Instructions to use basically-experimental/Pebble-50M-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basically-experimental/Pebble-50M-beta with Transformers:

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

pipe = pipeline("text-generation", model="basically-experimental/Pebble-50M-beta", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("basically-experimental/Pebble-50M-beta", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use basically-experimental/Pebble-50M-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "basically-experimental/Pebble-50M-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basically-experimental/Pebble-50M-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/basically-experimental/Pebble-50M-beta

SGLang

How to use basically-experimental/Pebble-50M-beta 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 "basically-experimental/Pebble-50M-beta" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basically-experimental/Pebble-50M-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "basically-experimental/Pebble-50M-beta" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basically-experimental/Pebble-50M-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use basically-experimental/Pebble-50M-beta with Docker Model Runner:
```
docker model run hf.co/basically-experimental/Pebble-50M-beta
```

Hoglet-33 commited on Sep 6

Commit

ceb9215

verified ·

1 Parent(s): 56b4186

SFT step 50

Browse files

Files changed (4) hide show

config.json +16 -16
model.safetensors +2 -2
special_tokens_map.json +1 -1
tokenizer_config.json +19 -8

config.json CHANGED Viewed

@@ -2,31 +2,31 @@
   "architectures": [
     "PebbleForCausalLM"
   ],
-  "model_type": "pebble_50m",
   "auto_map": {
     "AutoConfig": "configuration_pebble.PebbleConfig",
     "AutoModelForCausalLM": "modeling_pebble.PebbleForCausalLM"
   },
-  "vocab_size": 16384,
-  "hidden_size": 768,
-  "intermediate_size": 3072,
-  "num_hidden_layers": 8,
-  "num_attention_heads": 12,
   "block_pattern": "mmma|mmma",
   "hybrid_ratio": "3:1 mamba2:attention",
-  "max_position_embeddings": 16384,
-  "rms_norm_eps": 1e-06,
-  "tie_word_embeddings": true,
   "mamba2": {
-    "d_state": 128,
     "d_conv": 4,
     "expand": 2,
     "headdim": 64,
     "use_mem_eff_path": true
   },
-  "attention": {
-    "rope_theta": 10000.0,
-    "is_causal": true
-  },
-  "torch_dtype": "float32"
-}

   "architectures": [
     "PebbleForCausalLM"
   ],
+  "attention": {
+    "is_causal": true,
+    "rope_theta": 10000.0
+  },
   "auto_map": {
     "AutoConfig": "configuration_pebble.PebbleConfig",
     "AutoModelForCausalLM": "modeling_pebble.PebbleForCausalLM"
   },
   "block_pattern": "mmma|mmma",
+  "dtype": "bfloat16",
+  "hidden_size": 768,
   "hybrid_ratio": "3:1 mamba2:attention",
+  "intermediate_size": 3072,
   "mamba2": {
     "d_conv": 4,
+    "d_state": 128,
     "expand": 2,
     "headdim": 64,
     "use_mem_eff_path": true
   },
+  "max_position_embeddings": 16384,
+  "model_type": "pebble_50m",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
+  "rms_norm_eps": 1e-06,
+  "transformers_version": "4.57.1",
+  "vocab_size": 16384
+}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5579714d6c3353fa168e9d51a6f4389cf1a6df42d84333d57dcea18ee6342ced
-size 247675816

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f0f2ad1c51c9f4401748fba5f2d91906fe06095a1e5d91b14173873b064b150
+size 98675424

special_tokens_map.json CHANGED Viewed

@@ -13,4 +13,4 @@
     "rstrip": false,
     "single_word": false
   }
-}

     "rstrip": false,
     "single_word": false
   }
+}

tokenizer_config.json CHANGED Viewed

@@ -1,16 +1,27 @@
 {
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "bos_token": "<|eos|>",
-  "eos_token": "<|eos|>",
-  "pad_token": null,
-  "unk_token": null,
   "add_bos_token": false,
   "add_eos_token": false,
-  "model_max_length": 16384,
   "model_input_names": [
     "input_ids"
   ],
-  "name_or_path": "pebble-bpe-16384",
-  "eos_token_id": 0,
   "vocab_size": 16384
 }

 {
   "add_bos_token": false,
   "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|eos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "eos_token_id": 0,
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids"
   ],
+  "model_max_length": 16384,
+  "pad_token": null,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null,
   "vocab_size": 16384
 }