Instructions to use AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0 with Transformers:

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

pipe = pipeline("text-generation", model="AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0")
model = AutoModelForCausalLM.from_pretrained("AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0", 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 AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0

SGLang

How to use AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0 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 "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0" \
    --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": "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0",
		"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 "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0" \
        --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": "AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0 with Docker Model Runner:
```
docker model run hf.co/AmberYifan/capsdnum-marin-8b-base-code_random_b1000_s0
```

AmberYifan commited on Jul 17

Commit

776c30b

verified ·

1 Parent(s): a82b679

capmix single-domain code_random_b1000_s0 (marin-8b-base)

Browse files

Files changed (10) hide show

README.md +1 -1
all_results.json +5 -5
checkpoint-16/model.safetensors +1 -1
checkpoint-16/trainer_state.json +1 -1
checkpoint-16/training_args.bin +1 -1
model.safetensors +1 -1
train_results.json +5 -5
trainer_log.jsonl +1 -1
trainer_state.json +6 -6
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # marin-8b-base_code_random_b1000_s0
-This model is a fine-tuned version of [marin-community/marin-8b-base](https://huggingface.co/marin-community/marin-8b-base) on the capsd_marin-8b-base-n80000-code__mix_code_random_b1000_s0 dataset.
 ## Model description

 # marin-8b-base_code_random_b1000_s0
+This model is a fine-tuned version of [marin-community/marin-8b-base](https://huggingface.co/marin-community/marin-8b-base) on the capsd_marin-8b-base-n80000-opc__mix_code_random_b1000_s0 dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "total_flos": 591742894080.0,
-    "train_loss": 0.3349860608577728,
-    "train_runtime": 513.1196,
-    "train_samples_per_second": 1.949,
-    "train_steps_per_second": 0.031
 }

 {
     "epoch": 1.0,
+    "total_flos": 293928960000.0,
+    "train_loss": 0.44835618138313293,
+    "train_runtime": 505.4764,
+    "train_samples_per_second": 1.978,
+    "train_steps_per_second": 0.032
 }

checkpoint-16/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654864173588567cdccafcc15328cfae9dd21795fa0f4f1ff79c051433f4dc37
 size 16060556616

 version https://git-lfs.github.com/spec/v1
+oid sha256:890d393c33bb08577646ebfd9e4fccef9a85963af34c7f8008bd615f67df865f
 size 16060556616

checkpoint-16/trainer_state.json CHANGED Viewed

@@ -26,7 +26,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 591742894080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

       "attributes": {}
     }
   },
+  "total_flos": 293928960000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-16/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2f90276c855ffd23f7dc7ce13101ddaf5c4523206c9baeb55816b8930bd272
 size 7761

 version https://git-lfs.github.com/spec/v1
+oid sha256:144ab5073ac7c48be0a50e41fdda757cc8d9ffd5204d108bac9f585cf5726e43
 size 7761

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654864173588567cdccafcc15328cfae9dd21795fa0f4f1ff79c051433f4dc37
 size 16060556616

 version https://git-lfs.github.com/spec/v1
+oid sha256:890d393c33bb08577646ebfd9e4fccef9a85963af34c7f8008bd615f67df865f
 size 16060556616

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "total_flos": 591742894080.0,
-    "train_loss": 0.3349860608577728,
-    "train_runtime": 513.1196,
-    "train_samples_per_second": 1.949,
-    "train_steps_per_second": 0.031
 }

 {
     "epoch": 1.0,
+    "total_flos": 293928960000.0,
+    "train_loss": 0.44835618138313293,
+    "train_runtime": 505.4764,
+    "train_samples_per_second": 1.978,
+    "train_steps_per_second": 0.032
 }

trainer_log.jsonl CHANGED Viewed

	@@ -1 +1 @@
1	- {"current_steps": 16, "total_steps": 16, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:08:33", "remaining_time": "0:00:00"}


1	+ {"current_steps": 16, "total_steps": 16, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:08:25", "remaining_time": "0:00:00"}

trainer_state.json CHANGED Viewed

@@ -12,11 +12,11 @@
     {
       "epoch": 1.0,
       "step": 16,
-      "total_flos": 591742894080.0,
-      "train_loss": 0.3349860608577728,
-      "train_runtime": 513.1196,
-      "train_samples_per_second": 1.949,
-      "train_steps_per_second": 0.031
     }
   ],
   "logging_steps": 50,
@@ -36,7 +36,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 591742894080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

     {
       "epoch": 1.0,
       "step": 16,
+      "total_flos": 293928960000.0,
+      "train_loss": 0.44835618138313293,
+      "train_runtime": 505.4764,
+      "train_samples_per_second": 1.978,
+      "train_steps_per_second": 0.032
     }
   ],
   "logging_steps": 50,
       "attributes": {}
     }
   },
+  "total_flos": 293928960000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2f90276c855ffd23f7dc7ce13101ddaf5c4523206c9baeb55816b8930bd272
 size 7761

 version https://git-lfs.github.com/spec/v1
+oid sha256:144ab5073ac7c48be0a50e41fdda757cc8d9ffd5204d108bac9f585cf5726e43
 size 7761