Instructions to use tegana/model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tegana/model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "tegana/model")

Transformers

How to use tegana/model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tegana/model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tegana/model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tegana/model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tegana/model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tegana/model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tegana/model

SGLang

How to use tegana/model 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 "tegana/model" \
    --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": "tegana/model",
		"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 "tegana/model" \
        --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": "tegana/model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tegana/model with Docker Model Runner:
```
docker model run hf.co/tegana/model
```

tegana commited on Mar 10

Commit

10194a2

verified ·

1 Parent(s): eb3b577

Training in progress, step 252

Browse files

Files changed (8) hide show

.gitattributes +1 -0
adapter_config.json +46 -0
adapter_model.safetensors +3 -0
chat_template.jinja +54 -0
tokenizer.json +3 -0
tokenizer_config.json +30 -0
trainer_log.jsonl +28 -0
training_args.bin +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcde4a9e8531794a7c6f8e035d65e0627142045d9ff92d2679d86dc19d834d5
+size 295488936

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,54 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl ADDED Viewed

	@@ -0,0 +1,28 @@

+{"current_steps": 10, "total_steps": 252, "loss": 0.5328742027282715, "lr": 3.461538461538462e-05, "epoch": 0.11940298507462686, "percentage": 3.97, "elapsed_time": "0:02:47", "remaining_time": "1:07:31"}
+{"current_steps": 20, "total_steps": 252, "loss": 0.28172030448913576, "lr": 7.307692307692307e-05, "epoch": 0.23880597014925373, "percentage": 7.94, "elapsed_time": "0:05:41", "remaining_time": "1:05:56"}
+{"current_steps": 30, "total_steps": 252, "loss": 0.22340788841247558, "lr": 9.995652871840006e-05, "epoch": 0.3582089552238806, "percentage": 11.9, "elapsed_time": "0:08:54", "remaining_time": "1:05:58"}
+{"current_steps": 40, "total_steps": 252, "loss": 0.19026432037353516, "lr": 9.918580696928205e-05, "epoch": 0.47761194029850745, "percentage": 15.87, "elapsed_time": "0:11:59", "remaining_time": "1:03:32"}
+{"current_steps": 50, "total_steps": 252, "loss": 0.1776690363883972, "lr": 9.746617916180905e-05, "epoch": 0.5970149253731343, "percentage": 19.84, "elapsed_time": "0:15:08", "remaining_time": "1:01:11"}
+{"current_steps": 60, "total_steps": 252, "loss": 0.16183719635009766, "lr": 9.483082082658983e-05, "epoch": 0.7164179104477612, "percentage": 23.81, "elapsed_time": "0:18:08", "remaining_time": "0:58:02"}
+{"current_steps": 70, "total_steps": 252, "loss": 0.18729711771011354, "lr": 9.133057401836159e-05, "epoch": 0.835820895522388, "percentage": 27.78, "elapsed_time": "0:21:12", "remaining_time": "0:55:07"}
+{"current_steps": 80, "total_steps": 252, "loss": 0.17510976791381835, "lr": 8.703296645714609e-05, "epoch": 0.9552238805970149, "percentage": 31.75, "elapsed_time": "0:24:14", "remaining_time": "0:52:07"}
+{"current_steps": 90, "total_steps": 252, "loss": 0.15757997035980226, "lr": 8.202090876498144e-05, "epoch": 1.0716417910447762, "percentage": 35.71, "elapsed_time": "0:26:54", "remaining_time": "0:48:26"}
+{"current_steps": 100, "total_steps": 252, "loss": 0.14641659259796141, "lr": 7.639109493149537e-05, "epoch": 1.191044776119403, "percentage": 39.68, "elapsed_time": "0:29:47", "remaining_time": "0:45:16"}
