Instructions to use InterstellarCG/HRM-Text-1B-Code-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InterstellarCG/HRM-Text-1B-Code-FT with Transformers:

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

pipe = pipeline("text-generation", model="InterstellarCG/HRM-Text-1B-Code-FT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")
model = AutoModelForMultimodalLM.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InterstellarCG/HRM-Text-1B-Code-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InterstellarCG/HRM-Text-1B-Code-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InterstellarCG/HRM-Text-1B-Code-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InterstellarCG/HRM-Text-1B-Code-FT

SGLang

How to use InterstellarCG/HRM-Text-1B-Code-FT 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 "InterstellarCG/HRM-Text-1B-Code-FT" \
    --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": "InterstellarCG/HRM-Text-1B-Code-FT",
		"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 "InterstellarCG/HRM-Text-1B-Code-FT" \
        --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": "InterstellarCG/HRM-Text-1B-Code-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InterstellarCG/HRM-Text-1B-Code-FT with Docker Model Runner:
```
docker model run hf.co/InterstellarCG/HRM-Text-1B-Code-FT
```

InterstellarCG commited on 15 days ago

Commit

856cf68

verified ·

1 Parent(s): f837c8b

Upload HRM-Text-1B Code Fine-tuned epoch 3

Browse files

Files changed (5) hide show

README.md +52 -0
config.json +26 -0
model.safetensors +3 -0
tokenizer.json +0 -0
tokenizer_config.json +12 -0

README.md ADDED Viewed

	@@ -0,0 +1,52 @@

+---
+license: mit
+language:
+- en
+library_name: transformers
+tags:
+- code
+- text-generation
+- hrm-text
+- fine-tuned
+base_model: sapientai/hrm-text-1b
+---
+# HRM-Text-1B Code Fine-tuned
+Fine-tuned from HRM-Text-1B on combined code dataset (192M tokens).
+## Training Details
+- **Base**: HRM-Text-1B (stacked from HTML/CSS 100k checkpoint)
+- **Dataset**: Combined code (Python, JavaScript, TypeScript, SQL, HTML/CSS)
+- **Tokens**: 192M
+- **Epochs**: 3
+- **Learning rate**: 1e-5
+## Capabilities
+- Python code generation
+- JavaScript functions
+- SQL queries
+- General QA (improved over base)
+## Limitations
+- Weak at React/TSX syntax
+- HTML/CSS output can be malformed
+- TypeScript interfaces not well-formed
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")
+tokenizer = AutoTokenizer.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")
+```
+## Evaluation
+| Task | Base | Fine-tuned |
+|------|------|------------|
+| Python (is_prime) | Garbage | Correct |
+| JS (reverse array) | Garbage | Correct |
+| SQL (join query) | Garbage | Correct |
+| QA (Paris capital) | Garbage | Correct |

config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "model_type": "hrm_text",
+  "architectures": [
+    "HrmTextForCausalLM"
+  ],
+  "vocab_size": 65536,
+  "hidden_size": 1536,
+  "intermediate_size": 4096,
+  "num_hidden_layers": 32,
+  "num_attention_heads": 12,
+  "num_key_value_heads": 12,
+  "head_dim": 128,
+  "H_cycles": 2,
+  "L_cycles": 3,
+  "L_bp_steps": [
+    0,
+    3
+  ],
+  "max_position_embeddings": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "initializer_range": 0.025515518153991442,
+  "embedding_scale": 39.191835884530846,
+  "prefix_lm": true
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1da7577c9f7c9e88c136d7529eae5c3e638dde9874c1793725f7a2c2600eb1bb
+size 2365606568

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|box_end|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}