NaNK
license:apache-2.0
2
0

gemma-3-4b-it-ft-touch-rugby-comprehensive-qa

NaNK
license:apache-2.0
2
0

gemini-2.5-reasoning-smol-21-jul

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
2
0

Qwen2.5-Coder-7B-Instruct-gemini_synth_50_random_split_1_training-20250723-113848

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen2.5-Coder-7B-Instruct This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
2
0

qwen-soar-sft-23-jul

NaNK
license:apache-2.0
2
0

Qwen3-4B-ds20250729_114431-20250730-172810

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
2
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets-c4

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bds-arc-agi-2-partial-100-c2806 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
2
0

whisper-turbo-sample-uk-english

—
1
0

mpt-7b-instruct-hosted-inference-8bit

NaNK
license:cc-by-sa-3.0
1
0

TinyLlama-1.1B-intermediate-step-480k-1T-chat-llama-style

NaNK
llama
1
0

Llama-2-13b-chat-hf-stanford-nil-policy-adapters

NaNK
base_model:meta-llama/Llama-2-13b-chat-hf
1
0

Llama-2-7b-chat-hf-6k

NaNK
llama
1
0

falcon-7b-chat-commercially-licensed-adapters

NaNK
—
1
0

falcon-7b-chat-commercial-use-4k

NaNK
—
1
0

Llama-2-7b-hf-stanford-nil-policy-ft-push-demo

NaNK
llama
1
0

mamba-2.8b-slimpj-chat-4k

NaNK
license:apache-2.0
1
0

TinyLlama-chat-ORPO-beta0.2

NaNK
llama
1
0

all-MiniLM-L12-v2-ft-Llama-3-70B

NaNK
—
1
0

all-MiniLM-L12-v2-ft-pairs-balanced

NaNK
—
1
0

all-MiniLM-L12-v2-ft-pairs-balanced-cpu

NaNK
—
1
0

all-MiniLM-L12-v2-ft-triplets-10q

NaNK
—
1
0

multi-qa-MiniLM-L6-cos-v1-ft-pairs

NaNK
—
1
0

multi-qa-MiniLM-L6-cos-v1-ft-pairs-1-epoch-scale-20

NaNK
—
1
0

multi-qa-MiniLM-L6-cos-v1-ft-pairs-2-cos-epoch-s20

NaNK
—
1
0

multi-qa-MiniLM-L6-dot-v1-ft-pairs-4-cst-epoch-s1-overlap

NaNK
—
1
0

multi-qa-MiniLM-L6-dot-v1-ft-triplets-2-cst-epoch-overlap

NaNK
—
1
0

SmolLM-360M-width-depth-pruned-to-80M

llama
1
0

Llama-3.2-3B-Instruct-MATH-ft

NaNK
llama
1
0

Llama-3.2-1B-Instruct-MATH-augmented-synthetic

NaNK
llama
1
0

Llama-3.2-1B-Instruct-MATH-synthetic-augmented

NaNK
llama
1
0

Llama-3.2-1B-Instruct-touch-rugby-synth-1epochs-20241009-122734-distilled-distilled

NaNK
llama
1
0

song-birds

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

—
1
0

Llama-3.2-1B-Instruct_gsm8k_rl_step2

NaNK
llama
1
0

Llama-3.2-1B-Instruct_ORPO_1_2p5em5lr

NaNK
llama
1
0

soar-sft-21-jul

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

gemini_synth_50_random_split_1_training-23jul-1epoch

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

qwen-synth_1-train-23jul-3epoch

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

Qwen3-4B-ds20250724_131808-20250724-123014

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

ddp-demo-2

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

Qwen3-4B_ds-arc-agi-2-partial-100-c2806_ds-datasets-c1

- Developed by: Trelis - License: apache-2.0 - Finetuned from model : Trelis/Qwen3-4Bds-arc-agi-2-partial-100-c2806 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

