Instructions to use prithivMLmods/Calcium-Opus-14B-Elite4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Calcium-Opus-14B-Elite4 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Calcium-Opus-14B-Elite4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Calcium-Opus-14B-Elite4")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Calcium-Opus-14B-Elite4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prithivMLmods/Calcium-Opus-14B-Elite4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Calcium-Opus-14B-Elite4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Calcium-Opus-14B-Elite4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Calcium-Opus-14B-Elite4

SGLang

How to use prithivMLmods/Calcium-Opus-14B-Elite4 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 "prithivMLmods/Calcium-Opus-14B-Elite4" \
    --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": "prithivMLmods/Calcium-Opus-14B-Elite4",
		"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 "prithivMLmods/Calcium-Opus-14B-Elite4" \
        --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": "prithivMLmods/Calcium-Opus-14B-Elite4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Calcium-Opus-14B-Elite4 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Calcium-Opus-14B-Elite4
```

prithivMLmods commited on Jan 30, 2025

Commit

8e0d080

verified ·

1 Parent(s): 6efc174

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -8

README.md CHANGED Viewed

@@ -11,6 +11,7 @@ tags:
 - Calcium
 - Opus
 - 14B
 model-index:
 - name: Calcium-Opus-14B-Elite4
   results:
@@ -28,7 +29,8 @@ model-index:
       value: 61.12
       name: averaged accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -44,7 +46,8 @@ model-index:
       value: 45.21
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -60,7 +63,8 @@ model-index:
       value: 23.04
       name: exact match
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -76,7 +80,8 @@ model-index:
       value: 14.09
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -91,7 +96,8 @@ model-index:
       value: 17.69
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -108,7 +114,8 @@ model-index:
       value: 46.1
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
 ---
@@ -212,5 +219,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
 |MATH Lvl 5 (4-Shot)|    23.04|
 |GPQA (0-shot)      |    14.09|
 |MuSR (0-shot)      |    17.69|
-|MMLU-PRO (5-shot)  |    46.10|

 - Calcium
 - Opus
 - 14B
+- qwq
 model-index:
 - name: Calcium-Opus-14B-Elite4
   results:
       value: 61.12
       name: averaged accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 45.21
       name: normalized accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 23.04
       name: exact match
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 14.09
       name: acc_norm
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 17.69
       name: acc_norm
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 46.1
       name: accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Elite4
       name: Open LLM Leaderboard
 ---
 |MATH Lvl 5 (4-Shot)|    23.04|
 |GPQA (0-shot)      |    14.09|
 |MuSR (0-shot)      |    17.69|
+|MMLU-PRO (5-shot)  |    46.10|