Text Generation
Transformers
Safetensors
Serbian
qwen3_5
image-text-to-text
unsloth
merged-model
multi-label-classification
emotion-recognition
serbian
social-media
json-output
conversational
Instructions to use te-sla/serbian-emotion-qwen3.5-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use te-sla/serbian-emotion-qwen3.5-9b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="te-sla/serbian-emotion-qwen3.5-9b") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("te-sla/serbian-emotion-qwen3.5-9b") model = AutoModelForMultimodalLM.from_pretrained("te-sla/serbian-emotion-qwen3.5-9b", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use te-sla/serbian-emotion-qwen3.5-9b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "te-sla/serbian-emotion-qwen3.5-9b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "te-sla/serbian-emotion-qwen3.5-9b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/te-sla/serbian-emotion-qwen3.5-9b
- SGLang
How to use te-sla/serbian-emotion-qwen3.5-9b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "te-sla/serbian-emotion-qwen3.5-9b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "te-sla/serbian-emotion-qwen3.5-9b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "te-sla/serbian-emotion-qwen3.5-9b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "te-sla/serbian-emotion-qwen3.5-9b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use te-sla/serbian-emotion-qwen3.5-9b with Docker Model Runner:
docker model run hf.co/te-sla/serbian-emotion-qwen3.5-9b
Update model-card notes for public release
Browse files- README.md +3 -3
- artifact_manifest.json +92 -92
README.md
CHANGED
|
@@ -27,7 +27,7 @@ This is the direct-load, merged BF16 form of
|
|
| 27 |
It combines the prespecified seed-42 LoRA adapter with
|
| 28 |
[`unsloth/Qwen3.5-9B`](https://huggingface.co/unsloth/Qwen3.5-9B) at pinned revision
|
| 29 |
`005429cee5cb648998cf2b70eebdd83175989c9a`, so users load one repository rather than loading a base
|
| 30 |
-
model and then attaching a PEFT adapter. The
|
| 31 |
`te-sla/serbian-emotion-qwen3.5-9b`.
|
| 32 |
|
| 33 |
This is deployment packaging of the same evaluated model, not another training run, seed, or ranking
|
|
@@ -180,5 +180,5 @@ neutral, or more-than-two-label outputs without repair.
|
|
| 180 |
|
| 181 |
## Citation
|
| 182 |
|
| 183 |
-
The final paper identifier and citation are pending.
|
| 184 |
-
|
|
|
|
| 27 |
It combines the prespecified seed-42 LoRA adapter with
|
| 28 |
[`unsloth/Qwen3.5-9B`](https://huggingface.co/unsloth/Qwen3.5-9B) at pinned revision
|
| 29 |
`005429cee5cb648998cf2b70eebdd83175989c9a`, so users load one repository rather than loading a base
|
| 30 |
+
model and then attaching a PEFT adapter. The repository ID is
|
| 31 |
`te-sla/serbian-emotion-qwen3.5-9b`.
|
| 32 |
|
| 33 |
This is deployment packaging of the same evaluated model, not another training run, seed, or ranking
|
|
|
|
| 180 |
|
| 181 |
## Citation
|
| 182 |
|
| 183 |
+
The final paper identifier and citation are pending. The verified paper link and shared
|
| 184 |
+
portfolio citation will be added to both Qwen repositories when available.