NaNK
license:apache-2.0
1
0

Mistral-7B-Instruct-v0.1-function-calling-v2

NaNK
—
0
33

Mixtral-8x7B-Instruct-v0.1-function-calling-v3

NaNK
—
0
32

openchat_3.5-function-calling-v3

—
0
20

Phi-3-mini-128k-instruct-function-calling

—
0
14

Mistral-7B-Instruct-v0.1-Summarize-16k

NaNK
license:apache-2.0
0
10

Mistral-7B-Instruct-v0.1-function-calling-v3

NaNK
llama
0
9

deepseek-llm-67b-chat-function-calling-v3

NaNK
llama
0
8

Tiny

llama
0
7

Llama-2-7b-chat-hf-function-calling-GGML

NaNK
llama
0
6

CodeLlama-34b-Instruct-hf-function-calling-v2

NaNK
llama
0
6

Yi-6B-200K-Llamafied-function-calling-v2

NaNK
llama
0
6

Mistral 7B Instruct V0.1 Summarize 64k

NaNK
—
0
6

zephyr-7b-beta-function-calling-v2

NaNK
—
0
5

Yi-34B-200K-Llamafied-function-calling-v2

NaNK
llama
0
5

Yi-34B-200K-Llamafied-chat-SFT-function-calling-v3

NaNK
llama
0
5

SUS-Chat-34B-function-calling-v3

NaNK
llama
0
5

Llama-2-13b-chat-hf-function-calling

NaNK
llama
0
4

Llama-2-13b-chat-hf-function-calling-v2

NaNK
llama
0
4

CodeLlama-34b-Instruct-hf-function-calling-adapters-v2

NaNK
llama
0
4

Llama-2-7b-chat-hf-function-calling-adapters-v2

NaNK
llama
0
3

Llama-2-70b-chat-hf-function-calling-adapters-v2

NaNK
llama
0
3

Llama-2-70b-chat-hf-function-calling-v2

NaNK
llama
0
3

deepseek-coder-6.7b-instruct-function-calling-v2

NaNK
llama
0
3

deepseek-coder-33b-instruct-function-calling-v3

NaNK
llama
0
3

TinyLlama-1.1B-Chat-v0.3-GGUF

NaNK
tinyllama
0
2

deepseek-coder-1.3b-instruct-function-calling-v2

NaNK
llama
0
2

deepseek-coder-33b-instruct-function-calling-v2

NaNK
llama
0
2

Yi-6B-200K-Llamafied-function-calling-adapters-v2

NaNK
—
0
2

Yi-6B-200K-Llamafied-chat-SFT-adapters

NaNK
base_model:larryvrh/Yi-6B-200K-Llamafied
0
2

Yi-34B-200K-Llamafied-chat-SFT-function-calling-v2

NaNK
llama
0
2

DeciLM-7B-instruct-function-calling-v3

NaNK
—
0
2

deepseek-coder-6.7b-instruct-function-calling-adapters-v2

NaNK
—
0
1

deepseek-coder-1.3b-instruct-function-calling-adapters-v2

NaNK
—
0
1

TinyLlama-1.1B-4k-chat-SFT-DPO-adapters

NaNK
base_model:Trelis/TinyLlama-1.1B-4k-chat-SFT
0
1

TinyLlama-1.1B-4k-chat-SFT-DPO

NaNK
llama
0
1

Yi-34B-200K-Llamafied-function-calling-adapters-v2

NaNK
—
0
1

Yi-6B-200K-Llamafied-chat-SFT

NaNK
llama
0
1

Yi-34B-200K-Llamafied-chat-SFT-function-calling-v2-AWQ

NaNK
llama
0
1

Mixtral-8x7B-Instruct-v0.1-function-calling-adapters-v3

NaNK
—
0
1

OpenELM-270M-instruct-ORPO

—
0
1

idefics2-8b-chatty-bf16

NaNK
license:apache-2.0
0
1

Meta-Llama-3-8B-Instruct-Gaeilge-Gaeilge

NaNK
llama
0
1

all-MiniLM-L12-v2-ft-pairs

NaNK
—
0
1