+{"current_steps": 100, "total_steps": 252, "eval_loss": 0.1869809627532959, "epoch": 1.191044776119403, "percentage": 39.68, "elapsed_time": "0:30:00", "remaining_time": "0:45:37"}
+{"current_steps": 110, "total_steps": 252, "loss": 0.11394469738006592, "lr": 7.02521368669762e-05, "epoch": 1.31044776119403, "percentage": 43.65, "elapsed_time": "0:32:56", "remaining_time": "0:42:30"}
+{"current_steps": 120, "total_steps": 252, "loss": 0.11726579666137696, "lr": 6.372246903165446e-05, "epoch": 1.4298507462686567, "percentage": 47.62, "elapsed_time": "0:36:08", "remaining_time": "0:39:44"}
+{"current_steps": 130, "total_steps": 252, "loss": 0.12615565061569214, "lr": 5.692806356566095e-05, "epoch": 1.5492537313432835, "percentage": 51.59, "elapsed_time": "0:39:02", "remaining_time": "0:36:38"}
+{"current_steps": 140, "total_steps": 252, "loss": 0.11287055015563965, "lr": 5e-05, "epoch": 1.6686567164179105, "percentage": 55.56, "elapsed_time": "0:41:52", "remaining_time": "0:33:30"}
+{"current_steps": 150, "total_steps": 252, "loss": 0.10663604736328125, "lr": 4.307193643433907e-05, "epoch": 1.7880597014925375, "percentage": 59.52, "elapsed_time": "0:45:19", "remaining_time": "0:30:48"}
+{"current_steps": 160, "total_steps": 252, "loss": 0.107212233543396, "lr": 3.627753096834555e-05, "epoch": 1.9074626865671642, "percentage": 63.49, "elapsed_time": "0:48:27", "remaining_time": "0:27:51"}
+{"current_steps": 170, "total_steps": 252, "loss": 0.11782596111297608, "lr": 2.9747863133023803e-05, "epoch": 2.023880597014925, "percentage": 67.46, "elapsed_time": "0:51:26", "remaining_time": "0:24:48"}
+{"current_steps": 180, "total_steps": 252, "loss": 0.0834022581577301, "lr": 2.3608905068504637e-05, "epoch": 2.1432835820895524, "percentage": 71.43, "elapsed_time": "0:54:14", "remaining_time": "0:21:41"}
+{"current_steps": 190, "total_steps": 252, "loss": 0.08206533193588257, "lr": 1.7979091235018565e-05, "epoch": 2.262686567164179, "percentage": 75.4, "elapsed_time": "0:57:31", "remaining_time": "0:18:46"}
+{"current_steps": 200, "total_steps": 252, "loss": 0.08110529780387879, "lr": 1.2967033542853917e-05, "epoch": 2.382089552238806, "percentage": 79.37, "elapsed_time": "1:00:32", "remaining_time": "0:15:44"}
+{"current_steps": 200, "total_steps": 252, "eval_loss": 0.1738630086183548, "epoch": 2.382089552238806, "percentage": 79.37, "elapsed_time": "1:00:45", "remaining_time": "0:15:47"}
+{"current_steps": 210, "total_steps": 252, "loss": 0.08261927366256713, "lr": 8.669425981638413e-06, "epoch": 2.5014925373134327, "percentage": 83.33, "elapsed_time": "1:03:33", "remaining_time": "0:12:42"}
+{"current_steps": 220, "total_steps": 252, "loss": 0.08233516216278076, "lr": 5.169179173410177e-06, "epoch": 2.62089552238806, "percentage": 87.3, "elapsed_time": "1:06:23", "remaining_time": "0:09:39"}
+{"current_steps": 230, "total_steps": 252, "loss": 0.07825937271118164, "lr": 2.533820838190959e-06, "epoch": 2.7402985074626867, "percentage": 91.27, "elapsed_time": "1:09:29", "remaining_time": "0:06:38"}
+{"current_steps": 240, "total_steps": 252, "loss": 0.08194915056228638, "lr": 8.141930307179468e-07, "epoch": 2.8597014925373134, "percentage": 95.24, "elapsed_time": "1:12:46", "remaining_time": "0:03:38"}
+{"current_steps": 250, "total_steps": 252, "loss": 0.08224834203720092, "lr": 4.3471281599938295e-08, "epoch": 2.97910447761194, "percentage": 99.21, "elapsed_time": "1:15:55", "remaining_time": "0:00:36"}
+{"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:16:27", "remaining_time": "0:00:00"}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a07b9caae9ac5e97a7c1dadc98f45fdb304d552d5d5b383b06e0e2cf036603e
+size 5649