|
artifact_manifest.json
CHANGED
|
@@ -1,94 +1,94 @@
|
|
| 1 |
-
{
|
| 2 |
-
"schema_version": 1,
|
| 3 |
-
"status": "merged_full_model_verified_locally",
|
| 4 |
-
"repo_id": "te-sla/serbian-emotion-qwen3.5-9b",
|
| 5 |
-
"artifact_kind": "merged_full_model",
|
| 6 |
-
"artifact_seed": 42,
|
| 7 |
-
"base_model": "unsloth/Qwen3.5-9B",
|
| 8 |
-
"base_revision": "005429cee5cb648998cf2b70eebdd83175989c9a",
|
| 9 |
-
"source_adapter_repo": "te-sla/serbian-emotion-qwen3.5-9b-lora",
|
| 10 |
-
"merge_method": "peft_safe_merge_and_unload_bf16",
|
| 11 |
-
"new_training_performed": false,
|
| 12 |
-
"files": [
|
| 13 |
-
{
|
| 14 |
-
"path": "chat_template.jinja",
|
| 15 |
-
"bytes": 8150,
|
| 16 |
-
"sha256": "dca767ce96946decf01e87358183070ce953a06a1033f06e92295193d8a432f6"
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"path": "config.json",
|
| 20 |
-
"bytes": 3094,
|
| 21 |
-
"sha256": "b537ee1701444bc30fec9b096a9261e0081338b4ed9cfc5b4f7e3f15861bfb30"
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"path": "generation_config.json",
|
| 25 |
-
"bytes": 148,
|
| 26 |
-
"sha256": "7fe7884646929f2846be3a608130609c3ba31a185478309e99004cf97d5fed1f"
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"path": "merge_provenance.json",
|
| 30 |
-
"bytes": 1040,
|
| 31 |
-
"sha256": "b296013447a4e91d95e438ef38e5451d4f58ba1fc09a0ccd39656a33f96f90cf"
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"path": "merge_smoke_test.json",
|
| 35 |
-
"bytes": 3228,
|
| 36 |
-
"sha256": "6bbf189d39a49d9f531076d8e36537fdcdc4d2c95caf949f44f357500c67c0de"
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"path": "model-00001-of-00004.safetensors",
|
| 40 |
-
"bytes": 4942748568,
|
| 41 |
-
"sha256": "6ca0558cf50524a95c50952da98f065249643d68a99bd89333a0f7f3237a486b"
|
| 42 |
-
},
|
| 43 |
-
{
|
| 44 |
-
"path": "model-00002-of-00004.safetensors",
|
| 45 |
-
"bytes": 4987947712,
|
| 46 |
-
"sha256": "b867f50f713ecf5c26213708541d20cad559693fea85981782c3fe188a1f9cc6"
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"path": "model-00003-of-00004.safetensors",
|
| 50 |
-
"bytes": 4955016248,
|
| 51 |
-
"sha256": "78d26024763bada27bc21bf4f3b4372aa158969ea1b7727a6046526ec08bbdac"
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"path": "model-00004-of-00004.safetensors",
|
| 55 |
-
"bytes": 3934824688,
|
| 56 |
-
"sha256": "a370189389aa518c5c7fe5dd077e1a4da0d7bc53a3c2f32dae3af53a85730353"
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"path": "model.safetensors.index.json",
|
| 60 |
-
"bytes": 87796,
|
| 61 |
-
"sha256": "c263bcdf5fd0dedec1b2a09e3af3077eb70b5b3a248cf6c26a8020c8ab7b3d5b"
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"path": "processor_config.json",
|
| 65 |
-
"bytes": 1359,
|
| 66 |
-
"sha256": "0c29f9491e769aabbc389ad5912127cf6d9d5fceda2db8767f73d48131348c81"
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"path": "publication_evidence.json",
|
| 70 |
-
"bytes": 646,
|
| 71 |
-
"sha256": "4c63241f3a1d942fefcb3de98464c315627947c9764401ec2a0101e81b46ad69"
|
| 72 |
-
},
|
| 73 |
{
|
| 74 |
"path": "README.md",
|
| 75 |
-
"bytes":
|
| 76 |
-
"sha256": "
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"path": "source_adapter_manifest.json",
|
| 80 |
-
"bytes": 1811,
|
| 81 |
-
"sha256": "b572e280eff98879a4e78ef331521a5e971758ed52602110cdb2d140c0547e27"
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"path": "tokenizer.json",
|
| 85 |
-
"bytes": 19989610,
|
| 86 |
-
"sha256": "92eafab4cd0ac0b8b06fcc0ffb8599a81ca9a55a7b2fc78a4416b27d561c7c80"
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"path": "tokenizer_config.json",
|
| 90 |
-
"bytes": 7460,
|
| 91 |
-
"sha256": "4e463cfd5bda02651d6edfc2712ded9e7b37014a056ebd5e3ded4ff3155e47a3"
|
| 92 |
-
}
|
| 93 |
-
]
|
