ConeML/coneml-1.2b-experimental
Text Generation • 1B • Updated • 362 • 2
Ahmed Morsi
eramax
AI & ML interests
None yet
Recent Activity
liked a model about 17 hours ago
ConeML/coneml-1.2b-experimental liked a model about 17 hours ago
speakleash/Bielik-11B-v3.1-Instruct-GGUF liked a model about 17 hours ago
speakleash/Bielik-11B-v3.1-InstructOrganizations
None yet
liked 9
models about 17 hours ago
speakleash/Bielik-11B-v3.1-Instruct-GGUF
11B • Updated • 1.13k • 6
speakleash/Bielik-11B-v3.1-Instruct
Text Generation • 11B • Updated • 47 • 14
MiniMaxAI/MiniMax-H3-Image
Text-to-Image • Updated • 143k • 620
empero-ai/Qwythos-9B-v2-GGUF
Image-Text-to-Text • 9B • Updated • 257k • 331
xtools-at/Qwen3.5-4B-MultiDistill-3xMerge-UNCENSORED-heretic
Text Generation • 5B • Updated • 774 • 2
xtools-at/Qwen3.5-9B-Claude-3xMerge-UNCENSORED-heretic
Text Generation • 9B • Updated • 965 • 3
xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
Text Generation • 9B • Updated • 16.7k • 1.46k
sergiopaniego/Qwen3.5-2B-SmolDataEnvs-SFT-500
Image-Text-to-Text • 2B • Updated • 15 • 1
reacted to sergiopaniego's post with 🔥 about 17 hours ago
Post
2,187
New post-training example: SFT on agent traces with TRL
→ A large model works as a coding agent in OpenCode, run through OpenEnv
→ The tasks it solves become the training data
→ A 2B model goes from 5.5% to 34.4% on held-out tasks
About 500 traces get most of the gain. Five times more add only 3 to 4 points, so SFT gets the agent working and RL has to do the rest
Full guide, with the models, traces and every rollout open:
https://github.com/huggingface/trl/tree/main/examples/sft_agent_traces
→ A large model works as a coding agent in OpenCode, run through OpenEnv
→ The tasks it solves become the training data
→ A 2B model goes from 5.5% to 34.4% on held-out tasks
About 500 traces get most of the gain. Five times more add only 3 to 4 points, so SFT gets the agent working and RL has to do the rest
Full guide, with the models, traces and every rollout open:
https://github.com/huggingface/trl/tree/main/examples/sft_agent_traces
- 1 reply
liked 2
models 1 day ago
liked 4
models 4 days ago
updated a
collection 4 days ago
reacted to Quazim0t0's post with 🔥 4 days ago
Post
7,432
Quazim0t0/Qwenx86-4B-compact
▶️ See it in action: Quazim0t0/Qwenx86-Debugger . Walk through actual recorded tool calls: the conversation, x86 registers and flags, code at the program counter, RAM and machine output, with all verified blocks on a timeline.
Qwen3.5-4B with a 64-bit x86 computer compiled into its weights: 13 transformer layers ahead of Qwen's own. There are no learned weights in them; all of their weights are computed by a compiler. Qwen invokes the computer through its own tool calls (<tool_call>), and the computer in the weights executes the tool. Calculator, Python, C compiler, notes store, physics/chemistry lookup and Python-docs lookup are all firmware in the checkpoint. This is the compact checkpoint: ~9 GB GPU memory, so it fits on a 16 GB GPU.
Edit: GGUF Release: Quazim0t0/Qwenx86-4B-GGUF
Credits: Qwenputer by Divyansh Agrawal (@divagr1925 , github.com/divagr18/qwenputer, MIT)
▶️ See it in action: Quazim0t0/Qwenx86-Debugger . Walk through actual recorded tool calls: the conversation, x86 registers and flags, code at the program counter, RAM and machine output, with all verified blocks on a timeline.
Qwen3.5-4B with a 64-bit x86 computer compiled into its weights: 13 transformer layers ahead of Qwen's own. There are no learned weights in them; all of their weights are computed by a compiler. Qwen invokes the computer through its own tool calls (<tool_call>), and the computer in the weights executes the tool. Calculator, Python, C compiler, notes store, physics/chemistry lookup and Python-docs lookup are all firmware in the checkpoint. This is the compact checkpoint: ~9 GB GPU memory, so it fits on a 16 GB GPU.
Edit: GGUF Release: Quazim0t0/Qwenx86-4B-GGUF
Credits: Qwenputer by Divyansh Agrawal (@divagr1925 , github.com/divagr18/qwenputer, MIT)
- 1 reply
liked 2
models 4 days ago