| 94 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"status": "merged_full_model_verified_locally",
|
| 4 |
+
"repo_id": "te-sla/serbian-emotion-qwen3.5-9b",
|
| 5 |
+
"artifact_kind": "merged_full_model",
|
| 6 |
+
"artifact_seed": 42,
|
| 7 |
+
"base_model": "unsloth/Qwen3.5-9B",
|
| 8 |
+
"base_revision": "005429cee5cb648998cf2b70eebdd83175989c9a",
|
| 9 |
+
"source_adapter_repo": "te-sla/serbian-emotion-qwen3.5-9b-lora",
|
| 10 |
+
"merge_method": "peft_safe_merge_and_unload_bf16",
|
| 11 |
+
"new_training_performed": false,
|
| 12 |
+
"files": [
|
| 13 |
+
{
|
| 14 |
+
"path": "chat_template.jinja",
|
| 15 |
+
"bytes": 8150,
|
| 16 |
+
"sha256": "dca767ce96946decf01e87358183070ce953a06a1033f06e92295193d8a432f6"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"path": "config.json",
|
| 20 |
+
"bytes": 3094,
|
| 21 |
+
"sha256": "b537ee1701444bc30fec9b096a9261e0081338b4ed9cfc5b4f7e3f15861bfb30"
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"path": "generation_config.json",
|
| 25 |
+
"bytes": 148,
|
| 26 |
+
"sha256": "7fe7884646929f2846be3a608130609c3ba31a185478309e99004cf97d5fed1f"
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"path": "merge_provenance.json",
|
| 30 |
+
"bytes": 1040,
|
| 31 |
+
"sha256": "b296013447a4e91d95e438ef38e5451d4f58ba1fc09a0ccd39656a33f96f90cf"
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"path": "merge_smoke_test.json",
|
| 35 |
+
"bytes": 3228,
|
| 36 |
+
"sha256": "6bbf189d39a49d9f531076d8e36537fdcdc4d2c95caf949f44f357500c67c0de"
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"path": "model-00001-of-00004.safetensors",
|
| 40 |
+
"bytes": 4942748568,
|
| 41 |
+
"sha256": "6ca0558cf50524a95c50952da98f065249643d68a99bd89333a0f7f3237a486b"
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"path": "model-00002-of-00004.safetensors",
|
| 45 |
+
"bytes": 4987947712,
|
| 46 |
+
"sha256": "b867f50f713ecf5c26213708541d20cad559693fea85981782c3fe188a1f9cc6"
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"path": "model-00003-of-00004.safetensors",
|
| 50 |
+
"bytes": 4955016248,
|
| 51 |
+
"sha256": "78d26024763bada27bc21bf4f3b4372aa158969ea1b7727a6046526ec08bbdac"
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"path": "model-00004-of-00004.safetensors",
|
| 55 |
+
"bytes": 3934824688,
|
| 56 |
+
"sha256": "a370189389aa518c5c7fe5dd077e1a4da0d7bc53a3c2f32dae3af53a85730353"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"path": "model.safetensors.index.json",
|
| 60 |
+
"bytes": 87796,
|
| 61 |
+
"sha256": "c263bcdf5fd0dedec1b2a09e3af3077eb70b5b3a248cf6c26a8020c8ab7b3d5b"
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"path": "processor_config.json",
|
| 65 |
+
"bytes": 1359,
|
| 66 |
+
"sha256": "0c29f9491e769aabbc389ad5912127cf6d9d5fceda2db8767f73d48131348c81"
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"path": "publication_evidence.json",
|
| 70 |
+
"bytes": 646,
|
| 71 |
+
"sha256": "4c63241f3a1d942fefcb3de98464c315627947c9764401ec2a0101e81b46ad69"
|
| 72 |
+
},
|
| 73 |
{
|
| 74 |
"path": "README.md",
|
| 75 |
+
"bytes": 7210,
|
| 76 |
+
"sha256": "98e51f6be043e946e5928f71f89368fbb859b7e55a28779bd1b586def7c616b6"
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"path": "source_adapter_manifest.json",
|
| 80 |
+
"bytes": 1811,
|
| 81 |
+
"sha256": "b572e280eff98879a4e78ef331521a5e971758ed52602110cdb2d140c0547e27"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"path": "tokenizer.json",
|
| 85 |
+
"bytes": 19989610,
|
| 86 |
+
"sha256": "92eafab4cd0ac0b8b06fcc0ffb8599a81ca9a55a7b2fc78a4416b27d561c7c80"
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"path": "tokenizer_config.json",
|
| 90 |
+
"bytes": 7460,
|
| 91 |
+
"sha256": "4e463cfd5bda02651d6edfc2712ded9e7b37014a056ebd5e3ded4ff3155e47a3"
|
| 92 |
+
}
|
| 93 |
+
]
|
| 94 |
+
}
|